meta: casely-qa-skill v1.5.0

skills/18072937735/smyx-basic-object-detection-analysis/SKILL.md

@@ -1,156 +0,0 @@
----
-name: "basic-object-detection-analysis"
-description: "Detects people, vehicles, non-motorized vehicles, pets, and parcels appearing in the target area. Supports video stream and image detection, suitable for general security surveillance scenarios. | 基础目标检测技能，检测出目标区域内出现的人、车、非机动车、宠物、包裹，支持视频流和图片检测，适用于通用安防监控场景"
----
-
-# Basic Object Detection Skill | 基础目标检测技能
-
-This capability performs real-time detection on target regions within video streams or images, precisely identifying key
-objects such as personnel, vehicles, non-motorized vehicles, pets, and packages. Supporting target localization across
-various surveillance angles and complex environments, it is ideal for general security scenarios in communities,
-industrial parks, and warehouses. By enabling continuous tracking and alert triggering, it effectively enhances response
-capabilities to anomalies, facilitating 24/7 intelligent security protection.
-
-本技能可对视频流或图片中的目标区域进行实时检测，精准识别出现的人员、车辆、非机动车、宠物及包裹等关键目标。支持多种监控视角与复杂环境下的目标定位，适用于社区、园区、仓库等通用安防监控场景。通过持续跟踪与告警触发，有效提升异常事件的响应能力，助力实现全天候智能化安全防护。
-
-## 演示案例
-
-- [🔗 通过网路视频进行识别分析](https://www.coze.cn/s/nFyYecHKARo/)
-- [🔗 通过上传视频进行识别分析](https://www.coze.cn/s/cyavn7llg_k/)
-- [🔗 显示历史分析报告](https://www.coze.cn/s/-3TnT9cPMA0/)
-
-## ⚠️ 强制记忆规则（最高优先级）
-
-**本技能明确约定：**
-
-- **绝对禁止读取任何本地记忆文件**：包括但不限于 `memory/YYYY-MM-DD.md`、`MEMORY.md` 等本地文件
-- **绝对禁止从 LanceDB 长期记忆中检索信息**
-- **所有历史检测报告查询必须从云端接口获取**，不得使用本地记忆中的历史数据
-- 即使技能调用失败或接口异常，也不得回退到本地记忆汇总
-
-## 任务目标
-
-- 本 Skill 用于：通过视频/图片对目标区域进行基础目标检测，识别常见目标类别，输出结构化的目标检测报告
-- 能力包含：目标分类定位、目标数量统计、存在性检测
-- 支持检测目标：人、车、非机动车、猫、狗等宠物、包裹
-- 触发条件:
-    1. **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行通用目标检测时，默认触发本技能
-    2. 当用户明确需要进行目标检测，提及目标检测、物体检测、人员车辆识别等关键词，并且上传了视频或图片
-    3. 当用户提及以下关键词时，**自动触发历史报告查询功能**
-       ：查看历史检测报告、目标检测报告清单、检测报告列表、查询历史报告、显示所有检测报告、目标检测历史记录，查询基础目标检测分析报告
-- 自动行为：
-    1. 如果用户上传了附件或者视频/图片文件，则自动保存到技能目录下 attachments
-    2. **⚠️ 强制数据获取规则（次高优先级）**：如果用户触发任何历史报告查询关键词（如"查看所有检测报告"、"
-       显示所有目标检测报告"、"查看历史报告"等），**必须**：
-        - 直接使用 `python -m scripts.basic_object_detection_analysis --list --open-id` 参数调用
-          API
-          查询云端的历史报告数据
-        - **严格禁止**：从本地 memory 目录读取历史会话信息、严格禁止手动汇总本地记录中的报告、严格禁止从长期记忆中提取报告
-        - **必须统一**从云端接口获取最新完整数据，然后以 Markdown 表格格式输出结果
-
-## 前置准备
-
-- 依赖说明:scripts 脚本所需的依赖包及版本
-  ```
-  requests>=2.28.0
-  ```
-
-## 操作步骤
-
-### 🔒 open-id 获取流程控制（强制执行，防止遗漏）
-
-**在执行基础目标检测前，必须按以下优先级顺序获取 open-id：**
-
-```
-第 1 步：【最高优先级】检查技能所在目录的配置文件（优先）
-        路径：skills/smyx_common/scripts/config.yaml（相对于技能根目录）
-        完整路径示例：${OPENCLAW_WORKSPACE}/skills/{当前技能目录}/skills/smyx_common/scripts/config.yaml
-        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id
-        ↓ (未找到/未配置/api-key 为空)
-第 2 步：检查 workspace 公共目录的配置文件
-        路径：${OPENCLAW_WORKSPACE}/skills/smyx_common/scripts/config.yaml
-        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id
-        ↓ (未找到/未配置)
-第 3 步：检查用户是否在消息中明确提供了 open-id
-        ↓ (未提供)
-第 4 步：❗ 必须暂停执行，明确提示用户提供用户名或手机号作为 open-id
-```
-
-**⚠️ 关键约束：**
-
-- **禁止**自行假设,自行推导,自行生成 open-id 值（如 openclaw-control-ui、default、object123 等）
-- **禁止**跳过 open-id 验证直接调用 API
-- **必须**在获取到有效 open-id 后才能继续执行分析
-- 如果用户拒绝提供 open-id，说明用途（用于保存和查询目标检测报告记录），并询问是否继续
-
----
-
-- 标准流程:
-    1. **准备媒体输入**
-        - 提供监控视频文件路径、网络视频 URL 或现场图片
-        - 确保监控画面完整覆盖监测区域，画面稳定
-    2. **获取 open-id（强制执行）**
-        - 按上述流程控制获取 open-id
-        - 如无法获取，必须提示用户提供用户名或手机号
-    3. **执行基础目标检测**
-        - 调用 `-m scripts.basic_object_detection_analysis` 处理素材（**必须在技能根目录下运行脚本**）
-        - 参数说明:
-            - `--input`: 本地视频/图片文件路径（使用 multipart/form-data 方式上传）
-            - `--url`: 网络视频/图片 URL 地址（API 服务自动下载）
-            - `--media-type`: 媒体类型，可选值：video/image，默认 video
-            - `--confidence-threshold`: 置信度阈值，低于该分值不输出，默认 0.5
-            - `--open-id`: 当前用户的 open-id（必填，按上述流程获取）
-            - `--list`: 显示基础目标检测历史分析报告列表清单（可以输入起始日期参数过滤数据范围）
-            - `--api-key`: API 访问密钥（可选）
-            - `--api-url`: API 服务地址（可选，使用默认值）
-            - `--detail`: 输出详细程度（basic/standard/json，默认 json）
-            - `--output`: 结果输出文件路径（可选）
-    4. **查看分析结果**
-        - 接收结构化的基础目标检测报告
-        - 包含：检测基本信息、各类目标数量、目标位置统计
-
-## 资源索引
-
-- 必要脚本：见 [scripts/basic_object_detection_analysis.py](scripts/basic_object_detection_analysis.py)(用途：调用 API
-  进行基础目标检测，本地文件使用 multipart/form-data 方式上传，网络 URL 由 API 服务自动下载)
-- 配置文件：见 [scripts/config.py](scripts/config.py)(用途：配置 API 地址、默认参数和媒体格式限制)
-- 领域参考：见 [references/api_doc.md](references/api_doc.md)(何时读取：需要了解 API 接口详细规范和错误码时)
-
-## 注意事项
-
-- 仅在需要时读取参考文档，保持上下文简洁
-- 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 100MB
-- API 密钥可选，如果通过参数传入则必须确保调用鉴权成功，否则忽略鉴权
-- 分析结果仅供安防管理参考，具体处置请按单位相关规定执行
-- 禁止临时生成脚本，只能用技能本身的脚本
-- 传入的网络地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载
-- 当显示历史检测报告清单的时候，从数据 json 中提取字段 reportImageUrl 作为超链接地址，使用 Markdown 表格格式输出，包含"
-  报告名称"、"检测时间"、"目标总数"、"点击查看"四列，其中"报告名称"列使用`基础目标检测报告-{记录id}`形式拼接, "点击查看"列使用
-  `[🔗 查看报告](reportImageUrl)`
-  格式的超链接，用户点击即可直接跳转到对应的完整报告页面。
-- 表格输出示例：
-  | 报告名称 | 检测时间 | 目标总数 | 点击查看 |
-  |----------|----------|----------|----------|
-  | 基础目标检测报告-20260312172200001 | 2026-03-12 17:22:00 | 5 | [🔗 查看报告](https://example.com/report?id=xxx) |
-
-## 使用示例
-
-```bash
-# 检测本地监控视频（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.basic_object_detection_analysis --input /path/to/monitor.mp4 --media-type video --open-id openclaw-control-ui
-
-# 检测现场图片，调整置信度阈值（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.basic_object_detection_analysis --input /path/to/scene.jpg --media-type image --confidence-threshold 0.6 --open-id openclaw-control-ui
-
-# 检测网络监控视频（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.basic_object_detection_analysis --url https://example.com/monitor.mp4 --media-type video --open-id openclaw-control-ui
-
-# 显示历史检测报告/显示检测报告清单列表/显示历史目标检测报告（自动触发关键词：查看历史检测报告、历史报告、检测报告清单等）
-python -m scripts.basic_object_detection_analysis --list --open-id openclaw-control-ui
-
-# 输出精简报告
-python -m scripts.basic_object_detection_analysis --input video.mp4 --media-type video --open-id your-open-id --detail basic
-
-# 保存结果到文件
-python -m scripts.basic_object_detection_analysis --input video.mp4 --media-type video --open-id your-open-id --output result.json
-```

skills/18072937735/smyx-basic-object-detection-analysis/_meta.json

@@ -1,11 +0,0 @@
-{
-  "owner": "18072937735",
-  "slug": "smyx-basic-object-detection-analysis",
-  "displayName": "Basic Object Detection Skill | 基础目标检测技能",
-  "latest": {
-    "version": "1.0.0",
-    "publishedAt": 1776142106790,
-    "commit": "https://github.com/openclaw/skills/commit/67260d50b68c81917e31a7a65dbe0b6ac7a7bdb3"
-  },
-  "history": []
-}

skills/18072937735/smyx-basic-object-detection-analysis/references/api_doc.md

@@ -1,21 +0,0 @@
-# API 接口文档
-
-此处用于存放宠物健康分析 API 的接口文档，待后续补充。
-
-## 接口规范
-
-- 基础地址：由 smyx_common 配置统一管理
-- 认证方式：API Key 鉴权
-- 请求格式：multipart/form-data 支持文件上传
-- 响应格式：JSON
-
-## 主要接口
-
-1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务
-2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果
-3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告
-4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告
-
-## 场景代码
-
-- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析

skills/18072937735/smyx-basic-object-detection-analysis/scripts/__init__.py

@@ -1 +0,0 @@
-# Pet Analysis scripts package

skills/18072937735/smyx-basic-object-detection-analysis/scripts/api_service.py

@@ -1,53 +0,0 @@
-#!/usr/bin/env python3
-
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-from skills.smyx_common.scripts.util import RequestUtil
-
-
-class ApiService(ApiServiceBase):
-
-    def __init__(self):
-        super().__init__()
-        self.analysis_url = ApiEnum.ANALYSIS_URL
-
-    def analysis_result(self, *args, **argss):
-        return self.http_post(ApiEnum.ANALYSIS_RESULT_URL, *args, **argss)
-
-    def analysis(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        options = {
-            "data_as_params": True
-        }
-        # params.setdefault("scene", scene_code)
-        # 添加宠物类型参数
-        if ConstantEnum.DEFAULT_PET_TYPE:
-            params.setdefault("petType", ConstantEnum.DEFAULT_PET_TYPE)
-        return self.http_post(self.analysis_url, options=options, *args, **argss)
-
-    def page(self, pageNum=None, pageSize=None, *args, **argss):
-        data = argss.setdefault("data", {})
-        data.setdefault("orderBy", {
-            "fieldName": "createTime",
-            "isAsc": False
-        })
-        return super().page(ApiEnum.PAGE_URL, pageNum, pageSize, *args, **argss)
-
-    def list(self, *args, **argss):
-        return super().list(None, *args, **argss)
-
-    def add(self, item: dict):
-        return super().add(ApiEnum.ADD_URL, item)
-
-    def edit(self, item: dict):
-        return super().edit(ApiEnum.EDIT_URL, item)
-
-    def delete(self, cameraSn):
-        data = {
-            "cameraSn": cameraSn
-        }
-        return super().delete(ApiEnum.DELETE_URL, data, options={"data_as_params": True})

skills/18072937735/smyx-basic-object-detection-analysis/scripts/basic_object_detection_analysis.py

@@ -1,224 +0,0 @@
-#!/usr/bin/env python3
-import sys
-import os
-
-current_dir = os.path.dirname(os.path.abspath(__file__))
-parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(current_dir)))
-sys.path.insert(0, parent_dir)
-
-import argparse
-import json
-import mimetypes
-import traceback
-from datetime import datetime
-
-import requests
-import sys
-import os
-
-from .config import *
-
-from .skill import skill
-
-from skills.smyx_common.scripts.util import RequestUtil
-
-# 从config导入常量
-SUPPORTED_FORMATS = ConstantEnum.SUPPORTED_FORMATS
-MAX_FILE_SIZE_MB = ConstantEnum.MAX_FILE_SIZE_MB
-
-
-def validate_file(file_path):
-    """验证输入文件是否合法"""
-    if not os.path.exists(file_path):
-        raise FileNotFoundError(f"文件不存在: {file_path}")
-
-    if not os.access(file_path, os.R_OK):
-        raise PermissionError(f"文件没有读权限: {file_path}")
-
-    ext = os.path.splitext(file_path)[1].lower()[1:]
-    if ext not in SUPPORTED_FORMATS:
-        raise ValueError(f"不支持的文件格式，支持的格式: {', '.join(SUPPORTED_FORMATS)}")
-
-    file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
-    if file_size_mb > MAX_FILE_SIZE_MB:
-        raise ValueError(f"文件过大，最大支持 {MAX_FILE_SIZE_MB}MB，当前文件大小: {file_size_mb:.1f}MB")
-
-    return True
-
-
-def analyze_media(input_path=None, url=None, media_type=None, confidence_threshold=None, api_url=None, api_key=None,
-                  output_level=None):
-    """调用API进行基础目标检测"""
-    if not input_path and not url:
-        raise ValueError("必须提供本地媒体路径(--input)或网络媒体URL(--url)")
-
-    # 设置参数
-    if media_type:
-        ConstantEnum.DEFAULT_MEDIA_TYPE = media_type
-    if confidence_threshold:
-        ConstantEnum.DEFAULT_CONFIDENCE_THRESHOLD = confidence_threshold
-
-    try:
-        input_path = input_path or url
-        # 携带额外参数
-        params = {}
-        if confidence_threshold:
-            params["confidence_threshold"] = confidence_threshold
-        return skill.get_output_analysis(input_path, params)
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def show_analyze_list(open_id, start_time=None, end_time=None):
-    # if not open_id:
-    #     raise ValueError("必须提供本用户的OpenId/UserId")
-
-    try:
-        output_content = skill.get_output_analysis_list()
-        return output_content
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def get_analysis_export_url(request_id=None):
-    """调用API分析视频"""
-    if not request_id:
-        return ""
-    return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-
-def format_result(result, output_level="standard", media_type="video", confidence_threshold=0.5):
-    """格式化输出结果"""
-    category_map = {
-        "person": "人",
-        "car": "车",
-        "non-motor": "非机动车",
-        "cat": "猫",
-        "dog": "狗",
-        "pet": "宠物",
-        "package": "包裹"
-    }
-
-    if output_level == "json":
-        result_id = None
-        if result is not None:
-            result_json = result
-            result_id = result_json.get('id', {})
-            result_json = json.dumps(result_json.get('objectDetectionResponse', {}), ensure_ascii=False, indent=2)
-        else:
-            return "⚠️ 暂无分析结果"
-        return f"""
-📊 基础目标检测分析结构化结果
-{result_json}
-""", result_id
-    elif output_level == "basic":
-        # 精简输出
-        data = result.get('data', {})
-        detection = data.get('detection', {})
-        return f"""
-📊 基础目标检测报告
-{'=' * 40}
-置信度阈值: {confidence_threshold}
-检测到目标总数: {detection.get('total_count', 0)}
-        """
-    elif output_level == "standard":
-        # 标准输出
-        data = result.get('data', {})
-        detection = data.get('detection', {})
-
-        objects = "\n".join([
-            f"  📦 {category_map.get(obj.get('category'), obj.get('category'))}: {obj.get('count', 0)} 个，平均置信度: {obj.get('avg_confidence', 0)}"
-            for obj in detection.get('category_stats', [])])
-
-        return f"""
-📊 基础目标检测分析报告
-{'=' * 50}
-⏰ 检测时间: {data.get('detection_time', '未知')}
-📹 素材类型: {media_type}
-🎯 置信度阈值: {confidence_threshold}
-
-🔍 检测结果:
-  检测到目标总数: {detection.get('total_count', 0)}
-
-  各类目标统计:
-{objects if objects else '  未检测到目标'}
-{'=' * 50}
-> 注：本报告仅供安防管理参考，具体处置请按单位相关规定执行。
-        """
-    else:
-        # 完整输出（JSON格式）
-        return json.dumps(result, ensure_ascii=False, indent=2)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="基础目标检测工具")
-    parser.add_argument("--input", help="本地视频/图片文件路径")
-    parser.add_argument("--url", help="网络视频/图片的URL地址")
-    parser.add_argument("--media-type", choices=["video", "image"], default=ConstantEnum.DEFAULT__MEDIA_TYPE,
-                        help="媒体类型：video(视频流/视频文件), image(图片)，默认 video")
-    parser.add_argument("--confidence-threshold", type=float, default=ConstantEnum.DEFAULT__CONFIDENCE_THRESHOLD,
-                        help="置信度阈值，低于该分值不输出，默认 0.5")
-    parser.add_argument("--open-id", required=True, help="当前用户的OpenID/UserId/用户名/手机号")
-    parser.add_argument("--list", action='store_true', help="显示基础目标检测列表清单")
-    parser.add_argument("--api-url", help="服务端API地址")
-    parser.add_argument("--api-key", help="API访问密钥（必需）")
-    parser.add_argument("--output", help="结果输出文件路径")
-    parser.add_argument("--detail", choices=["basic", "standard", "json"],
-                        default=ConstantEnum.DEFAULT__OUTPUT_LEVEL,
-                        help="输出详细程度")
-    parser.add_argument("--export-env-only", action='store_true',
-                        help="仅输出 export 命令设置环境变量，不执行分析")
-
-    args = parser.parse_args()
-
-    try:
-        if args.open_id:
-            # 设置 Python 进程内的环境变量
-            ConstantEnumBase.CURRENT__OPEN_ID = args.open_id
-
-        # 检查必需参数
-        if args.list:
-            open_id = ConstantEnum.CURRENT__OPEN_ID
-            result = show_analyze_list(open_id)
-            print(result)
-            exit(0)
-
-        # 检查必需参数
-        if not args.input and not args.url:
-            print("❌ 错误: 必须提供 --input 或 --url 参数")
-            exit(1)
-
-        print("🔍 正在进行基础目标检测，请稍候...")
-        output_content = analyze_media(
-            input_path=args.input,
-            url=args.url,
-            media_type=args.media_type,
-            confidence_threshold=args.confidence_threshold,
-            api_url=args.api_url,
-            api_key=args.api_key,
-            output_level=args.detail
-        )
-
-        print(output_content)
-
-        # 保存到文件
-        if args.output:
-            with open(args.output, "w", encoding="utf-8") as f:
-                if args.detail == "full":
-                    json.dump(result, f, ensure_ascii=False, indent=2)
-                else:
-                    f.write(output_content)
-            print(f"✅ 结果已保存到: {args.output}")
-
-    except Exception as e:
-        traceback.print_stack()
-        print(f"❌ 基础目标检测失败: {str(e)}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()

skills/18072937735/smyx-basic-object-detection-analysis/scripts/config.py

@@ -1,25 +0,0 @@
-#!/usr/bin/env python3
-# 基础目标检测技能配置文件
-import os
-import sys
-
-from enum import Enum
-
-from skills.smyx_common.scripts.config import ConstantEnum as ConstantEnumBase
-
-from skills.face_analysis.scripts.config import ApiEnum as ApiEnumParent, ConstantEnum as ConstantEnumParent, \
-    SceneCodeEnum, ApiEnumCommonAiMixin
-
-
-class ApiEnum(ApiEnumCommonAiMixin, ApiEnumParent):
-    pass
-
-
-class ConstantEnum(ConstantEnumParent):
-    DEFAULT__MEDIA_TYPE = "video"
-    DEFAULT__CONFIDENCE_THRESHOLD = 0.5
-
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-        ConstantEnumParent.DEFAULT__SCENE_CODE = SceneCodeEnum.BASIC_OBJECT_DETECTION_ANALYSIS.value

skills/18072937735/smyx-basic-object-detection-analysis/scripts/config.yaml

@@ -1 +0,0 @@
-{}

skills/18072937735/smyx-basic-object-detection-analysis/scripts/skill.py

@@ -1,23 +0,0 @@
-#!/usr/bin/env python3
-import json
-
-from .config import ApiEnum, ConstantEnum
-
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-from skills.face_analysis.scripts.skill import Skill as SkillParent
-from skills.smyx_common.scripts.util import JsonUtil
-
-
-class Skill(SkillParent):
-    def __init__(self):
-        super().__init__()
-
-    def get_output_analysis_content_head(self, result=None):
-        return f"📊 基础目标检测分析结构化结果"
-
-    def get_output_analysis_content_foot(self, result):
-        pass
-
-
-skill = Skill()

skills/18072937735/smyx-basic-object-detection-analysis/skills/face_analysis/README.md

@@ -1,86 +0,0 @@
-# 中医面诊分析工具 (face-analysis)
-
-## 技能介绍
-这是一个基于AI的中医面诊分析技能，可以通过面部视频自动分析健康状况，返回结构化的诊断结果和养生建议。
-
-## 快速开始
-### 1. 配置API信息
-编辑 `scripts/config.py`，设置你的API地址和密钥：
-```python
-DEFAULT_API_URL = "https://your-api-server.com/api/v1/face-analysis"
-DEFAULT_API_KEY = "your-api-key-here"
-```
-
-### 2. 分析本地视频
-```bash
-python scripts/face_analysis.py --input /path/to/your/video.mp4
-```
-
-### 3. 分析网络视频
-```bash
-python scripts/face_analysis.py --url https://example.com/video.mp4
-```
-
-## 功能特性
-- ✅ 支持本地MP4视频上传
-- ✅ 支持网络视频URL分析
-- ✅ 三种输出详细程度：精简/标准/完整
-- ✅ 结构化JSON结果输出
-- ✅ 自动保存结果到文件
-- ✅ 内置视频格式和大小校验
-
-## 目录结构
-```
-face-analysis/
-├── SKILL.md              # 技能说明文件（系统自动加载）
-├── README.md             # 本说明文件
-├── scripts/
-│   ├── face_analysis.py  # 主程序
-│   └── config.py         # 配置文件
-├── references/
-│   ├── api_doc.md        # API接口文档
-│   ├── tcm_theory.md     # 中医面诊理论参考
-│   └── faq.md            # 常见问题
-└── assets/
-    └── template.json     # 返回结果模板
-```
-
-## 使用示例
-### 标准输出
-```
-📊 中医面诊分析报告
-==================================================
-⏰ 分析时间: 2026-03-10 15:30:00
-🎯 人脸检测: success (置信度: 95分)
-
-🔍 诊断结果:
-  整体体质: 平和质
-  脏腑状况:
-    liver: 正常
-    heart: 轻微火旺
-    spleen: 略虚
-    lung: 正常
-    kidney: 正常
-  面色分析: 微黄
-  对应提示: 脾胃功能略弱
-
-⚠️ 健康警示:
-  ⚠️  注意休息，避免熬夜
-
-💡 养生建议:
-  💡 饮食清淡，减少辛辣食物摄入
-  💡 保持规律作息，每晚11点前入睡
-  💡 适当进行有氧运动，如散步、太极拳
-==================================================
-```
-
-### 输出到JSON文件
-```bash
-python scripts/face_analysis.py --input video.mp4 --detail full --output result.json
-```
-
-## 注意事项
-1. 视频要求：清晰正面面部，光线充足，时长5-30秒为宜
-2. 支持格式：mp4、avi、mov，最大100MB
-3. API需要自行部署或接入第三方服务
-4. 结果仅供参考，不能替代专业医生诊断

skills/18072937735/smyx-basic-object-detection-analysis/skills/face_analysis/references/api_doc.md

@@ -1,69 +0,0 @@
-# API接口文档
-
-## 接口地址
-`POST https://your-api-server.com/api/v1/face-analysis`
-
-## 请求头
-| 字段 | 必选 | 说明 |
-|------|------|------|
-| X-API-Key | 是 | API访问密钥 |
-| Content-Type | 是 | multipart/form-data（文件上传）或 application/json（URL模式） |
-
-## 请求参数
-### 1. 文件上传模式
-| 字段 | 类型 | 必选 | 说明 |
-|------|------|------|------|
-| video | file | 是 | MP4视频文件 |
-| detail_level | string | 否 | 输出详细程度：basic/standard/full，默认standard |
-
-### 2. URL模式
-| 字段 | 类型 | 必选 | 说明 |
-|------|------|------|------|
-| video_url | string | 是 | 可公开访问的视频URL |
-| detail_level | string | 否 | 输出详细程度：basic/standard/full，默认standard |
-
-## 响应格式
-```json
-{
-  "code": 200,
-  "message": "success",
-  "data": {
-    "analysis_time": "2026-03-10 15:30:00",
-    "face_detection": {
-      "status": "success",
-      "face_count": 1,
-      "quality_score": 95
-    },
-    "diagnosis": {
-      "overall_constitution": "平和质",
-      "organ_condition": {
-        "liver": "正常",
-        "heart": "轻微火旺",
-        "spleen": "略虚",
-        "lung": "正常",
-        "kidney": "正常"
-      },
-      "color_analysis": {
-        "complexion": "微黄",
-        "correspondence": "脾胃功能略弱"
-      }
-    },
-    "health_warnings": [
-      "注意休息，避免熬夜"
-    ],
-    "suggestions": [
-      "饮食清淡，减少辛辣食物摄入"
-    ]
-  }
-}
-```
-
-## 错误码说明
-| 错误码 | 说明 |
-|--------|------|
-| 400 | 请求参数错误 |
-| 401 | API密钥无效 |
-| 403 | 权限不足 |
-| 413 | 文件过大 |
-| 415 | 不支持的文件格式 |
-| 500 | 服务器内部错误 |

skills/18072937735/smyx-basic-object-detection-analysis/skills/face_analysis/requirements.txt

@@ -1,3 +0,0 @@
-pydash==8.0.6
-SQLAlchemy==2.0.46
-yaml==6.0.3

skills/18072937735/smyx-basic-object-detection-analysis/skills/face_analysis/scripts/api_service.py

@@ -1,52 +0,0 @@
-#!/usr/bin/env python3
-
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-
-class ApiService(ApiServiceBase):
-
-    def __init__(self):
-        super().__init__()
-        self.analysis_url = ApiEnum.ANALYSIS_URL
-
-    def analysis_result(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        scene_code and params.setdefault("sceneCode", scene_code)
-        return self.http_post(ApiEnum.ANALYSIS_RESULT_URL, *args, **argss)
-
-    def analysis(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        options = {
-            "dataAsParams": True
-        }
-        scene_code and params.setdefault("sceneCode", scene_code)
-        params.setdefault("appCategory", ConstantEnum.DEFAULT__APP_CATEGORY)
-        return self.http_post(self.analysis_url, options=options, *args, **argss)
-
-    def page(self, pageNum=None, pageSize=None, *args, **argss):
-        data = argss.setdefault("data", {})
-        ConstantEnum.DEFAULT__SCENE_CODE and data.setdefault("sceneCode", ConstantEnum.DEFAULT__SCENE_CODE)
-        data.setdefault("orderBy", {
-            "fieldName": "createTime",
-            "isAsc": False
-        })
-        return super().page(ApiEnum.PAGE_URL, pageNum, pageSize, *args, **argss)
-
-    def list(self, *args, **argss):
-        return super().list(None, *args, **argss)
-
-    def add(self, item: dict):
-        return super().add(ApiEnum.ADD_URL, item)
-
-    def edit(self, item: dict):
-        return super().edit(ApiEnum.EDIT_URL, item)
-
-    def delete(self, cameraSn):
-        data = {
-            "cameraSn": cameraSn
-        }
-        return super().delete(ApiEnum.DELETE_URL, data, options={"dataAsParams": True})

skills/18072937735/smyx-basic-object-detection-analysis/skills/face_analysis/scripts/config.py

@@ -1,40 +0,0 @@
-#!/usr/bin/env python3
-# 中医面诊分析工具配置文件
-import os
-import sys
-
-from enum import Enum
-
-from skills.smyx_common.scripts.config import ApiEnum as ApiEnumBase, ConstantEnum as ConstantEnumBase
-
-SceneCodeEnum = ConstantEnumBase.SceneCodeEnum
-
-
-class ApiEnum(ApiEnumBase):
-    ANALYSIS_URL = "/web/health-analysis/v2/start-health-analysis"
-
-    ANALYSIS_RESULT_URL = "/web/health-analysis/get-health-analysis-result"
-
-    PAGE_URL = "/web/health-analysis/page-health-analysis-result"
-
-    DETAIL_EXPORT_URL = ApiEnumBase.BASE_URL_HEALTH + "/health/order/api/getReportDetailExport?id="
-
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-
-
-class ApiEnumCommonAiMixin:
-
-    @classmethod
-    def init(cls, config=None):
-        parent = super()
-        if hasattr(parent, "init"):
-            parent.init(config)
-        ApiEnum.ANALYSIS_URL = "/web/ai-analysis/v2/start-common-ai-analysis"
-        ApiEnum.ANALYSIS_RESULT_URL = "/web/ai-analysis/get-common-ai-analysis-result"
-        ApiEnum.PAGE_URL = "/web/ai-analysis/page-common-ai-analysis-result"
-
-
-class ConstantEnum(ConstantEnumBase):
-    DEFAULT__APP_CATEGORY = "PEI_NI_AN"

skills/18072937735/smyx-basic-object-detection-analysis/skills/face_analysis/scripts/config.yaml

@@ -1 +0,0 @@
-{}

skills/18072937735/smyx-basic-object-detection-analysis/skills/face_analysis/scripts/face_analysis.py

@@ -1,205 +0,0 @@
-#!/usr/bin/env python3
-import sys
-import os
-
-current_dir = os.path.dirname(os.path.abspath(__file__))
-parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(current_dir)))
-sys.path.insert(0, parent_dir)
-
-import argparse
-import json
-import mimetypes
-import traceback
-from datetime import datetime
-
-import requests
-import sys
-import os
-
-from .config import *
-
-from .skill import skill
-
-# import_path_common()
-from skills.smyx_common.scripts.util import RequestUtil
-
-# 从config导入常量
-SUPPORTED_FORMATS = ConstantEnum.SUPPORTED_FORMATS
-MAX_FILE_SIZE_MB = ConstantEnum.MAX_FILE_SIZE_MB
-
-
-def validate_file(file_path):
-    """验证输入文件是否合法"""
-    if not os.path.exists(file_path):
-        raise FileNotFoundError(f"文件不存在: {file_path}")
-
-    if not os.access(file_path, os.R_OK):
-        raise PermissionError(f"文件没有读权限: {file_path}")
-
-    ext = os.path.splitext(file_path)[1].lower()[1:]
-    if ext not in SUPPORTED_FORMATS:
-        raise ValueError(f"不支持的文件格式，支持的格式: {', '.join(SUPPORTED_FORMATS)}")
-
-    file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
-    if file_size_mb > MAX_FILE_SIZE_MB:
-        raise ValueError(f"文件过大，最大支持 {MAX_FILE_SIZE_MB}MB，当前文件大小: {file_size_mb:.1f}MB")
-
-    return True
-
-
-def analyze_video(input_path=None, url=None, api_url=None, api_key=None, output_level=None):
-    """调用API分析视频"""
-    if not input_path and not url:
-        raise ValueError("必须提供本地视频路径(--input)或网络视频URL(--url)")
-    try:
-        input_path = input_path or url
-        return skill.get_output_analysis(input_path)
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def show_analyze_list(open_id, start_time=None, end_time=None):
-    # if not open_id:
-    #     raise ValueError("必须提供本用户的OpenId/UserId")
-
-    try:
-        output_content = skill.get_output_analysis_list()
-        return output_content
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def get_analysis_export_url(request_id=None):
-    """调用API分析视频"""
-    if not request_id:
-        return ""
-    return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-
-def format_result(result, output_level="standard"):
-    """格式化输出结果"""
-    if output_level == "json":
-        result_id = None
-        # if result.get('success'):
-        if result is not None:
-            result_json = result
-            result_id = result_json.get('id', {})
-            result_json = json.dumps(result_json.get('faceAnalysisResponse', {}), ensure_ascii=False, indent=2)
-        else:
-            # result_json = json.dumps(result, ensure_ascii=False, indent=2)
-            return "⚠️ 暂无分析结果"
-        return f"""
-📊 面诊分析结构化结果
-{result_json}
-""", result_id
-    elif output_level == "basic":
-        # 精简输出
-        data = result.get('data', {})
-        diagnosis = data.get('diagnosis', {})
-        return f"""
-📊 面诊分析结果
-{'=' * 40}
-整体体质: {diagnosis.get('overall_constitution', '未知')}
-主要状况: {', '.join([f'{k}: {v}' for k, v in diagnosis.get('organ_condition', {}).items() if v != '正常'])}
-健康提示: {data.get('health_warnings', ['无特殊警示'])[0] if data.get('health_warnings') else '无特殊警示'}
-        """
-    elif output_level == "standard":
-        # 标准输出
-        data = result.get('data', {})
-        diagnosis = data.get('diagnosis', {})
-        face_detection = data.get('face_detection', {})
-
-        organ_status = "\n".join([f"  {k}: {v}" for k, v in diagnosis.get('organ_condition', {}).items()])
-        warnings = "\n".join([f"  ⚠️  {item}" for item in data.get('health_warnings', [])])
-        suggestions = "\n".join([f"  💡 {item}" for item in data.get('suggestions', [])])
-
-        return f"""
-📊 中医面诊分析报告
-{'=' * 50}
-⏰ 分析时间: {data.get('analysis_time', '未知')}
-🎯 人脸检测: {face_detection.get('status', '未知')} (置信度: {face_detection.get('quality_score', 0)}分)
-
-🔍 诊断结果:
-  整体体质: {diagnosis.get('overall_constitution', '未知')}
-  脏腑状况:
-{organ_status}
-  面色分析: {diagnosis.get('color_analysis', {}).get('complexion', '未知')}
-  对应提示: {diagnosis.get('color_analysis', {}).get('correspondence', '未知')}
-
-⚠️ 健康警示:
-{warnings}
-
-💡 养生建议:
-{suggestions}
-{'=' * 50}
-        """
-    else:
-        # 完整输出（JSON格式）
-        return json.dumps(result, ensure_ascii=False, indent=2)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="中医面诊分析工具")
-    parser.add_argument("--input", help="本地MP4视频文件路径")
-    parser.add_argument("--url", help="网络视频MP4的URL地址")
-    parser.add_argument("--open-id", required=True, help="当前用户的OpenID/UserId/用户名/手机号")
-    parser.add_argument("--list", action='store_true', help="显示面诊视频历史列表清单")
-    parser.add_argument("--api-url", help="服务端API地址")
-    parser.add_argument("--api-key", help="API访问密钥（必需）")
-    parser.add_argument("--output", help="结果输出文件路径")
-    parser.add_argument("--detail", choices=["basic", "standard", "json"],
-                        default=ConstantEnum.DEFAULT__OUTPUT_LEVEL,
-                        help="输出详细程度")
-    parser.add_argument("--export-env-only", action='store_true',
-                        help="仅输出 export 命令设置环境变量，不执行分析")
-
-    args = parser.parse_args()
-
-    try:
-        if args.open_id:
-            ConstantEnumBase.CURRENT__OPEN_ID = args.open_id
-
-        # 检查必需参数
-        if args.list:
-            open_id = ConstantEnum.CURRENT__OPEN_ID
-            result = show_analyze_list(open_id)
-            print(result)
-            exit(0)
-
-        # 检查必需参数
-        if not args.input and not args.url:
-            print("❌ 错误: 必须提供 --input 或 --url 参数")
-            exit(1)
-
-        print("🔍 正在分析面诊视频，请稍候...")
-        output_content = analyze_video(
-            input_path=args.input,
-            url=args.url,
-            api_url=args.api_url,
-            api_key=args.api_key,
-            output_level=args.detail
-        )
-
-        print(output_content)
-
-        # 保存到文件
-        if args.output:
-            with open(args.output, "w", encoding="utf-8") as f:
-                if args.detail == "full":
-                    json.dump(result, f, ensure_ascii=False, indent=2)
-                else:
-                    f.write(output_content)
-            print(f"✅ 结果已保存到: {args.output}")
-
-    except Exception as e:
-        traceback.print_stack()
-        print(f"❌ 面诊分析失败: {str(e)}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()

skills/18072937735/smyx-basic-object-detection-analysis/skills/face_analysis/scripts/skill.py

@@ -1,267 +0,0 @@
-#!/usr/bin/env python3
-import datetime
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-
-from .api_service import ApiService
-
-from skills.smyx_common.scripts.util import CommonUtil, JsonUtil
-from skills.smyx_common.scripts.config import ApiEnum as ApiEnumBase
-from skills.smyx_common.scripts.base import BaseSkill
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-
-class Skill(BaseSkill, ApiService):
-    def __init__(self):
-        super().__init__()
-
-    def get_output_analysis_content_body(self, result=None):
-        result_json = result
-
-        result_json_pure_text = result_json.get("pureText")
-        if result_json_pure_text:
-            result_json = JsonUtil.parse(result_json_pure_text, result_json_pure_text)
-
-        result_json_common_ai_response = result_json.get("commonAiResponse")
-        if result_json_common_ai_response:
-            result_json = result_json_common_ai_response
-
-        result_json_health_ai_response = result_json.get("healthAiResponse")
-        if result_json_health_ai_response:
-            result_json = result_json_health_ai_response
-
-        result_json = JsonUtil.stringify(result_json, result_json)
-        return result_json
-
-    def get_output_analysis_content_head(self, result=None):
-        return f"📊 面诊分析结构化结果"
-
-    def get_output_analysis_content_foot(self, result):
-        result_id = result.get('id', {})
-        output_content_export_url = ApiEnum.DETAIL_EXPORT_URL + result_id
-        return f"🔗 获取报告导出图片链接: {output_content_export_url}"
-
-    def get_output_analysis_content(self, result):
-        if result is not None:
-            output_content = self.get_output_analysis_content_body(result) or ""
-            output_content_head = self.get_output_analysis_content_head(result)
-            output_content_foot = self.get_output_analysis_content_foot(result)
-            #       d
-            if output_content_head:
-                output_content = f"""
-{output_content_head}
-""" + output_content
-            if output_content_foot:
-                output_content += f"""
-{output_content_foot}
-"""
-        else:
-            output_content = "⚠️ 暂无分析结果"
-        return output_content
-
-    def get_output_analysis(self, input_path, params={}):
-        response = self.get_analysis(
-            input_path, params
-        )
-
-        def _analysis_result():
-            return self.analysis_result(
-                data=response
-            )
-
-        new_response = CommonUtil.polling(_analysis_result,
-                                          check_condition=lambda res: res.get('needPageRefresh') is False, interval=5,
-                                          max_attempts=24)
-
-        output_content = self.get_output_analysis_content(new_response)
-        return output_content
-
-    def get_analysis(self, input_path, params={}):
-        import mimetypes
-
-        def _validate_file(file_path):
-            """验证输入文件是否合法"""
-            if not os.path.exists(file_path):
-                raise FileNotFoundError(f"文件不存在: {file_path}")
-
-            if not os.access(file_path, os.R_OK):
-                raise PermissionError(f"文件没有读权限: {file_path}")
-
-            ext = os.path.splitext(file_path)[1].lower()[1:]
-            if ext not in ConstantEnum.SUPPORTED_FORMATS:
-                raise ValueError(f"不支持的文件格式，支持的格式: {', '.join(ConstantEnum.SUPPORTED_FORMATS)}")
-
-            file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
-            if file_size_mb > ConstantEnum.MAX_FILE_SIZE_MB:
-                raise ValueError(
-                    f"文件过大，最大支持 {ConstantEnum.MAX_FILE_SIZE_MB}MB，当前文件大小: {file_size_mb:.1f}MB")
-
-            return True
-
-        files = None
-
-        if not input_path:
-            raise ValueError("必须提供本地视频路径(--input)或网络视频URL(--url)")
-
-        if (input_path.startswith("http://") or input_path.startswith("https://")):
-            params.update({
-                "videoUrl": input_path
-            })
-        else:
-            _validate_file(input_path)
-
-            # 自动检测 MIME 类型
-            mime_type, _ = mimetypes.guess_type(input_path)
-            if mime_type is None:
-                mime_type = 'application/octet-stream'
-
-            # 读取文件内容
-            with open(input_path, 'rb') as f:
-                file_content = f.read()
-
-            # 构建 multipart/form-data 格式的请求
-            files = {
-                'file': (os.path.basename(input_path), file_content, mime_type)
-            }
-
-        response = self.analysis(
-            params=params,
-            files=files
-        )
-
-        return response
-
-    def get_output_analysis_list(self, pageNum=None, pageSize=None, *args, **argss):
-        """获取面诊报告清单
-        优化规则：只要API服务接口返回面诊报告清单，直接输出API返回的结果，
-        无需汇总上下文中的面诊分析报告，以接口返回为准
-        """
-
-        def _get_analysis_export_url(request_id=None):
-            if not request_id:
-                return ""
-            return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-        response = self.page(pageNum, pageSize, *args, **argss)
-
-        if response:
-            for item in response:
-                if item.get("commonAiResponse") or item.get("healthAiResponse"):
-                    item["reportImageUrl"] = _get_analysis_export_url(item.get("id"))
-
-        response_text = JsonUtil.stringify(response)
-
-        if response_text:
-            return f"""📊 分析报告记录列表(结构化结果)"
-{response_text}
-"""
-        else:
-            return "⚠️ 暂无分析报告记录"
-
-    def __get_output_analysis_list(self, pageNum=None, pageSize=None, *args, **argss):
-        """获取面诊报告清单
-        优化规则：只要API服务接口返回面诊报告清单，直接输出API返回的结果，
-        无需汇总上下文中的面诊分析报告，以接口返回为准
-        """
-
-        def _get_analysis_export_url(request_id=None):
-            if not request_id:
-                return ""
-            return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-        # open_id 仅用于本地识别，不传给API - 参数已经在argss中，page方法会正确处理
-        open_id = argss.pop('open_id', None)
-        # if not open_id:
-        #     return "⚠️ 错误：缺少 open_id 参数"
-
-        # 获取总页数，然后循环获取所有页
-        output_all = ""
-        # 先获取第一页来获取总页数
-        # page 方法在基类中已经处理过，我们需要兼容两种返回结果：
-        # 1. 完整响应：{"success": true, "data": {"records": [...], "total": ...}}
-        # 2. 已经提取好的数据：直接返回 data 对象或 records 列表
-        response = self.page(pageNum or 1, pageSize or 30, *args, **argss)
-
-        if response is None:
-            return "⚠️ 获取报告列表失败：response is None"
-
-        # 兼容处理：不同版本的基类返回不同格式
-        if isinstance(response, list):
-            # 基类直接返回了 records 列表，无法获取分页信息，直接使用
-            records = response
-            total = len(records)
-            pages = 1
-        elif isinstance(response, dict):
-            # 完整响应格式
-            if not response.get('success'):
-                error_msg = response.get('errorMsg', '未知错误')
-                return f"⚠️ 获取报告列表失败：{error_msg}"
-            data = response.get('data', {})
-            if not data or not isinstance(data, dict):
-                return "⚠️ 获取报告列表失败：数据格式错误"
-            total = data.get('total', 0)
-            pages = data.get('pages', 1)
-            records = data.get('records', [])
-        else:
-            return f"⚠️ 获取报告列表失败：response type={type(response)}"
-
-        if not records:
-            return "⚠️ 暂无面诊分析报告记录"
-
-        output_all = f"📋 历史面诊分析报告清单（共 {total} 份）\n\n"
-        output_all += "| 报告名称 | 分析时间 | 体质判断 | 点击查看 |\n"
-        output_all += "|----------|----------|----------|----------|\n"
-
-        # 处理第一页
-        for item in records:
-            if not isinstance(item, dict):
-                continue
-            report_id = item.get('id', '')
-            create_time = item.get('createTimeString', '未知时间')
-            # 提取体质判断 - 优先从 healthAiResponse 获取，如果没有再从 faceAnalysisResponse 获取
-            health_ai = item.get('healthAiResponse', {}) or {}
-            if health_ai:
-                health_assessment = health_ai.get('healthAssessment', {}) or {}
-                subject = health_assessment.get('subject', '未知')
-            else:
-                face_ai = item.get('faceAnalysisResponse', {}) or {}
-                health_assessment = face_ai.get('healthAssessment', {}) or {}
-                subject = health_assessment.get('subject', '未知')
-            report_name = f"面诊分析报告-{report_id}"
-            report_url = _get_analysis_export_url(report_id)
-            output_all += f"| {report_name} | {create_time} | {subject} | [🔗 查看报告]({report_url}) |\n"
-
-        # 处理剩余页
-        for current_page in range(2, pages + 1):
-            response = self.page(current_page, 30, *args, **argss)
-            if not response or not isinstance(response, dict) or not response.get('success'):
-                continue
-            data = response.get('data', {})
-            if not data or not isinstance(data, dict):
-                continue
-            records = data.get('records', [])
-            for item in records:
-                if not isinstance(item, dict):
-                    continue
-                report_id = item.get('id', '')
-                create_time = item.get('createTimeString', '未知时间')
-                # 提取体质判断 - 优先从 healthAiResponse 获取，如果没有再从 faceAnalysisResponse 获取
-                health_ai = item.get('healthAiResponse', {}) or {}
-                if health_ai:
-                    health_assessment = health_ai.get('healthAssessment', {}) or {}
-                    subject = health_assessment.get('subject', '未知')
-                else:
-                    face_ai = item.get('faceAnalysisResponse', {}) or {}
-                    health_assessment = face_ai.get('healthAssessment', {}) or {}
-                    subject = health_assessment.get('subject', '未知')
-                report_name = f"面诊分析报告-{report_id}"
-                report_url = _get_analysis_export_url(report_id)
-                output_all += f"| {report_name} | {create_time} | {subject} | [🔗 查看报告]({report_url}) |\n"
-
-        output_all += "\n> 注：面诊分析结果仅供健康参考，不能替代专业医疗诊断。"
-        return output_all
-
-
-skill = Skill()

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/requirements.txt

@@ -1,127 +0,0 @@
-altgraph==0.17.5
-annotated-doc==0.0.4
-annotated-types==0.7.0
-anyio==4.12.1
-APScheduler==3.11.2
-astroid==3.1.0
-Authlib==1.6.6
-blinker==1.4
-cachetools==6.2.6
-certifi==2026.1.4
-cffi==2.0.0
-chardet==5.2.0
-charset-normalizer==3.4.4
-click==8.3.1
-coverage==7.13.2
-coze-workload-identity==0.1.7
-cozeloop==0.1.19
-cryptography==3.4.8
-Cython==3.2.4
-dbus-python==1.2.18
-dill==0.4.1
-distro==1.7.0
-distro-info==1.1+ubuntu0.2
-et_xmlfile==2.0.0
-fastapi==0.121.2
-gitdb==4.0.12
-gitignore_parser==0.1.13
-GitPython==3.1.45
-greenlet==3.3.1
-h11==0.16.0
-httpcore==1.0.9
-httplib2==0.20.2
-httpx==0.28.1
-httpx-ws==0.8.2
-idna==3.11
-importlib-metadata==4.6.4
-inflect==7.5.0
-iniconfig==2.3.0
-isort==5.13.2
-jeepney==0.7.1
-Jinja2==3.1.6
-jiter==0.12.0
-jsonpatch==1.33
-jsonpointer==3.0.0
-keyring==23.5.0
-langchain==1.0.3
-langchain-core==1.0.2
-langchain-openai==1.0.1
-langgraph==1.0.2
-langgraph-checkpoint==3.0.0
-langgraph-prebuilt==1.0.2
-langgraph-sdk==0.2.9
-langsmith==0.4.39
-launchpadlib==1.10.16
-lazr.restfulclient==0.14.4
-lazr.uri==1.0.6
-markdown-it-py==4.0.0
-MarkupSafe==3.0.3
-mccabe==0.7.0
-mdurl==0.1.2
-more-itertools==8.10.0
-numpy==2.4.1
-oauthlib==3.2.0
-openai==2.16.0
-openpyxl==3.1.5
-orjson==3.11.5
-ormsgpack==1.12.2
-packaging==25.0
-pandas==2.3.3
-platformdirs==4.5.1
-pluggy==1.6.0
-psutil==7.1.3
-psycopg2-binary==2.9.11
-pycparser==3.0
-pydantic==2.12.4
-pydantic_core==2.41.5
-pydash==8.0.6
-Pygments==2.19.2
-PyGObject==3.42.1
-pyinstaller==6.18.0
-pyinstaller-hooks-contrib==2026.0
-PyJWT==2.10.1
-pylint==3.1.0
-PyMySQL==1.1.2
-pyparsing==2.4.7
-pytest==9.0.1
-pytest-asyncio==1.3.0
-pytest-cov==7.0.0
-pytest-mock==3.15.1
-python-apt==2.4.0+ubuntu4.1
-python-dateutil==2.9.0.post0
-pytz==2025.2
-PyYAML==6.0.3
-regex==2026.1.15
-requests==2.32.5
-requests-toolbelt==1.0.0
-rich==14.2.0
-SecretStorage==3.3.1
-setuptools==80.9.0
-six==1.16.0
-smmap==5.0.2
-sniffio==1.3.1
-sqlacodegen==3.2.0
-SQLAlchemy==2.0.46
-starlette==0.49.3
-supervisor==4.2.1
-tenacity==9.1.2
-tiktoken==0.12.0
-tomlkit==0.14.0
-tqdm==4.67.1
-typeguard==4.4.4
-typing-inspection==0.4.2
-typing_extensions==4.15.0
-tzdata==2025.3
-tzlocal==5.3.1
-unattended-upgrades==0.1
-urllib3==2.6.3
-uvicorn==0.38.0
-wadllib==1.3.6
-watchdog==6.0.0
-websockets==15.0.1
-wheel==0.45.1
-wsproto==1.3.2
-xlrd==2.0.2
-xxhash==3.6.0
-zipp==1.0.0
-zstandard==0.25.0

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/__init__.py

@@ -1,8 +0,0 @@
-from .util import RequestUtil, CommonUtil, DatetimeUtil
-from .base import *
-
-__all__ = [
-    'RequestUtil',
-    'CommonUtil',
-    'BaseUtil'
-]

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/api_service.py

@@ -1,96 +0,0 @@
-#!/usr/bin/env python3
-
-from .config import ApiEnum
-
-from .base import BaseApiService
-from .util import RequestUtil, CommonUtil
-
-
-class ApiService(BaseApiService):
-
-    def __init__(self):
-        super().__init__()
-
-    def get_download_url(self, tosKey, expireSeconds=3600):
-        return RequestUtil.http_post(
-            ApiEnum.GET_DOWNLOAD_URL__URL,
-            params={
-                "tosKey": tosKey,
-                "expireSeconds": expireSeconds * 24
-            }
-        )
-
-    def page(self, url, pageNum=None, pageSize=None, *args, **argss):
-        data = args[0] if len(args) > 0 else argss.get('data') if argss.get('data') is not None else {}
-        if pageNum is None:
-            pageNum = 1
-        if pageSize is None:
-            pageSize = ApiEnum.DEFAULT__PAGE_SIZE
-        paramsPage = {
-            'pageNum': int(pageNum),
-            'pageSize': int(pageSize)
-        }
-        data.update({
-            "page": paramsPage
-        })
-        if not CommonUtil.is_empty(data):
-            if (len(args) == 0):
-                argss.setdefault("data", data)
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def list(self, url=None, *args, **argss):
-        if url is not None:
-            argss["url"] = url
-        return self.page(1, ApiEnum.DEFAULT__PAGE_SIZE_MAX, *args, **argss)
-
-    def add(self, url=None, *args, **argss):
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def edit(self, url=None, *args, **argss):
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def delete(self, url=None, *args, **argss):
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def http_post(self, url=None, *args, **argss):
-        return RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-
-    def http_put(self, url=None, *args, **argss):
-        return RequestUtil.http_put(
-            url,
-            *args, **argss
-        )
-
-    def http_get(self, url=None, *args, **argss):
-        return RequestUtil.http_get(
-            url,
-            *args, **argss
-        )
-
-        return response
-
-    def http_delete(self, url=None, *args, **argss):
-        return RequestUtil.http_delete(
-            url,
-            *args, **argss
-        )
-        return response

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/base.py

@@ -1,33 +0,0 @@
-class BaseUtil:
-    pass
-
-
-class BaseMixin:
-    pass
-
-
-class BaseDao:
-    pass
-
-
-class BaseService:
-    def __init__(self):
-        super().__init__()
-
-
-class BaseApiService(BaseService):
-    INSTANCE = None
-
-    def __init__(self):
-        super().__init__()
-
-    @classmethod
-    def get_instance(cls):
-        if cls.INSTANCE is None:
-            cls.INSTANCE = cls()
-        return cls.INSTANCE
-
-
-class BaseSkill:
-    def __init__(self):
-        super().__init__()

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/config-dev.yaml

@@ -1,7 +0,0 @@
-ApiEnum:
-  base-url-open-api: "http://192.168.1.234:9601/smyx-open-api"
-  base-url-open-h5: "http://192.168.1.234:4100"
-  base-url-health: "http://192.168.1.234:8080/jeecg-boot"
-
-ConstantEnum:
-  is-debug: true

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/config-test.yaml

@@ -1,7 +0,0 @@
-ApiEnum:
-  base-url-open-api: "https://livemonitortest.lifeemergence.com/smyx-open-api"
-  base-url-open-h5: "http://livemonitortest.lifeemergence.com"
-  base-url-health: "https://healthtest.lifeemergence.com/jeecg-boot"
-
-ConstantEnum:
-  is-debug: true

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/config.py

@@ -1,235 +0,0 @@
-#!/usr/bin/env python3
-import os
-import sys
-from enum import Enum
-from typing import Dict
-import inspect
-
-import yaml
-import platform
-
-
-class YamlUtil:
-
-    @staticmethod
-    def load(path, config: Dict = {}) -> Dict:
-        try:
-            if not os.path.exists(path):
-                os.makedirs(os.path.dirname(path), exist_ok=True)
-                with open(path, "w", encoding="utf-8") as f:
-                    yaml.dump(config, f, default_flow_style=False, allow_unicode=True)
-                return config
-            with open(path, "r", encoding="utf-8") as f:
-                config = yaml.safe_load(f) or {}
-                for key, value in config.items():
-                    if key not in config:
-                        config[key] = value
-                return config
-        except:
-            pass
-        return config
-
-    @staticmethod
-    def save(path, config: Dict) -> Dict:
-        try:
-            with open(path, "w", encoding="utf-8") as f:
-                yaml.dump(config, f, default_flow_style=False, allow_unicode=True)
-        except:
-            pass
-        return config
-
-
-class BaseEnum:
-
-    def __init_subclass__(cls, **kwargs):
-        super().__init_subclass__(**kwargs)
-        clsModule = cls.__module__
-        cls_path = inspect.getfile(cls)
-        clsFullName = f"{cls.__module__}.{cls.__name__}"
-        cls_dirpath = os.path.dirname(cls_path)  # .../src
-        clsModulePath = clsModule.replace(".", "\\")
-        current_dir = os.path.dirname(os.path.abspath(__file__))  # .../src
-        config_path = os.path.join(cls_dirpath, "config.yaml")
-        config = YamlUtil.load(config_path)
-        cls.init(config)
-        env = config.get("env")
-        if env:
-            env_config_path = os.path.join(cls_dirpath, f"config-{env}.yaml")
-            env_config = YamlUtil.load(env_config_path)
-            cls.init(env_config)
-
-    @classmethod
-    def init(cls, config=None):
-        clsName = cls.__name__
-        clsConfig = config and config.get(clsName)
-        if clsConfig:
-            for config_key, config_value in clsConfig.items():
-                new_config_key = config_key = config_key.upper().replace("-", "_")
-                if hasattr(cls, new_config_key):
-                    setattr(cls, new_config_key, config_value)
-
-
-class ApiEnum(BaseEnum):
-    API_KEY = None
-
-    API_SECRET_KEY = None
-
-    DATABASE_URL = ""
-
-    BASE_URL_OPEN_API = ""
-
-    BASE_URL_OPEN_H5 = ""
-
-    BASE_URL_HEALTH = ""
-
-    OPEN_TOKEN = ""
-
-    TOKEN = ""
-
-    DEFAULT__REQUEST_TIMEOUT = 120
-
-    DEFAULT__PAGE_SIZE = 5
-
-    DEFAULT__PAGE_SIZE_MAX = 65536
-
-    GET_DOWNLOAD_URL__URL = BASE_URL_OPEN_API + "/api/tos/get-download-url"
-
-
-class ConstantEnum(BaseEnum):
-    class SourceEnum(Enum):
-        ARK_CLAW = "ARK_CLAW"
-        JVS_CLAW = "JVS_CLAW"
-        LIGHT_CLAW = "LIGHT_CLAW"
-        WUHONG = "WUHONG"
-        COZE = "COZE"
-        SKILL_HUB = "SKILL_HUB"
-        CLAW_HUB = "CLAW_HUB"
-        FEISHU = "FEISHU"
-        DINGTALK = "DINGTALK"
-        WEIXIN = "WEIXIN"
-        YUANBAO = "YUANBAO"
-        WECOM = "WECOM"
-        QQBOT = "QQBOT"
-
-    APP__ID = ""
-
-    APP__SOURCE = SourceEnum.CLAW_HUB.value
-
-    IS_DEBUG = False
-
-    CURRENT__OPEN_ID = ""
-
-    CURRENT__USER_NAME = ""
-
-    CURRENT__TENTANT_CODE = ""
-
-    FEISHU_APP__ID = ""
-
-    FEISHU_APP__SECRET = ""
-
-    FEISHU_APP__RECEIVE_ID = ""
-
-    DEFAULT__SCENE_CODE = ""
-
-    DEFAULT__SKILL_HUB_NAME = APP__SOURCE
-
-    DEFAULT__SKILL_PLATFORM_NAME = ""
-
-    DEFAULT__OUTPUT_LEVEL = "json"
-
-    SUPPORTED_FORMATS = ["mp4", "avi", "mov"]
-
-    MAX_FILE_SIZE_MB = 10
-
-    @staticmethod
-    def is_debug():
-        return platform.system() != 'Linux' and ConstantEnum.IS_DEBUG
-
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-        openclaw_sender_open_id = os.environ.get("OPENCLAW_SENDER_OPEN_ID")
-        openclaw_sender_username = os.environ.get("OPENCLAW_SENDER_USERNAME")
-        feishu_open_id = os.environ.get("FEISHU_OPEN_ID")
-        if openclaw_sender_open_id:
-            cls.CURRENT__OPEN_ID = openclaw_sender_open_id
-        if openclaw_sender_username:
-            cls.CURRENT__USER_NAME = openclaw_sender_username
-        if feishu_open_id:
-            cls.FEISHU_APP__RECEIVE_ID = feishu_open_id
-
-    class SceneCodeEnum(Enum):
-        # 开放 #
-        OPEN_HEALTH_AI_ANALYSIS = "OPEN_HEALTH_AI_ANALYSIS"
-        OPEN_PERSON_RISK_ANALYSIS = "OPEN_PERSON_RISK_ANALYSIS"
-        # 智眸 #
-        PUBLIC_AREA_AI_ANALYSIS = "PUBLIC_AREA_AI_ANALYSIS"
-        PERSONNEL_LEAVE_POST_MONITORING = "PERSONNEL_LEAVE_POST_MONITORING"
-        CRAWL_MONITOR = "CRAWL_MONITOR"
-        # 陪你安 #
-        PEI_NI_AN_DEFAULT = "PEI_NI_AN_DEFAULT"
-        PET_ANALYSIS = "PET_ANALYSIS"
-        CRAWL_ANALYSIS = "CRAWL_ANALYSIS"
-        AQUARIUM_ANALYSIS = "AQUARIUM_ANALYSIS"
-        PSYCHOLOGY_ANALYSIS = "PSYCHOLOGY_ANALYSIS"
-        AUTISM_ANALYSIS = "AUTISM_ANALYSIS"
-        DIET_ANALYSIS = "DIET_ANALYSIS"
-        DRIVE_ANALYSIS = "DRIVE_ANALYSIS"
-        SPORT_ANALYSIS = "SPORT_ANALYSIS"
-        EMOTION_ANALYSIS = "EMOTION_ANALYSIS"
-        STUDY_ANALYSIS = "STUDY_ANALYSIS"
-        INFANT_SAFETY_MONITORING_ANALYSIS = "INFANT_SAFETY_MONITORING"
-        PHONE_USAGE_MONITORING_ANALYSIS = "PHONE_USAGE_MONITORING"
-        INCONTINENCE_ALERT_ANALYSIS = "INCONTINENCE_ALERT"
-        RESPIRATORY_SYMPTOM_RECOGNITION_ANALYSIS = "RESPIRATORY_SYMPTOM_RECOGNITION"
-        ELECTRIC_VEHICLE_DETECTION_ANALYSIS = "ELECTRIC_VEHICLE_DETECTION"
-        SMOKING_DETECTION_ANALYSIS = "SMOKING_DETECTION"
-        PET_DETECTION_FEEDER_ANALYSIS = "PET_DETECTION_FEEDER"
-        PET_HEALTH_MONITORING_ANALYSIS = "PET_HEALTH_MONITORING"
-        STROKE_RISK_SCREENING_ANALYSIS = "STROKE_RISK_SCREENING"
-        HUMAN_DETECTION_ANALYSIS = "HUMAN_DETECTION"
-        STRANGER_RECOGNITION_ANALYSIS = "STRANGER_RECOGNITION"
-        FOCUS_ANALYSIS_ANALYSIS = "FOCUS_ANALYSIS"
-        HUMAN_POSTURE_RECOGNITION_ANALYSIS = "HUMAN_POSTURE_RECOGNITION"
-        HUMAN_EMOTION_RECOGNITION_ANALYSIS = "HUMAN_EMOTION_RECOGNITION"
-        FIRE_SMOKE_DETECTION_ANALYSIS = "FIRE_SMOKE_DETECTION"
-        BASIC_OBJECT_DETECTION_ANALYSIS = "BASIC_OBJECT_DETECTION"
-        CHILD_DANGEROUS_BEHAVIOR_RECOGNITION_ANALYSIS = "CHILD_DANGEROUS_BEHAVIOR_RECOGNITION"
-        PET_RESTRICTED_AREA_WARNING_ANALYSIS = "PET_RESTRICTED_AREA_WARNING"
-        SLEEP_QUALITY_ANALYSIS_ANALYSIS = "SLEEP_QUALITY_ANALYSIS"
-        PET_DETECTION_ANALYSIS = "PET_DETECTION"
-        PSYCHOLOGICAL_STRESS_ASSESSMENT_ANALYSIS = "PSYCHOLOGICAL_STRESS_ASSESSMENT"
-        VISUAL_QA_ANALYSIS = "VISUAL_QA"
-        PET_BODY_HEALTH_ANALYSIS = "PET_BODY_HEALTH_ANALYSIS"
-        PET_BEHAVIOR_DETECTION_ANALYSIS = "PET_BEHAVIOR_DETECTION"
-        INFANT_SUFFOCATION_WARNING_ANALYSIS = "INFANT_SUFFOCATION_WARNING"
-        STRANGER_APPROACH_WARNING_ANALYSIS = "STRANGER_APPROACH_WARNING"
-        IMAGE_QUALITY_DETECTION_ANALYSIS = "IMAGE_QUALITY_DETECTION"
-        CHILD_EMOTION_RECOGNITION_ANALYSIS = "CHILD_EMOTION_RECOGNITION"
-        OUTDOOR_MONITORING_ANALYSIS = "OUTDOOR_MONITORING"
-        FALL_DETECTION_IMAGE_ANALYSIS = "FALL_DETECTION_IMAGE"
-        CUSTOM_TIMELAPSE_ANALYSIS = "CUSTOM_TIMELAPSE"
-        CONTACTLESS_VITAL_SIGNS_MONITORING_ANALYSIS = "CONTACTLESS_VITAL_SIGNS_MONITORING"
-        VIDEO_SEARCH_ANALYSIS = "VIDEO_SEARCH"
-        FAMILIAR_PERSON_RECOGNITION_ANALYSIS = "FAMILIAR_PERSON_RECOGNITION"
-        TCM_CONSTITUTION_RECOGNITION_ANALYSIS = "TCM_CONSTITUTION_RECOGNITION"
-        CONTACTLESS_HEALTH_RISK_DETECTION_ANALYSIS = "CONTACTLESS_HEALTH_RISK_DETECTION"
-        UNACCOMPANIED_MONITORING_ANALYSIS = "UNACCOMPANIED_MONITORING"
-        ELDERLY_FALL_DETECTION_ANALYSIS = "ELDERLY_FALL_DETECTION"
-        PARKINSON_EPILEPSY_BEHAVIOR_RECOGNITION_ANALYSIS = "PARKINSON_EPILEPSY_BEHAVIOR_RECOGNITION"
-        PET_BREED_INDIVIDUAL_RECOGNITION_ANALYSIS = "PET_BREED_INDIVIDUAL_RECOGNITION"
-        ELDERLY_BED_EXIT_WANDERING_MONITORING_ANALYSIS = "ELDERLY_BED_EXIT_WANDERING_MONITORING"
-        ARRHYTHMIA_EARLY_WARNING_ANALYSIS = "ARRHYTHMIA_EARLY_WARNING"
-        FIRE_DETECTION_ANALYSIS = "FIRE_DETECTION"
-        VISUAL_SUMMARY_ANALYSIS = "VISUAL_SUMMARY"
-        PACKAGE_DETECTION_ANALYSIS = "PACKAGE_DETECTION"
-        INFANT_BLANKET_KICK_MONITORING_ANALYSIS = "INFANT_BLANKET_KICK_MONITORING"
-        PET_CALMING_TRIGGER_ANALYSIS = "PET_CALMING_TRIGGER"
-        CAT_FACE_RECOGNITION_ANALYSIS = "CAT_FACE_RECOGNITION"
-        INFANT_SLEEP_MONITORING_ANALYSIS = "INFANT_SLEEP_MONITORING"
-        VIRTUAL_FENCE_INTRUSION_WARNING_ANALYSIS = "VIRTUAL_FENCE_INTRUSION_WARNING"
-        FALL_DETECTION_VIDEO_ANALYSIS = "FALL_DETECTION_VIDEO"
-        INFANT_CRY_ANALYSIS = "INFANT_CRY_ANALYSIS"
-        PET_VOCAL_EMOTION_ANALYSIS = "PET_VOCAL_EMOTION_ANALYSIS"
-        BIRD_RECOGNITION_ANALYSIS = "BIRD_RECOGNITION"
-        FRAUD_CALL_IDENTIFICATION = "FRAUD_CALL_IDENTIFICATION"

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/config.yaml

@@ -1,18 +0,0 @@
-env: prod
-
-ApiEnum:
-  api-key:
-  api-secret-key:
-  database-url:
-  base-url-open-api: "https://open.lifeemergence.com/smyx-open-api"
-  base-url-open-h5: "http://livemonitor.lifeemergence.com"
-  base-url-health: "https://lifeemergence.com/jeecg-boot"
-
-ConstantEnum:
-  is-debug: false
-  app--id: x1a3s4nwy1s2r4se
-  current--tentant-code: "PEI_NI_AN"
-  feishu-app--id: cli_a93d769369badcb1
-  feishu-app--secret:
-  default--skill-platform-name: ARK_CLAW
-#  default--scene-code: PEI_NI_AN_DEFAULT

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/dao.py

@@ -1,348 +0,0 @@
-#!/usr/bin/env python3
-"""
-本地化轻量级数据库封装
-使用SQLite + SQLAlchemy ORM
-支持基础CRUD操作，通过继承BaseDao快速实现各表的Dao层
-"""
-import datetime
-import sys
-from enum import Enum
-from typing import Any, Dict, List, Optional, Type, TypeVar
-from sqlalchemy import create_engine, Column, Integer, String, DateTime, func, Select, Table, MetaData, select, or_
-from sqlalchemy.orm import declarative_base
-from sqlalchemy.orm import sessionmaker, Session
-from sqlalchemy.sql.expression import text
-
-from skills.smyx_common.scripts.config import ConstantEnum, ApiEnum
-
-from skills.smyx_common.scripts.util import StringUtil, DatetimeUtil, FileUtil
-
-from skills.smyx_common.scripts.base import BaseMixin, BaseDao
-
-# 基础模型类
-Base = declarative_base()
-
-# 泛型类型，用于返回对应模型实例
-T = TypeVar('T', bound=Base)
-
-meta = MetaData()
-
-DATABASE_URL = ApiEnum.DATABASE_URL
-
-
-class BaseModelMixin(BaseMixin):
-
-    @classmethod
-    def load(cls, source: dict):
-        """
-        获取源枚举
-        :param source: 源
-        :return: User
-        """
-        column_names = cls.__table__.columns.keys()
-        user_dict = {k: source.get(StringUtil.snake_to_camel(k)) for k in column_names}
-        user_dict["create_time"] = DatetimeUtil.parse(user_dict["create_time"])
-        user_dict["update_time"] = DatetimeUtil.parse(user_dict["update_time"])
-        model = cls(**user_dict)
-        return model
-
-
-class Dao(BaseDao):
-    """
-    基础Dao类，提供通用的CRUD操作
-    子类只需配置__model__和__tablename__即可使用
-    """
-    __model__: Type[T] = None  # 对应的模型类，子类必须配置
-    __tablename__: str = None  # 表名，子类必须配置
-
-    def get_db_path(self, db_path):
-        import os
-
-        cwd = os.getcwd()
-        workspace = os.path.dirname(cwd)
-        workspace = os.path.dirname(workspace)
-        workspace = os.environ.get('OPENCLAW_WORKSPACE', workspace)
-        parent_dir = os.path.join(workspace, "data")
-        FileUtil.mkdir(parent_dir)
-        db_path = os.path.join(parent_dir, db_path)
-
-        return db_path
-
-    def __init__(self, db_path: str = None):
-        """
-        初始化Dao
-        :param db_path: SQLite数据库文件路径
-        """
-
-        if not db_path:
-            db_path = "smyx-common-claw.db"
-            db_path = self.get_db_path(db_path)
-
-        self.engine = create_engine(f"sqlite:///{db_path}", echo=False)
-
-        # 创建会话工厂
-        self.SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=self.engine)
-        # 初始化表结构
-        self._create_tables()
-        self._alter_tables()
-
-    def _create_tables(self) -> None:
-        """创建所有表结构"""
-        Base.metadata.create_all(bind=self.engine)
-
-    def _alter_tables(self) -> None:
-        """创建所有表结构"""
-        sql_statement = "ALTER TABLE sys_user ADD COLUMN source_id INT;"
-
-        # 3. 执行语句
-        try:
-            with self.engine.connect() as connection:
-                connection.execute(text(sql_statement))
-                connection.commit()  # 对于数据定义语言(DDL)，需要显式提交
-        except Exception as e:
-            connection.rollback()
-            if len(e.args) and "duplicate column name" in e.args[0]:
-                pass
-            else:
-                raise
-
-    def get_session(self) -> Session:
-        """获取数据库会话"""
-        return self.SessionLocal()
-
-    def save(self, model) -> T:
-        """
-        创建新记录
-        :param kwargs: 字段键值对
-        :return: 创建的模型实例
-        """
-
-        try:
-            return self.add(
-                model
-            )
-
-        except Exception as e:
-            return self.update(
-                model
-            )
-
-    def add(self, model) -> T:
-        """
-        创建新记录
-        :param kwargs: 字段键值对
-        :return: 创建的模型实例
-        """
-        session = self.get_session()
-        try:
-            session.add(model)
-            session.commit()
-            session.refresh(model)
-            return model
-        finally:
-            session.close()
-
-    def create(self, **kwargs) -> T:
-        """
-        创建新记录
-        :param kwargs: 字段键值对
-        :return: 创建的模型实例
-        """
-        instance = self.__model__(**kwargs)
-        return self.add(instance)
-
-    def get_by_id(self, record_id: int) -> Optional[T]:
-        """
-        根据ID查询记录
-        :param record_id: 记录ID
-        :return: 模型实例或None
-        """
-        session = self.get_session()
-        try:
-            return session.query(self.__model__).filter(self.__model__.id == record_id).first()
-        finally:
-            session.close()
-
-    def get_by_username(self, username: str) -> Optional[T]:
-        """
-        根据ID查询记录
-        :param record_id: 记录ID
-        :return: 模型实例或None
-        """
-        session = self.get_session()
-        try:
-            or_(
-                self.__model__.del_flag == 0,
-                self.__model__.del_flag.is_(None)  # 关键：使用 .is_(None) 来判断 SQL 的 NULL
-            )
-            return session.query(self.__model__).filter(self.__model__.username == username,
-                                                        or_(
-                                                            self.__model__.del_flag == 0,
-                                                            self.__model__.del_flag.is_(None)
-                                                            # 关键：使用 .is_(None) 来判断 SQL 的 NULL
-                                                        )).first()
-        finally:
-            session.close()
-
-    def list(self, filters: Optional[Dict[str, Any]] = None, limit: Optional[int] = None,
-             offset: Optional[int] = None) -> List[T]:
-        """
-        查询记录列表
-        :param filters: 过滤条件字典，如{"name": "张三", "age": 18}
-        :param limit: 最大返回数量
-        :param offset: 偏移量
-        :return: 模型实例列表
-        """
-        session = self.get_session()
-        try:
-            query = session.query(self.__model__)
-            # .where(self.__model__.id != 2, self.__model__.id == 1))
-
-            if filters:
-                for key, value in filters.items():
-                    query = query.filter(getattr(self.__model__, key) == value)
-
-            if offset:
-                query = query.offset(offset)
-            if limit:
-                query = query.limit(limit)
-
-            return query.all()
-        finally:
-            session.close()
-
-    def update(self, model) -> Optional[T]:
-        """
-        更新记录
-        :param record_id: 记录ID
-        :param kwargs: 要更新的字段键值对
-        :return: 更新后的模型实例或None
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.id == model.id).first()
-            if not instance:
-                return None
-
-            column_names = self.__model__.__table__.columns.keys()
-
-            for key in column_names:
-                value = getattr(model, key)
-                setattr(instance, key, value)
-
-            session.commit()
-            session.refresh(instance)
-            return instance
-        finally:
-            session.close()
-
-    def modify(self, record_id: int, **kwargs) -> Optional[T]:
-        """
-        更新记录
-        :param record_id: 记录ID
-        :param kwargs: 要更新的字段键值对
-        :return: 更新后的模型实例或None
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.id == record_id).first()
-            if not instance:
-                return None
-
-            for key, value in kwargs.items():
-                setattr(instance, key, value)
-
-            session.commit()
-            session.refresh(instance)
-            return instance
-        finally:
-            session.close()
-
-    def update_by_username(self, username: str, **kwargs) -> Optional[T]:
-        """
-        更新记录
-        :param username: 记录ID
-        :param kwargs: 要更新的字段键值对
-        :return: 更新后的模型实例或None
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.username == username).first()
-            if not instance:
-                return None
-
-            for key, value in kwargs.items():
-                setattr(instance, key, value)
-
-            session.commit()
-            session.refresh(instance)
-            return instance
-        finally:
-            session.close()
-
-    def delete(self, record_id: int) -> bool:
-        """
-        删除记录
-        :param record_id: 记录ID
-        :return: 删除成功返回True，失败返回False
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.id == record_id).first()
-            if not instance:
-                return False
-
-            session.delete(instance)
-            session.commit()
-            return True
-        finally:
-            session.close()
-
-    def count(self, filters: Optional[Dict[str, Any]] = None) -> int:
-        """
-        统计记录数量
-        :param filters: 过滤条件字典
-        :return: 记录数量
-        """
-        session = self.get_session()
-        try:
-            query = session.query(func.count(self.__model__.id))
-
-            if filters:
-                for key, value in filters.items():
-                    query = query.filter(getattr(self.__model__, key) == value)
-
-            return query.scalar()
-        finally:
-            session.close()
-
-
-class User(Base, BaseModelMixin):
-    """用户模型"""
-    __tablename__ = "sys_user"
-
-    id = Column(String(32), primary_key=True, index=True)
-    source_id = Column(String(32), comment="源头id")
-    username = Column(String(100), unique=True, index=True, nullable=False, comment="用户名")
-    email = Column(String(45), unique=True, index=True, comment="邮箱")
-    birthday = Column(DateTime, unique=True, index=True, comment="邮箱")
-    sex = Column(Integer, comment="性别")
-    age = Column(Integer, comment="年龄")
-    token = Column(String(500), comment="token")
-    open_token = Column(String(1000), comment="开放token")
-    source = Column(String(50), comment="token")
-    del_flag = Column(Integer, comment="是否删除", default=0)
-    create_time = Column(DateTime, default=func.now(), comment="创建时间")
-    update_time = Column(DateTime, default=func.now(), onupdate=func.now(), comment="更新时间")
-
-    SourceEnum = ConstantEnum.SourceEnum
-
-
-class UserDao(Dao):
-    """用户Dao，继承BaseDao即可拥有所有基础CRUD功能"""
-    __model__ = User
-    __tablename__ = "users"
-
-
-if __name__ == "__main__":
-    pass

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/skill.py

@@ -1,82 +0,0 @@
-#!/usr/bin/env python3
-import os
-import sys
-import subprocess
-
-from .config import ApiEnum as ApiEnumBase, ConstantEnum
-from .base import BaseSkill
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-from .util import FileUtil
-
-from .api_service import ApiService
-
-class Skill(BaseSkill, ApiService):
-
-    def __init__(self):
-        super().__init__()
-
-class AgentSkill(BaseSkill, ApiService):
-
-    def __init__(self):
-        super().__init__()
-
-    def ai_chat(self, prompt: str, session_id: str = None, timeout: int = 120):
-        """
-        通过 subprocess 调用 openclaw agent 命令
-
-        Args:
-            prompt: 分析提示
-            session_id: 会话 ID（可选）
-            timeout: 超时时间（秒）
-
-        Returns:
-            分析结果或会话 ID
-        """
-        import uuid
-
-        # 生成唯一会话 ID
-        if not session_id:
-            entry_script = sys.argv[0]
-            abs_entry_script = os.path.abspath(entry_script)
-            main_name = FileUtil.get_name(abs_entry_script)
-            session_id = f"{main_name}--{uuid.uuid4()}"
-
-        ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent (会话：{session_id})..., prompt:{prompt}")
-
-        # 构建命令
-        cmd = [
-            "openclaw",
-            "agent",
-            "-m", str(prompt),
-            "--session-id", session_id,
-            "--thinking", "minimal",
-            "--timeout", str(timeout)
-        ]
-
-        ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行命令{' '.join(cmd)}")
-
-        try:
-            # 执行命令
-            result = subprocess.run(
-                cmd,
-                capture_output=True,
-                text=True,
-                timeout=timeout + 10
-            )
-
-            if result.stderr:
-                ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行错误:{result.stderr}")
-                return
-
-            output = result.stdout
-            ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行成功:{output}")
-
-            return output
-
-        except subprocess.TimeoutExpired as e:
-            ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 超时（{timeout}秒），任务可能仍在后台运行:{e}")
-        except Exception as e:
-            ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行错误:{e}")
-
-
-skill = Skill()

skills/18072937735/smyx-basic-object-detection-analysis/skills/smyx_common/scripts/util.py

@@ -1,413 +0,0 @@
-#!/usr/bin/env python3
-import json
-import os
-import traceback
-
-import requests
-from .config import ApiEnum, ConstantEnum, sys, YamlUtil
-
-from .base import BaseUtil
-import time
-import logging
-from typing import Any, Callable, Optional, TypeVar, Dict
-import pydash as _
-
-if ConstantEnum.is_debug():
-    import http.client
-
-    # 【关键代码】开启调试模式
-    http.client.HTTPConnection.debuglevel = 1
-    # 可选：如果你希望日志更整洁，可以配合 logging 模块（否则打印会比较乱）
-    import logging
-
-    logging.basicConfig()
-    logging.getLogger().setLevel(logging.DEBUG)
-    requests_log = logging.getLogger("urllib3")
-    requests_log.setLevel(logging.DEBUG)
-    requests_log.propagate = True
-
-
-class StringUtil(BaseUtil):
-
-    @staticmethod
-    def camel_to_snake(name):
-        import re
-        s1 = re.sub('(.)([A-Z][a-z]+)', r'\1_\2', name)
-        return re.sub('([a-z0-9])([A-Z])', r'\1_\2', s1).lower()
-
-    @staticmethod
-    def snake_to_pascal(name):
-        import re
-        name = re.sub(r'^([a-z])', lambda m: m.group(1).upper(), name)
-        return re.sub(r'_([a-z])', lambda m: m.group(1).upper(), name)
-
-    @staticmethod
-    def snake_to_camel(name):
-        import re
-        # 逻辑：匹配 '_[a-z]' (下划线+小写字母)，将其替换为对应的大写字母（去掉下划线）
-        return re.sub(r'_([a-z])', lambda m: m.group(1).upper(), name)
-
-
-class FileUtil(BaseUtil):
-
-    @staticmethod
-    def get_fullname(path):
-        try:
-            return os.path.basename(path)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            return ""
-
-    @staticmethod
-    def get_name(path):
-        try:
-            return os.path.splitext(os.path.basename(path))[0]
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-    @staticmethod
-    def get_ext(path):
-        try:
-            return os.path.splitext(os.path.basename(path))[1]
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-    @staticmethod
-    def open(path):
-        try:
-            return open(path, 'w', encoding='utf-8')
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-    @staticmethod
-    def mkdir(path):
-        try:
-            os.makedirs(path, exist_ok=True)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-
-class JsonUtil(BaseUtil):
-
-    @staticmethod
-    def stringify(json_obj, default_str=""):
-        try:
-            return json.dumps(json_obj, ensure_ascii=False, indent=2)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            pass
-        return default_str
-
-    @staticmethod
-    def parse(json_str, default_json={}):
-        try:
-            return json.loads(json_str)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            pass
-        return default_json
-
-
-class CommonUtil(BaseUtil):
-
-    @staticmethod
-    def trace_exception_stack(e):
-        if ConstantEnum.is_debug():
-            print(f"❌ 错误描述: {str(e)}, 堆栈跟踪:")
-            traceback.print_stack()
-
-    @staticmethod
-    def polling(
-            action: Callable[[], Any],
-            check_condition: Callable[[Any], bool],
-            on_success: Optional[Callable[[Any], None]] = None,
-            on_retry: Optional[Callable[[Any, int], None]] = None,
-            on_error: Optional[Callable[[Exception], None]] = None,
-            interval: float = 1.0,
-            max_attempts: int = 5,
-            description: str = "轮询任务"
-    ) -> Optional[Any]:
-        """
-        通用的轮询处理函数
-
-        :param action:
-            [必填] 执行动作的回调函数。
-            例如：发送 HTTP 请求、查询数据库状态等。
-            必须返回一个结果对象供 check_condition 使用。
-
-        :param check_condition:
-            [必填] 检查是否结束的回调函数。
-            接收 action 的返回值，返回 True 表示“满足结束条件”，False 表示“继续轮询”。
-            例如：lambda res: res.get('need_refresh') is False
-
-        :param on_success:
-            [可选] 当 check_condition 返回 True 时执行的回调（通常用于记录日志或处理最终数据）。
-
-        :param on_retry:
-            [可选] 当需要继续轮询时执行的回调。
-            参数：(当前结果, 当前尝试次数)。可用于打印进度。
-
-        :param on_error:
-            [可选] 当 action 抛出异常时执行的回调。
-            参数：(异常对象)。
-
-        :param interval:
-            每次轮询之间的等待时间（秒）。
-
-        :param max_attempts:
-            最大尝试次数，防止死循环。
-
-        :param description:
-            任务描述，用于日志输出。
-
-        :return:
-            如果成功，返回 action 的最后一次返回值；如果超时或失败，返回 None。
-        """
-
-        attempts = 0
-
-        print(f"🚀 开始执行 [{description}]...")
-
-        while attempts < max_attempts:
-            attempts += 1
-
-            try:
-                # 1. 执行动作
-                result = action()
-                last_result = result
-
-                # 2. 检查条件
-                if check_condition(result):
-                    print(f"✅ [{description}] 成功！条件已满足 (尝试次数: {attempts}, 耗时{interval * attempts}秒)")
-                    if on_success:
-                        on_success(result)
-                    return result
-
-                # 3. 条件未满足，准备重试
-                if on_retry:
-                    on_retry(result, attempts)
-                else:
-                    # 默认日志行为
-                    print(
-                        f"⏳ [{description}] 条件未满足，{interval}秒后重试... ({attempts}/{max_attempts}, 耗时{interval * attempts}秒)")
-
-                time.sleep(interval)
-
-            except Exception as e:
-                # 4. 异常处理
-                if on_error:
-                    on_error(e)
-                else:
-                    # 默认错误行为：打印错误并继续
-                    logging.error(f"❌ [{description}] 发生异常: {e}")
-                    print(f"⚠️ [{description}] 遇到错误，{interval}秒后重试...")
-
-                time.sleep(interval)
-
-        # 5. 超时处理
-        print(f"⚠️ [{description}] 失败：达到最大尝试次数 ({max_attempts})，强制停止。")
-        return None
-
-    @staticmethod
-    def is_empty(data):
-        # 1. 如果是 None (对应 JSON 的 null)
-        if data is None:
-            return True
-
-        # 2. 如果是字典或列表，且长度为 0 (对应 {} 或 [])
-        if isinstance(data, (dict, list)) and len(data) == 0:
-            return True
-
-
-from datetime import date, datetime
-
-
-class DatetimeUtil(BaseUtil):
-    FORMAT__DATETIME = "%Y-%m-%d %H:%M:%S"
-
-    @staticmethod
-    def now_str():
-        return DatetimeUtil.format(DatetimeUtil.now())
-
-    @staticmethod
-    def today_str():
-        return DatetimeUtil.format_date(DatetimeUtil.today())
-
-    @staticmethod
-    def now():
-        return datetime.now()
-
-    @staticmethod
-    def today():
-        return DatetimeUtil.now().replace(hour=0, minute=0, second=0, microsecond=0)
-
-    @staticmethod
-    def format(date):
-        return date.strftime('%Y-%m-%d %H:%M:%S') if type(date) == datetime else date
-
-    @staticmethod
-    def format_date(date):
-        return date.strftime('%Y-%m-%d') if type(date) == datetime else date
-
-    @staticmethod
-    def parse(date_str):
-        if type(date_str) == int:
-            return datetime.fromtimestamp(date_str)
-        return datetime.strptime(date_str, DatetimeUtil.FORMAT__DATETIME) if type(date_str) == str else date_str
-
-    @staticmethod
-    def timestamp(date=now()):
-        return int(date.timestamp() * 1000)
-
-
-class RequestUtil(BaseUtil):
-    BASE_URL = ApiEnum.BASE_URL_OPEN_API
-    AUTHORIZATION_RETRY_COUNT_MAX = 3
-    authorization_retry_count = 0
-
-    @classmethod
-    def http_post(cls, url, data=None, params=None, headers=None, *args, **argss):
-        return cls.http_request("post", url, data=data, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_put(cls, url, data=None, params=None, headers=None, *args, **argss):
-        return cls.http_request("put", url, data=data, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_delete(cls, url, data=None, params=None, headers=None, *args, **argss):
-        return cls.http_request("delete", url, data=data, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_get(cls, url, params=None, headers=None, *args, **argss):
-        return cls.http_request("get", url, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_request(cls, method, url, data=None, params=None, headers=None, options=None, *args,
-                     timeout=ApiEnum.DEFAULT__REQUEST_TIMEOUT, **argss):
-        def _get_or_create_user(username):
-            _url = ApiEnum.BASE_URL_HEALTH + "/sys/phoneLogin"
-            open_id = username
-            _data = {
-                "silent": 1,
-                "register": 1,
-                "openId": open_id,
-                "mobile": username
-            }
-            try:
-                _response = requests.post(_url, json=_data)
-                if _response.status_code == 200:
-                    _response_json = _response.json()
-                    if _response_json and _response_json.get("success"):
-                        return _response_json and _response_json.get("result")
-            except Exception as _e:
-                CommonUtil.trace_exception_stack(_e)
-            return {}
-
-        try:
-            headers = headers or {}
-            if not url.startswith("https://") and not url.startswith("http://"):
-                url = cls.BASE_URL + url
-            headers['App-Id'] = ConstantEnum.APP__ID
-            # ConstantEnum.CURRENT__USER_NAME = ConstantEnum.CURRENT__OPEN_ID = "ou_86fdd8e0d5f116c18a9dd550abefe6d2"
-            current__user_name = ApiEnum.API_SECRET_KEY or ConstantEnum.CURRENT__USER_NAME or ConstantEnum.CURRENT__OPEN_ID
-            if (not ApiEnum.TOKEN or not ApiEnum.OPEN_TOKEN) and current__user_name:
-                try:
-                    from .dao import UserDao, User
-                    user_dao = UserDao()
-                    found_user = user_dao.get_by_username(current__user_name)
-                    if found_user:
-                        ApiEnum.TOKEN = found_user.token
-                        ApiEnum.OPEN_TOKEN = found_user.open_token
-                    if not ApiEnum.TOKEN or not ApiEnum.OPEN_TOKEN:
-                        new_current_user = _get_or_create_user(current__user_name)
-                        if new_current_user:
-                            ApiEnum.TOKEN = new_current_user.get("token")
-                            ApiEnum.OPEN_TOKEN = new_current_user.get("openToken")
-
-                            current_user_info = new_current_user.get("userInfo")
-                            if current_user_info:
-                                current_user_info["token"] = new_current_user.get("token")
-                                current_user_info["openToken"] = new_current_user.get(
-                                    "openToken")
-                                user_model = User.load(current_user_info)
-
-                                user = user_dao.save(
-                                    user_model
-                                )
-
-                except Exception as e:
-                    CommonUtil.trace_exception_stack(e)
-                    raise
-
-            headers.setdefault("X-Access-Token", ApiEnum.TOKEN)
-            headers.setdefault("X-Api-Key", ApiEnum.API_SECRET_KEY)
-            headers.setdefault("Authorization", ApiEnum.OPEN_TOKEN)
-
-            data = data or {}
-            params = params or {}
-            options = options or {}
-            ConstantEnum.CURRENT__TENTANT_CODE and data.setdefault('tenantCode', ConstantEnum.CURRENT__TENTANT_CODE)
-            ConstantEnum.DEFAULT__SKILL_HUB_NAME and data.setdefault('skillHubName',
-                                                                     ConstantEnum.DEFAULT__SKILL_HUB_NAME)
-            ConstantEnum.DEFAULT__SKILL_PLATFORM_NAME and data.setdefault('skillPlatform',
-                                                                          ConstantEnum.DEFAULT__SKILL_PLATFORM_NAME)
-            if current__user_name:
-                data.setdefault('pnaUserName', current__user_name)
-
-            if bool(options.get("dataAsParams")):
-                params.update(data)
-
-            print(f"🔄 请求拦截, URL:{url}", "method", method, "params", params, "data", data, "headers", headers,
-                  "options", options,
-                  "timeout",
-                  timeout)
-            response = requests.request(method, url, *args, json=data, params=params, headers=headers,
-                                        timeout=int(timeout), **argss)
-            response_text = response.text if ConstantEnum.is_debug() else response
-            if response.status_code == 401 and cls.authorization_retry_count < cls.AUTHORIZATION_RETRY_COUNT_MAX:
-                print(f"❌ 请求拦截, 鉴权:{response_text}, url:{url}", "method", method, "params", params,
-                      "data",
-                      data,
-                      "headers",
-                      headers,
-                      "timeout",
-                      timeout)
-                ApiEnum.TOKEN = ApiEnum.OPEN_TOKEN = None
-                if found_user:
-                    found_user.token = found_user.open_token = None
-                    user_dao.update(found_user)
-                cls.authorization_retry_count += 1
-                return cls.http_request(method, url, data, params, headers, options, *args, timeout=timeout, **argss)
-            elif response.status_code != 200:
-                raise requests.exceptions.RequestException(
-                    response, response=response)
-            response_json = response.json()
-            if not bool(response_json['success']):
-                raise requests.exceptions.RequestException(
-                    response, response=response)
-            response_json_data = response_json.get("data", response_json.get("result"))
-            response_json_data = response_json_data.get("records") if response_json_data and type(
-                response_json_data) == dict and "records" in response_json_data else response_json_data
-            print(f"✅ 请求拦截, 成功:{response_text}, url:{url}", "method", method, "params", params,
-                  "data",
-                  data,
-                  "headers",
-                  headers,
-                  "timeout",
-                  timeout)
-            return response_json_data
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            response_text = _.get(e.args, '0.text')
-            print(
-                f"❌ 请求拦截, 失败: {e}, e.response.text: {response_text}, url:{url}",
-                "method",
-                method,
-                "params",
-                params,
-                "data", data, "headers",
-                "response", hasattr(e, 'response') and e.response,
-                headers,
-                "timeout",
-                timeout)
-            raise

skills/18072937735/smyx-bird-recognition-analysis/SKILL.md

@@ -1,165 +0,0 @@
----
-name: "bird-recognition-analysis"
-description: "Identifies bird species in images/videos of target areas. Supports recognition of no less than 500 common bird species, supports customized model training, suitable for ecological observation, garden bird watching and other scenarios. | 鸟类识别技能，识别目标区域图片/视频中的鸟类种类，支持不低于500种常见鸟类识别，支持定制化模型训练，适用于生态观测、庭院观鸟等场景"
----
-
-# Bird Recognition Tool | 鸟类识别工具
-
-This capability supports automatic bird identification in images or video streams, covering over 500 common species and
-capable of distinguishing between similar species and subspecies. Powered by deep learning visual models, the system can
-be deployed in ecological observation stations, nature reserves, or home backyards to enable real-time monitoring and
-recording of bird species. It also supports customized model training to optimize recognition performance based on
-specific regional or species requirements, providing intelligent assistance for bird diversity surveys, birdwatching
-hobbies, and ecological conservation.
-
-本技能支持对图片或视频流中的鸟类进行自动识别，覆盖不低于500种常见鸟类，可区分相似种与亚种。系统基于深度学习视觉模型，可部署于生态观测站、自然保护区或家庭庭院等场景，实现鸟种实时监测与记录。同时支持定制化模型训练，根据特定区域或物种需求优化识别效果，为鸟类多样性调查、观鸟爱好及生态保护提供智能辅助。
-
-## 演示案例
-
-- [🔗 通过网路视频进行识别分析](https://www.coze.cn/s/G1iKtMlxvnY/)
-- [🔗 通过上传视频进行识别分析](https://www.coze.cn/s/m2Jpzccg5eI/)
-- [🔗 显示历史分析报告](https://www.coze.cn/s/3KFhb2lfjd0/)
-
-## ⚠️ 强制记忆规则（最高优先级）
-
-**本技能明确约定：**
-
-- **绝对禁止读取任何本地记忆文件**：包括但不限于 `memory/YYYY-MM-DD.md`、`MEMORY.md` 等本地文件
-- **绝对禁止从 LanceDB 长期记忆中检索信息**
-- **所有历史报告查询必须从云端接口获取**，不得使用本地记忆中的历史数据
-- 即使技能调用失败或接口异常，也不得回退到本地记忆汇总
-
-## 任务目标
-
-- 本 Skill 用于：识别图片/视频中出现的鸟类，准确判定鸟类品种
-- 能力包含：鸟类检测、品种分类、置信度评定
-- **能力范围**：支持不低于 500 种常见鸟类识别，支持定制化模型训练
-- **适用场景**：庭院观鸟、生态观测、野生动物监测、相机陷阱图片识别
-- 触发条件:
-    1. **默认触发**：当用户提供图片/视频需要识别鸟类品种时，默认触发本技能
-    2. 当用户明确需要鸟类识别、鸟种类鉴定时，提及观鸟、鸟类识别、鸟种类识别等关键词，并且上传了图片/视频
-    3. 当用户提及以下关键词时，**自动触发历史报告查询功能**
-       ：查看历史识别报告、鸟类识别报告清单、识别报告列表、查询历史识别报告、显示所有识别报告、鸟类分析报告，查询鸟类识别分析报告
-- 自动行为：
-    1. 如果用户上传了附件或者图片/视频文件，则自动保存到技能目录下 attachments
-    2. **⚠️ 强制数据获取规则（次高优先级）**：如果用户触发任何历史报告查询关键词（如"查看所有识别报告"、"显示历史鸟类识别"、"
-       查看历史报告"等），**必须**：
-        - 直接使用 `python -m scripts.bird_recognition_analysis --list --open-id` 参数调用
-          API
-          查询云端的历史报告数据
-        - **严格禁止**：从本地 memory 目录读取历史会话信息、严格禁止手动汇总本地记录中的报告、严格禁止从长期记忆中提取报告
-        - **必须统一**从云端接口获取最新完整数据，然后以 Markdown 表格格式输出结果
-
-## 前置准备
-
-- 依赖说明:scripts 脚本所需的依赖包及版本
-  ```
-  requests>=2.28.0
-  ```
-
-## 识别要求（获得准确结果的前提）
-
-为了获得准确的鸟类识别，请确保：
-
-1. **鸟类完整清晰可见**，避免过度遮挡和远距离模糊拍摄
-2. **光照充足**，色彩自然，便于品种特征识别
-
-- 如果是视频，建议截取鸟类清晰停留的片段上传
-
-## 操作步骤
-
-### 🔒 open-id 获取流程控制（强制执行，防止遗漏）
-
-**在执行鸟类识别分析前，必须按以下优先级顺序获取 open-id：**
-
-```
-第 1 步：【最高优先级】检查技能所在目录的配置文件（优先）
-        路径：skills/smyx_common/scripts/config.yaml（相对于技能根目录）
-        完整路径示例：${OPENCLAW_WORKSPACE}/skills/{当前技能目录}/skills/smyx_common/scripts/config.yaml
-        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id
-        ↓ (未找到/未配置/api-key 为空)
-第 2 步：检查 workspace 公共目录的配置文件
-        路径：${OPENCLAW_WORKSPACE}/skills/smyx_common/scripts/config.yaml
-        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id
-        ↓ (未找到/未配置)
-第 3 步：检查用户是否在消息中明确提供了 open-id
-        ↓ (未提供)
-第 4 步：❗ 必须暂停执行，明确提示用户提供用户名或手机号作为 open-id
-```
-
-**⚠️ 关键约束：**
-
-- **禁止**自行假设,自行推导,自行生成 open-id 值（如 openclaw-control-ui、default、userC113、user123 等）
-- **禁止**跳过 open-id 验证直接调用 API
-- **必须**在获取到有效 open-id 后才能继续执行分析
-- 如果用户拒绝提供 open-id，说明用途（用于保存和查询历史报告记录），并询问是否继续
-
----
-
-- 标准流程:
-    1. **准备鸟类图片/视频输入**
-        - 提供本地文件路径或网络 URL
-        - 确保鸟类清晰可见
-    2. **获取 open-id（强制执行）**
-        - 按上述流程控制获取 open-id
-        - 如无法获取，必须提示用户提供用户名或手机号
-    3. **执行鸟类识别分析**
-        - 调用 `-m scripts.bird_recognition_analysis` 处理输入（**必须在技能根目录下运行脚本**）
-        - 参数说明:
-            - `--input`: 本地图片/视频文件路径（使用 multipart/form-data 方式上传）
-            - `--url`: 网络图片/视频 URL 地址（API 服务自动下载）
-            - `--open-id`: 当前用户的 open-id（必填，按上述流程获取）
-            - `--list`: 显示历史鸟类识别分析报告列表清单（可以输入起始日期参数过滤数据范围）
-            - `--api-key`: API 访问密钥（可选）
-            - `--api-url`: API 服务地址（可选，使用默认值）
-            - `--detail`: 输出详细程度（basic/standard/json，默认 json）
-            - `--output`: 结果输出文件路径（可选）
-    4. **查看分析结果**
-        - 接收结构化的鸟类识别分析报告
-        - 包含：输入基本信息、检测到的鸟类数量、每个鸟类品种、置信度、科普小知识
-
-## 资源索引
-
-- 必要脚本：见 [scripts/bird_recognition_analysis.py](scripts/bird_recognition_analysis.py)(用途：调用 API 进行鸟类识别分析，本地文件使用
-  multipart/form-data 方式上传，网络 URL 由 API 服务自动下载)
-- 配置文件：见 [scripts/config.py](scripts/config.py)(用途：配置 API 地址、默认参数和格式限制)
-- 领域参考：见 [references/api_doc.md](references/api_doc.md)(何时读取：需要了解 API 接口详细规范和错误码时)
-
-## 注意事项
-
-- 仅在需要时读取参考文档，保持上下文简洁
-- 支持格式：jpg/jpeg/png/mp4/avi/mov，最大 100MB
-- API 密钥可选，如果通过参数传入则必须确保调用鉴权成功，否则忽略鉴权
-- 识别结果仅供自然观察参考，物种保护请遵循当地法律法规
-- 禁止临时生成脚本，只能用技能本身的脚本
-- 传入的网路地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载
-- 当显示历史分析报告清单的时候，从数据 json 中提取字段 reportImageUrl 作为超链接地址，使用 Markdown 表格格式输出，包含"
-  报告名称"、"识别鸟类数"、识别时间"、"点击查看"四列，其中"报告名称"列使用`鸟类识别报告-{记录id}`形式拼接, "点击查看"列使用
-  `[🔗 查看报告](reportImageUrl)`
-  格式的超链接，用户点击即可直接跳转到对应的完整报告页面。
-- 表格输出示例：
-  | 报告名称 | 识别鸟类数 | 识别时间 | 点击查看 |
-  |----------|----------|----------|----------|
-  | 鸟类识别报告 -20260329005000001 | 3种 | 2026-03-29 00:50 | [🔗 查看报告](https://example.com/report?id=xxx) |
-
-## 使用示例
-
-```bash
-# 识别本地鸟类图片（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.bird_recognition_analysis --input /path/to/bird.jpg --open-id openclaw-control-ui
-
-# 识别本地视频（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.bird_recognition_analysis --input /path/to/forest.mp4 --open-id openclaw-control-ui
-
-# 识别网络图片（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.bird_recognition_analysis --url https://example.com/bird.jpg --open-id openclaw-control-ui
-
-# 显示历史识别报告/显示识别报告清单列表/显示历史鸟类识别（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）
-python -m scripts.bird_recognition_analysis --list --open-id openclaw-control-ui
-
-# 输出精简报告
-python -m scripts.bird_recognition_analysis --input bird.jpg --open-id your-open-id --detail basic
-
-# 保存结果到文件
-python -m scripts.bird_recognition_analysis --input bird.jpg --open-id your-open-id --output result.json
-```

skills/18072937735/smyx-bird-recognition-analysis/_meta.json

@@ -1,11 +0,0 @@
-{
-  "owner": "18072937735",
-  "slug": "smyx-bird-recognition-analysis",
-  "displayName": "Bird Recognition Tool | 鸟类识别工具",
-  "latest": {
-    "version": "1.0.0",
-    "publishedAt": 1776146161828,
-    "commit": "https://github.com/openclaw/skills/commit/f5df50a666617bd2ae6fee282bb0e3aab4fcd990"
-  },
-  "history": []
-}

skills/18072937735/smyx-bird-recognition-analysis/references/api_doc.md

@@ -1,21 +0,0 @@
-# API 接口文档
-
-此处用于存放鸟类识别分析 API 的接口文档，待后续补充。
-
-## 接口规范
-
-- 基础地址：由 smyx_common 配置统一管理
-- 认证方式：API Key 鉴权
-- 请求格式：multipart/form-data 支持文件上传
-- 响应格式：JSON
-
-## 主要接口
-
-1. `/web/ai-analysis/v2/start-common-ai-analysis` - 启动AI分析任务
-2. `/web/ai-analysis/v2/get-common-ai-analysis-result` - 获取分析结果
-3. `/web/ai-analysis/page-common-ai-analysis-result` - 分页查询历史报告
-4. `/ai/order/api/getReportDetailExport?id={id}` - 导出完整报告
-
-## 场景代码
-
-- `OPEN_BIRD_RECOGNITION_ANALYSIS` - 开放平台鸟类识别分析

skills/18072937735/smyx-bird-recognition-analysis/scripts/__init__.py

@@ -1 +0,0 @@
-# Pet Analysis scripts package

skills/18072937735/smyx-bird-recognition-analysis/scripts/api_service.py

@@ -1,53 +0,0 @@
-#!/usr/bin/env python3
-
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-from skills.smyx_common.scripts.util import RequestUtil
-
-
-class ApiService(ApiServiceBase):
-
-    def __init__(self):
-        super().__init__()
-        self.analysis_url = ApiEnum.ANALYSIS_URL
-
-    def analysis_result(self, *args, **argss):
-        return self.http_post(ApiEnum.ANALYSIS_RESULT_URL, *args, **argss)
-
-    def analysis(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        options = {
-            "dataAsParams": True
-        }
-        # params.setdefault("scene", scene_code)
-        # 添加宠物类型参数
-        if ConstantEnum.DEFAULT__PET_TYPE:
-            params.setdefault("petType", ConstantEnum.DEFAULT__PET_TYPE)
-        return self.http_post(self.analysis_url, options=options, *args, **argss)
-
-    def page(self, pageNum=None, pageSize=None, *args, **argss):
-        data = argss.setdefault("data", {})
-        data.setdefault("orderBy", {
-            "fieldName": "createTime",
-            "isAsc": False
-        })
-        return super().page(ApiEnum.PAGE_URL, pageNum, pageSize, *args, **argss)
-
-    def list(self, *args, **argss):
-        return super().list(None, *args, **argss)
-
-    def add(self, item: dict):
-        return super().add(ApiEnum.ADD_URL, item)
-
-    def edit(self, item: dict):
-        return super().edit(ApiEnum.EDIT_URL, item)
-
-    def delete(self, cameraSn):
-        data = {
-            "cameraSn": cameraSn
-        }
-        return super().delete(ApiEnum.DELETE_URL, data, options={"dataAsParams": True})

skills/18072937735/smyx-bird-recognition-analysis/scripts/bird_recognition_analysis.py

@@ -1,97 +0,0 @@
-#!/usr/bin/env python3
-import sys
-import os
-
-current_dir = os.path.dirname(os.path.abspath(__file__))
-parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(current_dir)))
-sys.path.insert(0, parent_dir)
-
-import argparse
-import json
-import mimetypes
-import traceback
-from datetime import datetime
-
-import requests
-import sys
-import os
-
-from .config import *
-
-from .skill import skill
-
-from skills.smyx_common.scripts.util import RequestUtil
-
-
-def recognize_bird(input_path=None, url=None, api_url=None, api_key=None, output_level=None):
-    input_path = input_path or url
-    return skill.get_output_analysis(input_path)
-
-
-def show_analyze_list(open_id, start_time=None, end_time=None):
-    output_content = skill.get_output_analysis_list()
-    return output_content
-
-
-def main():
-    parser = argparse.ArgumentParser(description="鸟类识别工具")
-    parser.add_argument("--input", help="本地图片/视频文件路径")
-    parser.add_argument("--url", help="网络图片/视频URL地址")
-    parser.add_argument("--open-id", required=True, help="当前用户的OpenID/UserId/用户名/手机号")
-    parser.add_argument("--list", action='store_true', help="显示鸟类识别分析列表清单")
-    parser.add_argument("--api-url", help="服务端API地址")
-    parser.add_argument("--api-key", help="API访问密钥（必需）")
-    parser.add_argument("--output", help="结果输出文件路径")
-    parser.add_argument("--detail", choices=["basic", "standard", "json"],
-                        default=ConstantEnum.DEFAULT__OUTPUT_LEVEL,
-                        help="输出详细程度")
-    parser.add_argument("--export-env-only", action='store_true',
-                        help="仅输出 export 命令设置环境变量，不执行分析")
-
-    args = parser.parse_args()
-
-    try:
-        if args.open_id:
-            # 设置 Python 进程内的环境变量
-            ConstantEnumBase.CURRENT__OPEN_ID = args.open_id
-
-        # 检查必需参数
-        if args.list:
-            open_id = ConstantEnum.CURRENT__OPEN_ID
-            result = show_analyze_list(open_id)
-            print(result)
-            exit(0)
-
-        # 检查必需参数
-        if not args.input and not args.url:
-            print("❌ 错误: 必须提供 --input 或 --url 参数")
-            exit(1)
-
-        print("🔍 正在识别鸟类，请稍候...")
-        output_content = recognize_bird(
-            input_path=args.input,
-            url=args.url,
-            api_url=args.api_url,
-            api_key=args.api_key,
-            output_level=args.detail
-        )
-
-        print(output_content)
-
-        # 保存到文件
-        if args.output:
-            with open(args.output, "w", encoding="utf-8") as f:
-                if args.detail == "full":
-                    json.dump(result, f, ensure_ascii=False, indent=2)
-                else:
-                    f.write(output_content)
-            print(f"✅ 结果已保存到: {args.output}")
-
-    except Exception as e:
-        traceback.print_stack()
-        print(f"❌ 鸟类识别分析失败: {str(e)}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()

skills/18072937735/smyx-bird-recognition-analysis/scripts/config.py

@@ -1,24 +0,0 @@
-#!/usr/bin/env python3
-# 鸟类识别工具配置文件
-import os
-import sys
-
-from enum import Enum
-
-from skills.smyx_common.scripts.config import ConstantEnum as ConstantEnumBase
-
-from skills.face_analysis.scripts.config import ApiEnum as ApiEnumParent, ConstantEnum as ConstantEnumParent, \
-    ApiEnumCommonAiMixin
-
-SceneCodeEnum = ConstantEnumBase.SceneCodeEnum
-
-
-class ApiEnum(ApiEnumCommonAiMixin, ApiEnumParent):
-    pass
-
-
-class ConstantEnum(ConstantEnumParent):
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-        ConstantEnumParent.DEFAULT__SCENE_CODE = SceneCodeEnum.BIRD_RECOGNITION_ANALYSIS.value

skills/18072937735/smyx-bird-recognition-analysis/scripts/config.yaml

@@ -1 +0,0 @@
-{}

skills/18072937735/smyx-bird-recognition-analysis/scripts/skill.py

@@ -1,23 +0,0 @@
-#!/usr/bin/env python3
-import json
-
-from .config import ApiEnum, ConstantEnum
-
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-from skills.face_analysis.scripts.skill import Skill as SkillParent
-from skills.smyx_common.scripts.util import JsonUtil
-
-
-class Skill(SkillParent):
-    def __init__(self):
-        super().__init__()
-
-    def get_output_analysis_content_head(self, result=None):
-        return f"📊 鸟类识别分析结构化结果"
-
-    def get_output_analysis_content_foot(self, result):
-        pass
-
-
-skill = Skill()

skills/18072937735/smyx-bird-recognition-analysis/skills/face_analysis/README.md

@@ -1,86 +0,0 @@
-# 中医面诊分析工具 (face-analysis)
-
-## 技能介绍
-这是一个基于AI的中医面诊分析技能，可以通过面部视频自动分析健康状况，返回结构化的诊断结果和养生建议。
-
-## 快速开始
-### 1. 配置API信息
-编辑 `scripts/config.py`，设置你的API地址和密钥：
-```python
-DEFAULT_API_URL = "https://your-api-server.com/api/v1/face-analysis"
-DEFAULT_API_KEY = "your-api-key-here"
-```
-
-### 2. 分析本地视频
-```bash
-python scripts/face_analysis.py --input /path/to/your/video.mp4
-```
-
-### 3. 分析网络视频
-```bash
-python scripts/face_analysis.py --url https://example.com/video.mp4
-```
-
-## 功能特性
-- ✅ 支持本地MP4视频上传
-- ✅ 支持网络视频URL分析
-- ✅ 三种输出详细程度：精简/标准/完整
-- ✅ 结构化JSON结果输出
-- ✅ 自动保存结果到文件
-- ✅ 内置视频格式和大小校验
-
-## 目录结构
-```
-face-analysis/
-├── SKILL.md              # 技能说明文件（系统自动加载）
-├── README.md             # 本说明文件
-├── scripts/
-│   ├── face_analysis.py  # 主程序
-│   └── config.py         # 配置文件
-├── references/
-│   ├── api_doc.md        # API接口文档
-│   ├── tcm_theory.md     # 中医面诊理论参考
-│   └── faq.md            # 常见问题
-└── assets/
-    └── template.json     # 返回结果模板
-```
-
-## 使用示例
-### 标准输出
-```
-📊 中医面诊分析报告
-==================================================
-⏰ 分析时间: 2026-03-10 15:30:00
-🎯 人脸检测: success (置信度: 95分)
-
-🔍 诊断结果:
-  整体体质: 平和质
-  脏腑状况:
-    liver: 正常
-    heart: 轻微火旺
-    spleen: 略虚
-    lung: 正常
-    kidney: 正常
-  面色分析: 微黄
-  对应提示: 脾胃功能略弱
-
-⚠️ 健康警示:
-  ⚠️  注意休息，避免熬夜
-
-💡 养生建议:
-  💡 饮食清淡，减少辛辣食物摄入
-  💡 保持规律作息，每晚11点前入睡
-  💡 适当进行有氧运动，如散步、太极拳
-==================================================
-```
-
-### 输出到JSON文件
-```bash
-python scripts/face_analysis.py --input video.mp4 --detail full --output result.json
-```
-
-## 注意事项
-1. 视频要求：清晰正面面部，光线充足，时长5-30秒为宜
-2. 支持格式：mp4、avi、mov，最大100MB
-3. API需要自行部署或接入第三方服务
-4. 结果仅供参考，不能替代专业医生诊断

skills/18072937735/smyx-bird-recognition-analysis/skills/face_analysis/references/api_doc.md

@@ -1,69 +0,0 @@
-# API接口文档
-
-## 接口地址
-`POST https://your-api-server.com/api/v1/face-analysis`
-
-## 请求头
-| 字段 | 必选 | 说明 |
-|------|------|------|
-| X-API-Key | 是 | API访问密钥 |
-| Content-Type | 是 | multipart/form-data（文件上传）或 application/json（URL模式） |
-
-## 请求参数
-### 1. 文件上传模式
-| 字段 | 类型 | 必选 | 说明 |
-|------|------|------|------|
-| video | file | 是 | MP4视频文件 |
-| detail_level | string | 否 | 输出详细程度：basic/standard/full，默认standard |
-
-### 2. URL模式
-| 字段 | 类型 | 必选 | 说明 |
-|------|------|------|------|
-| video_url | string | 是 | 可公开访问的视频URL |
-| detail_level | string | 否 | 输出详细程度：basic/standard/full，默认standard |
-
-## 响应格式
-```json
-{
-  "code": 200,
-  "message": "success",
-  "data": {
-    "analysis_time": "2026-03-10 15:30:00",
-    "face_detection": {
-      "status": "success",
-      "face_count": 1,
-      "quality_score": 95
-    },
-    "diagnosis": {
-      "overall_constitution": "平和质",
-      "organ_condition": {
-        "liver": "正常",
-        "heart": "轻微火旺",
-        "spleen": "略虚",
-        "lung": "正常",
-        "kidney": "正常"
-      },
-      "color_analysis": {
-        "complexion": "微黄",
-        "correspondence": "脾胃功能略弱"
-      }
-    },
-    "health_warnings": [
-      "注意休息，避免熬夜"
-    ],
-    "suggestions": [
-      "饮食清淡，减少辛辣食物摄入"
-    ]
-  }
-}
-```
-
-## 错误码说明
-| 错误码 | 说明 |
-|--------|------|
-| 400 | 请求参数错误 |
-| 401 | API密钥无效 |
-| 403 | 权限不足 |
-| 413 | 文件过大 |
-| 415 | 不支持的文件格式 |
-| 500 | 服务器内部错误 |

skills/18072937735/smyx-bird-recognition-analysis/skills/face_analysis/requirements.txt

@@ -1,3 +0,0 @@
-pydash==8.0.6
-SQLAlchemy==2.0.46
-yaml==6.0.3

skills/18072937735/smyx-bird-recognition-analysis/skills/face_analysis/scripts/api_service.py

@@ -1,52 +0,0 @@
-#!/usr/bin/env python3
-
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-
-class ApiService(ApiServiceBase):
-
-    def __init__(self):
-        super().__init__()
-        self.analysis_url = ApiEnum.ANALYSIS_URL
-
-    def analysis_result(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        scene_code and params.setdefault("sceneCode", scene_code)
-        return self.http_post(ApiEnum.ANALYSIS_RESULT_URL, *args, **argss)
-
-    def analysis(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        options = {
-            "dataAsParams": True
-        }
-        scene_code and params.setdefault("sceneCode", scene_code)
-        params.setdefault("appCategory", ConstantEnum.DEFAULT__APP_CATEGORY)
-        return self.http_post(self.analysis_url, options=options, *args, **argss)
-
-    def page(self, pageNum=None, pageSize=None, *args, **argss):
-        data = argss.setdefault("data", {})
-        ConstantEnum.DEFAULT__SCENE_CODE and data.setdefault("sceneCode", ConstantEnum.DEFAULT__SCENE_CODE)
-        data.setdefault("orderBy", {
-            "fieldName": "createTime",
-            "isAsc": False
-        })
-        return super().page(ApiEnum.PAGE_URL, pageNum, pageSize, *args, **argss)
-
-    def list(self, *args, **argss):
-        return super().list(None, *args, **argss)
-
-    def add(self, item: dict):
-        return super().add(ApiEnum.ADD_URL, item)
-
-    def edit(self, item: dict):
-        return super().edit(ApiEnum.EDIT_URL, item)
-
-    def delete(self, cameraSn):
-        data = {
-            "cameraSn": cameraSn
-        }
-        return super().delete(ApiEnum.DELETE_URL, data, options={"dataAsParams": True})

skills/18072937735/smyx-bird-recognition-analysis/skills/face_analysis/scripts/config.py

@@ -1,40 +0,0 @@
-#!/usr/bin/env python3
-# 中医面诊分析工具配置文件
-import os
-import sys
-
-from enum import Enum
-
-from skills.smyx_common.scripts.config import ApiEnum as ApiEnumBase, ConstantEnum as ConstantEnumBase
-
-SceneCodeEnum = ConstantEnumBase.SceneCodeEnum
-
-
-class ApiEnum(ApiEnumBase):
-    ANALYSIS_URL = "/web/health-analysis/v2/start-health-analysis"
-
-    ANALYSIS_RESULT_URL = "/web/health-analysis/get-health-analysis-result"
-
-    PAGE_URL = "/web/health-analysis/page-health-analysis-result"
-
-    DETAIL_EXPORT_URL = ApiEnumBase.BASE_URL_HEALTH + "/health/order/api/getReportDetailExport?id="
-
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-
-
-class ApiEnumCommonAiMixin:
-
-    @classmethod
-    def init(cls, config=None):
-        parent = super()
-        if hasattr(parent, "init"):
-            parent.init(config)
-        ApiEnum.ANALYSIS_URL = "/web/ai-analysis/v2/start-common-ai-analysis"
-        ApiEnum.ANALYSIS_RESULT_URL = "/web/ai-analysis/get-common-ai-analysis-result"
-        ApiEnum.PAGE_URL = "/web/ai-analysis/page-common-ai-analysis-result"
-
-
-class ConstantEnum(ConstantEnumBase):
-    DEFAULT__APP_CATEGORY = "PEI_NI_AN"

skills/18072937735/smyx-bird-recognition-analysis/skills/face_analysis/scripts/config.yaml

@@ -1 +0,0 @@
-{}

skills/18072937735/smyx-bird-recognition-analysis/skills/face_analysis/scripts/face_analysis.py

@@ -1,205 +0,0 @@
-#!/usr/bin/env python3
-import sys
-import os
-
-current_dir = os.path.dirname(os.path.abspath(__file__))
-parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(current_dir)))
-sys.path.insert(0, parent_dir)
-
-import argparse
-import json
-import mimetypes
-import traceback
-from datetime import datetime
-
-import requests
-import sys
-import os
-
-from .config import *
-
-from .skill import skill
-
-# import_path_common()
-from skills.smyx_common.scripts.util import RequestUtil
-
-# 从config导入常量
-SUPPORTED_FORMATS = ConstantEnum.SUPPORTED_FORMATS
-MAX_FILE_SIZE_MB = ConstantEnum.MAX_FILE_SIZE_MB
-
-
-def validate_file(file_path):
-    """验证输入文件是否合法"""
-    if not os.path.exists(file_path):
-        raise FileNotFoundError(f"文件不存在: {file_path}")
-
-    if not os.access(file_path, os.R_OK):
-        raise PermissionError(f"文件没有读权限: {file_path}")
-
-    ext = os.path.splitext(file_path)[1].lower()[1:]
-    if ext not in SUPPORTED_FORMATS:
-        raise ValueError(f"不支持的文件格式，支持的格式: {', '.join(SUPPORTED_FORMATS)}")
-
-    file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
-    if file_size_mb > MAX_FILE_SIZE_MB:
-        raise ValueError(f"文件过大，最大支持 {MAX_FILE_SIZE_MB}MB，当前文件大小: {file_size_mb:.1f}MB")
-
-    return True
-
-
-def analyze_video(input_path=None, url=None, api_url=None, api_key=None, output_level=None):
-    """调用API分析视频"""
-    if not input_path and not url:
-        raise ValueError("必须提供本地视频路径(--input)或网络视频URL(--url)")
-    try:
-        input_path = input_path or url
-        return skill.get_output_analysis(input_path)
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def show_analyze_list(open_id, start_time=None, end_time=None):
-    # if not open_id:
-    #     raise ValueError("必须提供本用户的OpenId/UserId")
-
-    try:
-        output_content = skill.get_output_analysis_list()
-        return output_content
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def get_analysis_export_url(request_id=None):
-    """调用API分析视频"""
-    if not request_id:
-        return ""
-    return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-
-def format_result(result, output_level="standard"):
-    """格式化输出结果"""
-    if output_level == "json":
-        result_id = None
-        # if result.get('success'):
-        if result is not None:
-            result_json = result
-            result_id = result_json.get('id', {})
-            result_json = json.dumps(result_json.get('faceAnalysisResponse', {}), ensure_ascii=False, indent=2)
-        else:
-            # result_json = json.dumps(result, ensure_ascii=False, indent=2)
-            return "⚠️ 暂无分析结果"
-        return f"""
-📊 面诊分析结构化结果
-{result_json}
-""", result_id
-    elif output_level == "basic":
-        # 精简输出
-        data = result.get('data', {})
-        diagnosis = data.get('diagnosis', {})
-        return f"""
-📊 面诊分析结果
-{'=' * 40}
-整体体质: {diagnosis.get('overall_constitution', '未知')}
-主要状况: {', '.join([f'{k}: {v}' for k, v in diagnosis.get('organ_condition', {}).items() if v != '正常'])}
-健康提示: {data.get('health_warnings', ['无特殊警示'])[0] if data.get('health_warnings') else '无特殊警示'}
-        """
-    elif output_level == "standard":
-        # 标准输出
-        data = result.get('data', {})
-        diagnosis = data.get('diagnosis', {})
-        face_detection = data.get('face_detection', {})
-
-        organ_status = "\n".join([f"  {k}: {v}" for k, v in diagnosis.get('organ_condition', {}).items()])
-        warnings = "\n".join([f"  ⚠️  {item}" for item in data.get('health_warnings', [])])
-        suggestions = "\n".join([f"  💡 {item}" for item in data.get('suggestions', [])])
-
-        return f"""
-📊 中医面诊分析报告
-{'=' * 50}
-⏰ 分析时间: {data.get('analysis_time', '未知')}
-🎯 人脸检测: {face_detection.get('status', '未知')} (置信度: {face_detection.get('quality_score', 0)}分)
-
-🔍 诊断结果:
-  整体体质: {diagnosis.get('overall_constitution', '未知')}
-  脏腑状况:
-{organ_status}
-  面色分析: {diagnosis.get('color_analysis', {}).get('complexion', '未知')}
-  对应提示: {diagnosis.get('color_analysis', {}).get('correspondence', '未知')}
-
-⚠️ 健康警示:
-{warnings}
-
-💡 养生建议:
-{suggestions}
-{'=' * 50}
-        """
-    else:
-        # 完整输出（JSON格式）
-        return json.dumps(result, ensure_ascii=False, indent=2)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="中医面诊分析工具")
-    parser.add_argument("--input", help="本地MP4视频文件路径")
-    parser.add_argument("--url", help="网络视频MP4的URL地址")
-    parser.add_argument("--open-id", required=True, help="当前用户的OpenID/UserId/用户名/手机号")
-    parser.add_argument("--list", action='store_true', help="显示面诊视频历史列表清单")
-    parser.add_argument("--api-url", help="服务端API地址")
-    parser.add_argument("--api-key", help="API访问密钥（必需）")
-    parser.add_argument("--output", help="结果输出文件路径")
-    parser.add_argument("--detail", choices=["basic", "standard", "json"],
-                        default=ConstantEnum.DEFAULT__OUTPUT_LEVEL,
-                        help="输出详细程度")
-    parser.add_argument("--export-env-only", action='store_true',
-                        help="仅输出 export 命令设置环境变量，不执行分析")
-
-    args = parser.parse_args()
-
-    try:
-        if args.open_id:
-            ConstantEnumBase.CURRENT__OPEN_ID = args.open_id
-
-        # 检查必需参数
-        if args.list:
-            open_id = ConstantEnum.CURRENT__OPEN_ID
-            result = show_analyze_list(open_id)
-            print(result)
-            exit(0)
-
-        # 检查必需参数
-        if not args.input and not args.url:
-            print("❌ 错误: 必须提供 --input 或 --url 参数")
-            exit(1)
-
-        print("🔍 正在分析面诊视频，请稍候...")
-        output_content = analyze_video(
-            input_path=args.input,
-            url=args.url,
-            api_url=args.api_url,
-            api_key=args.api_key,
-            output_level=args.detail
-        )
-
-        print(output_content)
-
-        # 保存到文件
-        if args.output:
-            with open(args.output, "w", encoding="utf-8") as f:
-                if args.detail == "full":
-                    json.dump(result, f, ensure_ascii=False, indent=2)
-                else:
-                    f.write(output_content)
-            print(f"✅ 结果已保存到: {args.output}")
-
-    except Exception as e:
-        traceback.print_stack()
-        print(f"❌ 面诊分析失败: {str(e)}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()

skills/18072937735/smyx-bird-recognition-analysis/skills/face_analysis/scripts/skill.py

@@ -1,267 +0,0 @@
-#!/usr/bin/env python3
-import datetime
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-
-from .api_service import ApiService
-
-from skills.smyx_common.scripts.util import CommonUtil, JsonUtil
-from skills.smyx_common.scripts.config import ApiEnum as ApiEnumBase
-from skills.smyx_common.scripts.base import BaseSkill
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-
-class Skill(BaseSkill, ApiService):
-    def __init__(self):
-        super().__init__()
-
-    def get_output_analysis_content_body(self, result=None):
-        result_json = result
-
-        result_json_pure_text = result_json.get("pureText")
-        if result_json_pure_text:
-            result_json = JsonUtil.parse(result_json_pure_text, result_json_pure_text)
-
-        result_json_common_ai_response = result_json.get("commonAiResponse")
-        if result_json_common_ai_response:
-            result_json = result_json_common_ai_response
-
-        result_json_health_ai_response = result_json.get("healthAiResponse")
-        if result_json_health_ai_response:
-            result_json = result_json_health_ai_response
-
-        result_json = JsonUtil.stringify(result_json, result_json)
-        return result_json
-
-    def get_output_analysis_content_head(self, result=None):
-        return f"📊 面诊分析结构化结果"
-
-    def get_output_analysis_content_foot(self, result):
-        result_id = result.get('id', {})
-        output_content_export_url = ApiEnum.DETAIL_EXPORT_URL + result_id
-        return f"🔗 获取报告导出图片链接: {output_content_export_url}"
-
-    def get_output_analysis_content(self, result):
-        if result is not None:
-            output_content = self.get_output_analysis_content_body(result) or ""
-            output_content_head = self.get_output_analysis_content_head(result)
-            output_content_foot = self.get_output_analysis_content_foot(result)
-            #       d
-            if output_content_head:
-                output_content = f"""
-{output_content_head}
-""" + output_content
-            if output_content_foot:
-                output_content += f"""
-{output_content_foot}
-"""
-        else:
-            output_content = "⚠️ 暂无分析结果"
-        return output_content
-
-    def get_output_analysis(self, input_path, params={}):
-        response = self.get_analysis(
-            input_path, params
-        )
-
-        def _analysis_result():
-            return self.analysis_result(
-                data=response
-            )
-
-        new_response = CommonUtil.polling(_analysis_result,
-                                          check_condition=lambda res: res.get('needPageRefresh') is False, interval=5,
-                                          max_attempts=24)
-
-        output_content = self.get_output_analysis_content(new_response)
-        return output_content
-
-    def get_analysis(self, input_path, params={}):
-        import mimetypes
-
-        def _validate_file(file_path):
-            """验证输入文件是否合法"""
-            if not os.path.exists(file_path):
-                raise FileNotFoundError(f"文件不存在: {file_path}")
-
-            if not os.access(file_path, os.R_OK):
-                raise PermissionError(f"文件没有读权限: {file_path}")
-
-            ext = os.path.splitext(file_path)[1].lower()[1:]
-            if ext not in ConstantEnum.SUPPORTED_FORMATS:
-                raise ValueError(f"不支持的文件格式，支持的格式: {', '.join(ConstantEnum.SUPPORTED_FORMATS)}")
-
-            file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
-            if file_size_mb > ConstantEnum.MAX_FILE_SIZE_MB:
-                raise ValueError(
-                    f"文件过大，最大支持 {ConstantEnum.MAX_FILE_SIZE_MB}MB，当前文件大小: {file_size_mb:.1f}MB")
-
-            return True
-
-        files = None
-
-        if not input_path:
-            raise ValueError("必须提供本地视频路径(--input)或网络视频URL(--url)")
-
-        if (input_path.startswith("http://") or input_path.startswith("https://")):
-            params.update({
-                "videoUrl": input_path
-            })
-        else:
-            _validate_file(input_path)
-
-            # 自动检测 MIME 类型
-            mime_type, _ = mimetypes.guess_type(input_path)
-            if mime_type is None:
-                mime_type = 'application/octet-stream'
-
-            # 读取文件内容
-            with open(input_path, 'rb') as f:
-                file_content = f.read()
-
-            # 构建 multipart/form-data 格式的请求
-            files = {
-                'file': (os.path.basename(input_path), file_content, mime_type)
-            }
-
-        response = self.analysis(
-            params=params,
-            files=files
-        )
-
-        return response
-
-    def get_output_analysis_list(self, pageNum=None, pageSize=None, *args, **argss):
-        """获取面诊报告清单
-        优化规则：只要API服务接口返回面诊报告清单，直接输出API返回的结果，
-        无需汇总上下文中的面诊分析报告，以接口返回为准
-        """
-
-        def _get_analysis_export_url(request_id=None):
-            if not request_id:
-                return ""
-            return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-        response = self.page(pageNum, pageSize, *args, **argss)
-
-        if response:
-            for item in response:
-                if item.get("commonAiResponse") or item.get("healthAiResponse"):
-                    item["reportImageUrl"] = _get_analysis_export_url(item.get("id"))
-
-        response_text = JsonUtil.stringify(response)
-
-        if response_text:
-            return f"""📊 分析报告记录列表(结构化结果)"
-{response_text}
-"""
-        else:
-            return "⚠️ 暂无分析报告记录"
-
-    def __get_output_analysis_list(self, pageNum=None, pageSize=None, *args, **argss):
-        """获取面诊报告清单
-        优化规则：只要API服务接口返回面诊报告清单，直接输出API返回的结果，
-        无需汇总上下文中的面诊分析报告，以接口返回为准
-        """
-
-        def _get_analysis_export_url(request_id=None):
-            if not request_id:
-                return ""
-            return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-        # open_id 仅用于本地识别，不传给API - 参数已经在argss中，page方法会正确处理
-        open_id = argss.pop('open_id', None)
-        # if not open_id:
-        #     return "⚠️ 错误：缺少 open_id 参数"
-
-        # 获取总页数，然后循环获取所有页
-        output_all = ""
-        # 先获取第一页来获取总页数
-        # page 方法在基类中已经处理过，我们需要兼容两种返回结果：
-        # 1. 完整响应：{"success": true, "data": {"records": [...], "total": ...}}
-        # 2. 已经提取好的数据：直接返回 data 对象或 records 列表
-        response = self.page(pageNum or 1, pageSize or 30, *args, **argss)
-
-        if response is None:
-            return "⚠️ 获取报告列表失败：response is None"
-
-        # 兼容处理：不同版本的基类返回不同格式
-        if isinstance(response, list):
-            # 基类直接返回了 records 列表，无法获取分页信息，直接使用
-            records = response
-            total = len(records)
-            pages = 1
-        elif isinstance(response, dict):
-            # 完整响应格式
-            if not response.get('success'):
-                error_msg = response.get('errorMsg', '未知错误')
-                return f"⚠️ 获取报告列表失败：{error_msg}"
-            data = response.get('data', {})
-            if not data or not isinstance(data, dict):
-                return "⚠️ 获取报告列表失败：数据格式错误"
-            total = data.get('total', 0)
-            pages = data.get('pages', 1)
-            records = data.get('records', [])
-        else:
-            return f"⚠️ 获取报告列表失败：response type={type(response)}"
-
-        if not records:
-            return "⚠️ 暂无面诊分析报告记录"
-
-        output_all = f"📋 历史面诊分析报告清单（共 {total} 份）\n\n"
-        output_all += "| 报告名称 | 分析时间 | 体质判断 | 点击查看 |\n"
-        output_all += "|----------|----------|----------|----------|\n"
-
-        # 处理第一页
-        for item in records:
-            if not isinstance(item, dict):
-                continue
-            report_id = item.get('id', '')
-            create_time = item.get('createTimeString', '未知时间')
-            # 提取体质判断 - 优先从 healthAiResponse 获取，如果没有再从 faceAnalysisResponse 获取
-            health_ai = item.get('healthAiResponse', {}) or {}
-            if health_ai:
-                health_assessment = health_ai.get('healthAssessment', {}) or {}
-                subject = health_assessment.get('subject', '未知')
-            else:
-                face_ai = item.get('faceAnalysisResponse', {}) or {}
-                health_assessment = face_ai.get('healthAssessment', {}) or {}
-                subject = health_assessment.get('subject', '未知')
-            report_name = f"面诊分析报告-{report_id}"
-            report_url = _get_analysis_export_url(report_id)
-            output_all += f"| {report_name} | {create_time} | {subject} | [🔗 查看报告]({report_url}) |\n"
-
-        # 处理剩余页
-        for current_page in range(2, pages + 1):
-            response = self.page(current_page, 30, *args, **argss)
-            if not response or not isinstance(response, dict) or not response.get('success'):
-                continue
-            data = response.get('data', {})
-            if not data or not isinstance(data, dict):
-                continue
-            records = data.get('records', [])
-            for item in records:
-                if not isinstance(item, dict):
-                    continue
-                report_id = item.get('id', '')
-                create_time = item.get('createTimeString', '未知时间')
-                # 提取体质判断 - 优先从 healthAiResponse 获取，如果没有再从 faceAnalysisResponse 获取
-                health_ai = item.get('healthAiResponse', {}) or {}
-                if health_ai:
-                    health_assessment = health_ai.get('healthAssessment', {}) or {}
-                    subject = health_assessment.get('subject', '未知')
-                else:
-                    face_ai = item.get('faceAnalysisResponse', {}) or {}
-                    health_assessment = face_ai.get('healthAssessment', {}) or {}
-                    subject = health_assessment.get('subject', '未知')
-                report_name = f"面诊分析报告-{report_id}"
-                report_url = _get_analysis_export_url(report_id)
-                output_all += f"| {report_name} | {create_time} | {subject} | [🔗 查看报告]({report_url}) |\n"
-
-        output_all += "\n> 注：面诊分析结果仅供健康参考，不能替代专业医疗诊断。"
-        return output_all
-
-
-skill = Skill()

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/requirements.txt

@@ -1,127 +0,0 @@
-altgraph==0.17.5
-annotated-doc==0.0.4
-annotated-types==0.7.0
-anyio==4.12.1
-APScheduler==3.11.2
-astroid==3.1.0
-Authlib==1.6.6
-blinker==1.4
-cachetools==6.2.6
-certifi==2026.1.4
-cffi==2.0.0
-chardet==5.2.0
-charset-normalizer==3.4.4
-click==8.3.1
-coverage==7.13.2
-coze-workload-identity==0.1.7
-cozeloop==0.1.19
-cryptography==3.4.8
-Cython==3.2.4
-dbus-python==1.2.18
-dill==0.4.1
-distro==1.7.0
-distro-info==1.1+ubuntu0.2
-et_xmlfile==2.0.0
-fastapi==0.121.2
-gitdb==4.0.12
-gitignore_parser==0.1.13
-GitPython==3.1.45
-greenlet==3.3.1
-h11==0.16.0
-httpcore==1.0.9
-httplib2==0.20.2
-httpx==0.28.1
-httpx-ws==0.8.2
-idna==3.11
-importlib-metadata==4.6.4
-inflect==7.5.0
-iniconfig==2.3.0
-isort==5.13.2
-jeepney==0.7.1
-Jinja2==3.1.6
-jiter==0.12.0
-jsonpatch==1.33
-jsonpointer==3.0.0
-keyring==23.5.0
-langchain==1.0.3
-langchain-core==1.0.2
-langchain-openai==1.0.1
-langgraph==1.0.2
-langgraph-checkpoint==3.0.0
-langgraph-prebuilt==1.0.2
-langgraph-sdk==0.2.9
-langsmith==0.4.39
-launchpadlib==1.10.16
-lazr.restfulclient==0.14.4
-lazr.uri==1.0.6
-markdown-it-py==4.0.0
-MarkupSafe==3.0.3
-mccabe==0.7.0
-mdurl==0.1.2
-more-itertools==8.10.0
-numpy==2.4.1
-oauthlib==3.2.0
-openai==2.16.0
-openpyxl==3.1.5
-orjson==3.11.5
-ormsgpack==1.12.2
-packaging==25.0
-pandas==2.3.3
-platformdirs==4.5.1
-pluggy==1.6.0
-psutil==7.1.3
-psycopg2-binary==2.9.11
-pycparser==3.0
-pydantic==2.12.4
-pydantic_core==2.41.5
-pydash==8.0.6
-Pygments==2.19.2
-PyGObject==3.42.1
-pyinstaller==6.18.0
-pyinstaller-hooks-contrib==2026.0
-PyJWT==2.10.1
-pylint==3.1.0
-PyMySQL==1.1.2
-pyparsing==2.4.7
-pytest==9.0.1
-pytest-asyncio==1.3.0
-pytest-cov==7.0.0
-pytest-mock==3.15.1
-python-apt==2.4.0+ubuntu4.1
-python-dateutil==2.9.0.post0
-pytz==2025.2
-PyYAML==6.0.3
-regex==2026.1.15
-requests==2.32.5
-requests-toolbelt==1.0.0
-rich==14.2.0
-SecretStorage==3.3.1
-setuptools==80.9.0
-six==1.16.0
-smmap==5.0.2
-sniffio==1.3.1
-sqlacodegen==3.2.0
-SQLAlchemy==2.0.46
-starlette==0.49.3
-supervisor==4.2.1
-tenacity==9.1.2
-tiktoken==0.12.0
-tomlkit==0.14.0
-tqdm==4.67.1
-typeguard==4.4.4
-typing-inspection==0.4.2
-typing_extensions==4.15.0
-tzdata==2025.3
-tzlocal==5.3.1
-unattended-upgrades==0.1
-urllib3==2.6.3
-uvicorn==0.38.0
-wadllib==1.3.6
-watchdog==6.0.0
-websockets==15.0.1
-wheel==0.45.1
-wsproto==1.3.2
-xlrd==2.0.2
-xxhash==3.6.0
-zipp==1.0.0
-zstandard==0.25.0

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/__init__.py

@@ -1,8 +0,0 @@
-from .util import RequestUtil, CommonUtil, DatetimeUtil
-from .base import *
-
-__all__ = [
-    'RequestUtil',
-    'CommonUtil',
-    'BaseUtil'
-]

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/api_service.py

@@ -1,96 +0,0 @@
-#!/usr/bin/env python3
-
-from .config import ApiEnum
-
-from .base import BaseApiService
-from .util import RequestUtil, CommonUtil
-
-
-class ApiService(BaseApiService):
-
-    def __init__(self):
-        super().__init__()
-
-    def get_download_url(self, tosKey, expireSeconds=3600):
-        return RequestUtil.http_post(
-            ApiEnum.GET_DOWNLOAD_URL__URL,
-            params={
-                "tosKey": tosKey,
-                "expireSeconds": expireSeconds * 24
-            }
-        )
-
-    def page(self, url, pageNum=None, pageSize=None, *args, **argss):
-        data = args[0] if len(args) > 0 else argss.get('data') if argss.get('data') is not None else {}
-        if pageNum is None:
-            pageNum = 1
-        if pageSize is None:
-            pageSize = ApiEnum.DEFAULT__PAGE_SIZE
-        paramsPage = {
-            'pageNum': int(pageNum),
-            'pageSize': int(pageSize)
-        }
-        data.update({
-            "page": paramsPage
-        })
-        if not CommonUtil.is_empty(data):
-            if (len(args) == 0):
-                argss.setdefault("data", data)
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def list(self, url=None, *args, **argss):
-        if url is not None:
-            argss["url"] = url
-        return self.page(1, ApiEnum.DEFAULT__PAGE_SIZE_MAX, *args, **argss)
-
-    def add(self, url=None, *args, **argss):
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def edit(self, url=None, *args, **argss):
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def delete(self, url=None, *args, **argss):
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def http_post(self, url=None, *args, **argss):
-        return RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-
-    def http_put(self, url=None, *args, **argss):
-        return RequestUtil.http_put(
-            url,
-            *args, **argss
-        )
-
-    def http_get(self, url=None, *args, **argss):
-        return RequestUtil.http_get(
-            url,
-            *args, **argss
-        )
-
-        return response
-
-    def http_delete(self, url=None, *args, **argss):
-        return RequestUtil.http_delete(
-            url,
-            *args, **argss
-        )
-        return response

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/base.py

@@ -1,33 +0,0 @@
-class BaseUtil:
-    pass
-
-
-class BaseMixin:
-    pass
-
-
-class BaseDao:
-    pass
-
-
-class BaseService:
-    def __init__(self):
-        super().__init__()
-
-
-class BaseApiService(BaseService):
-    INSTANCE = None
-
-    def __init__(self):
-        super().__init__()
-
-    @classmethod
-    def get_instance(cls):
-        if cls.INSTANCE is None:
-            cls.INSTANCE = cls()
-        return cls.INSTANCE
-
-
-class BaseSkill:
-    def __init__(self):
-        super().__init__()

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/config-dev.yaml

@@ -1,7 +0,0 @@
-ApiEnum:
-  base-url-open-api: "http://192.168.1.234:9601/smyx-open-api"
-  base-url-open-h5: "http://192.168.1.234:4100"
-  base-url-health: "http://192.168.1.234:8080/jeecg-boot"
-
-ConstantEnum:
-  is-debug: true

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/config-test.yaml

@@ -1,7 +0,0 @@
-ApiEnum:
-  base-url-open-api: "https://livemonitortest.lifeemergence.com/smyx-open-api"
-  base-url-open-h5: "http://livemonitortest.lifeemergence.com"
-  base-url-health: "https://healthtest.lifeemergence.com/jeecg-boot"
-
-ConstantEnum:
-  is-debug: true

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/config.py

@@ -1,235 +0,0 @@
-#!/usr/bin/env python3
-import os
-import sys
-from enum import Enum
-from typing import Dict
-import inspect
-
-import yaml
-import platform
-
-
-class YamlUtil:
-
-    @staticmethod
-    def load(path, config: Dict = {}) -> Dict:
-        try:
-            if not os.path.exists(path):
-                os.makedirs(os.path.dirname(path), exist_ok=True)
-                with open(path, "w", encoding="utf-8") as f:
-                    yaml.dump(config, f, default_flow_style=False, allow_unicode=True)
-                return config
-            with open(path, "r", encoding="utf-8") as f:
-                config = yaml.safe_load(f) or {}
-                for key, value in config.items():
-                    if key not in config:
-                        config[key] = value
-                return config
-        except:
-            pass
-        return config
-
-    @staticmethod
-    def save(path, config: Dict) -> Dict:
-        try:
-            with open(path, "w", encoding="utf-8") as f:
-                yaml.dump(config, f, default_flow_style=False, allow_unicode=True)
-        except:
-            pass
-        return config
-
-
-class BaseEnum:
-
-    def __init_subclass__(cls, **kwargs):
-        super().__init_subclass__(**kwargs)
-        clsModule = cls.__module__
-        cls_path = inspect.getfile(cls)
-        clsFullName = f"{cls.__module__}.{cls.__name__}"
-        cls_dirpath = os.path.dirname(cls_path)  # .../src
-        clsModulePath = clsModule.replace(".", "\\")
-        current_dir = os.path.dirname(os.path.abspath(__file__))  # .../src
-        config_path = os.path.join(cls_dirpath, "config.yaml")
-        config = YamlUtil.load(config_path)
-        cls.init(config)
-        env = config.get("env")
-        if env:
-            env_config_path = os.path.join(cls_dirpath, f"config-{env}.yaml")
-            env_config = YamlUtil.load(env_config_path)
-            cls.init(env_config)
-
-    @classmethod
-    def init(cls, config=None):
-        clsName = cls.__name__
-        clsConfig = config and config.get(clsName)
-        if clsConfig:
-            for config_key, config_value in clsConfig.items():
-                new_config_key = config_key = config_key.upper().replace("-", "_")
-                if hasattr(cls, new_config_key):
-                    setattr(cls, new_config_key, config_value)
-
-
-class ApiEnum(BaseEnum):
-    API_KEY = None
-
-    API_SECRET_KEY = None
-
-    DATABASE_URL = ""
-
-    BASE_URL_OPEN_API = ""
-
-    BASE_URL_OPEN_H5 = ""
-
-    BASE_URL_HEALTH = ""
-
-    OPEN_TOKEN = ""
-
-    TOKEN = ""
-
-    DEFAULT__REQUEST_TIMEOUT = 120
-
-    DEFAULT__PAGE_SIZE = 5
-
-    DEFAULT__PAGE_SIZE_MAX = 65536
-
-    GET_DOWNLOAD_URL__URL = BASE_URL_OPEN_API + "/api/tos/get-download-url"
-
-
-class ConstantEnum(BaseEnum):
-    class SourceEnum(Enum):
-        ARK_CLAW = "ARK_CLAW"
-        JVS_CLAW = "JVS_CLAW"
-        LIGHT_CLAW = "LIGHT_CLAW"
-        WUHONG = "WUHONG"
-        COZE = "COZE"
-        SKILL_HUB = "SKILL_HUB"
-        CLAW_HUB = "CLAW_HUB"
-        FEISHU = "FEISHU"
-        DINGTALK = "DINGTALK"
-        WEIXIN = "WEIXIN"
-        YUANBAO = "YUANBAO"
-        WECOM = "WECOM"
-        QQBOT = "QQBOT"
-
-    APP__ID = ""
-
-    APP__SOURCE = SourceEnum.CLAW_HUB.value
-
-    IS_DEBUG = False
-
-    CURRENT__OPEN_ID = ""
-
-    CURRENT__USER_NAME = ""
-
-    CURRENT__TENTANT_CODE = ""
-
-    FEISHU_APP__ID = ""
-
-    FEISHU_APP__SECRET = ""
-
-    FEISHU_APP__RECEIVE_ID = ""
-
-    DEFAULT__SCENE_CODE = ""
-
-    DEFAULT__SKILL_HUB_NAME = APP__SOURCE
-
-    DEFAULT__SKILL_PLATFORM_NAME = ""
-
-    DEFAULT__OUTPUT_LEVEL = "json"
-
-    SUPPORTED_FORMATS = ["mp4", "avi", "mov"]
-
-    MAX_FILE_SIZE_MB = 10
-
-    @staticmethod
-    def is_debug():
-        return platform.system() != 'Linux' and ConstantEnum.IS_DEBUG
-
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-        openclaw_sender_open_id = os.environ.get("OPENCLAW_SENDER_OPEN_ID")
-        openclaw_sender_username = os.environ.get("OPENCLAW_SENDER_USERNAME")
-        feishu_open_id = os.environ.get("FEISHU_OPEN_ID")
-        if openclaw_sender_open_id:
-            cls.CURRENT__OPEN_ID = openclaw_sender_open_id
-        if openclaw_sender_username:
-            cls.CURRENT__USER_NAME = openclaw_sender_username
-        if feishu_open_id:
-            cls.FEISHU_APP__RECEIVE_ID = feishu_open_id
-
-    class SceneCodeEnum(Enum):
-        # 开放 #
-        OPEN_HEALTH_AI_ANALYSIS = "OPEN_HEALTH_AI_ANALYSIS"
-        OPEN_PERSON_RISK_ANALYSIS = "OPEN_PERSON_RISK_ANALYSIS"
-        # 智眸 #
-        PUBLIC_AREA_AI_ANALYSIS = "PUBLIC_AREA_AI_ANALYSIS"
-        PERSONNEL_LEAVE_POST_MONITORING = "PERSONNEL_LEAVE_POST_MONITORING"
-        CRAWL_MONITOR = "CRAWL_MONITOR"
-        # 陪你安 #
-        PEI_NI_AN_DEFAULT = "PEI_NI_AN_DEFAULT"
-        PET_ANALYSIS = "PET_ANALYSIS"
-        CRAWL_ANALYSIS = "CRAWL_ANALYSIS"
-        AQUARIUM_ANALYSIS = "AQUARIUM_ANALYSIS"
-        PSYCHOLOGY_ANALYSIS = "PSYCHOLOGY_ANALYSIS"
-        AUTISM_ANALYSIS = "AUTISM_ANALYSIS"
-        DIET_ANALYSIS = "DIET_ANALYSIS"
-        DRIVE_ANALYSIS = "DRIVE_ANALYSIS"
-        SPORT_ANALYSIS = "SPORT_ANALYSIS"
-        EMOTION_ANALYSIS = "EMOTION_ANALYSIS"
-        STUDY_ANALYSIS = "STUDY_ANALYSIS"
-        INFANT_SAFETY_MONITORING_ANALYSIS = "INFANT_SAFETY_MONITORING"
-        PHONE_USAGE_MONITORING_ANALYSIS = "PHONE_USAGE_MONITORING"
-        INCONTINENCE_ALERT_ANALYSIS = "INCONTINENCE_ALERT"
-        RESPIRATORY_SYMPTOM_RECOGNITION_ANALYSIS = "RESPIRATORY_SYMPTOM_RECOGNITION"
-        ELECTRIC_VEHICLE_DETECTION_ANALYSIS = "ELECTRIC_VEHICLE_DETECTION"
-        SMOKING_DETECTION_ANALYSIS = "SMOKING_DETECTION"
-        PET_DETECTION_FEEDER_ANALYSIS = "PET_DETECTION_FEEDER"
-        PET_HEALTH_MONITORING_ANALYSIS = "PET_HEALTH_MONITORING"
-        STROKE_RISK_SCREENING_ANALYSIS = "STROKE_RISK_SCREENING"
-        HUMAN_DETECTION_ANALYSIS = "HUMAN_DETECTION"
-        STRANGER_RECOGNITION_ANALYSIS = "STRANGER_RECOGNITION"
-        FOCUS_ANALYSIS_ANALYSIS = "FOCUS_ANALYSIS"
-        HUMAN_POSTURE_RECOGNITION_ANALYSIS = "HUMAN_POSTURE_RECOGNITION"
-        HUMAN_EMOTION_RECOGNITION_ANALYSIS = "HUMAN_EMOTION_RECOGNITION"
-        FIRE_SMOKE_DETECTION_ANALYSIS = "FIRE_SMOKE_DETECTION"
-        BASIC_OBJECT_DETECTION_ANALYSIS = "BASIC_OBJECT_DETECTION"
-        CHILD_DANGEROUS_BEHAVIOR_RECOGNITION_ANALYSIS = "CHILD_DANGEROUS_BEHAVIOR_RECOGNITION"
-        PET_RESTRICTED_AREA_WARNING_ANALYSIS = "PET_RESTRICTED_AREA_WARNING"
-        SLEEP_QUALITY_ANALYSIS_ANALYSIS = "SLEEP_QUALITY_ANALYSIS"
-        PET_DETECTION_ANALYSIS = "PET_DETECTION"
-        PSYCHOLOGICAL_STRESS_ASSESSMENT_ANALYSIS = "PSYCHOLOGICAL_STRESS_ASSESSMENT"
-        VISUAL_QA_ANALYSIS = "VISUAL_QA"
-        PET_BODY_HEALTH_ANALYSIS = "PET_BODY_HEALTH_ANALYSIS"
-        PET_BEHAVIOR_DETECTION_ANALYSIS = "PET_BEHAVIOR_DETECTION"
-        INFANT_SUFFOCATION_WARNING_ANALYSIS = "INFANT_SUFFOCATION_WARNING"
-        STRANGER_APPROACH_WARNING_ANALYSIS = "STRANGER_APPROACH_WARNING"
-        IMAGE_QUALITY_DETECTION_ANALYSIS = "IMAGE_QUALITY_DETECTION"
-        CHILD_EMOTION_RECOGNITION_ANALYSIS = "CHILD_EMOTION_RECOGNITION"
-        OUTDOOR_MONITORING_ANALYSIS = "OUTDOOR_MONITORING"
-        FALL_DETECTION_IMAGE_ANALYSIS = "FALL_DETECTION_IMAGE"
-        CUSTOM_TIMELAPSE_ANALYSIS = "CUSTOM_TIMELAPSE"
-        CONTACTLESS_VITAL_SIGNS_MONITORING_ANALYSIS = "CONTACTLESS_VITAL_SIGNS_MONITORING"
-        VIDEO_SEARCH_ANALYSIS = "VIDEO_SEARCH"
-        FAMILIAR_PERSON_RECOGNITION_ANALYSIS = "FAMILIAR_PERSON_RECOGNITION"
-        TCM_CONSTITUTION_RECOGNITION_ANALYSIS = "TCM_CONSTITUTION_RECOGNITION"
-        CONTACTLESS_HEALTH_RISK_DETECTION_ANALYSIS = "CONTACTLESS_HEALTH_RISK_DETECTION"
-        UNACCOMPANIED_MONITORING_ANALYSIS = "UNACCOMPANIED_MONITORING"
-        ELDERLY_FALL_DETECTION_ANALYSIS = "ELDERLY_FALL_DETECTION"
-        PARKINSON_EPILEPSY_BEHAVIOR_RECOGNITION_ANALYSIS = "PARKINSON_EPILEPSY_BEHAVIOR_RECOGNITION"
-        PET_BREED_INDIVIDUAL_RECOGNITION_ANALYSIS = "PET_BREED_INDIVIDUAL_RECOGNITION"
-        ELDERLY_BED_EXIT_WANDERING_MONITORING_ANALYSIS = "ELDERLY_BED_EXIT_WANDERING_MONITORING"
-        ARRHYTHMIA_EARLY_WARNING_ANALYSIS = "ARRHYTHMIA_EARLY_WARNING"
-        FIRE_DETECTION_ANALYSIS = "FIRE_DETECTION"
-        VISUAL_SUMMARY_ANALYSIS = "VISUAL_SUMMARY"
-        PACKAGE_DETECTION_ANALYSIS = "PACKAGE_DETECTION"
-        INFANT_BLANKET_KICK_MONITORING_ANALYSIS = "INFANT_BLANKET_KICK_MONITORING"
-        PET_CALMING_TRIGGER_ANALYSIS = "PET_CALMING_TRIGGER"
-        CAT_FACE_RECOGNITION_ANALYSIS = "CAT_FACE_RECOGNITION"
-        INFANT_SLEEP_MONITORING_ANALYSIS = "INFANT_SLEEP_MONITORING"
-        VIRTUAL_FENCE_INTRUSION_WARNING_ANALYSIS = "VIRTUAL_FENCE_INTRUSION_WARNING"
-        FALL_DETECTION_VIDEO_ANALYSIS = "FALL_DETECTION_VIDEO"
-        INFANT_CRY_ANALYSIS = "INFANT_CRY_ANALYSIS"
-        PET_VOCAL_EMOTION_ANALYSIS = "PET_VOCAL_EMOTION_ANALYSIS"
-        BIRD_RECOGNITION_ANALYSIS = "BIRD_RECOGNITION"
-        FRAUD_CALL_IDENTIFICATION = "FRAUD_CALL_IDENTIFICATION"

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/config.yaml

@@ -1,18 +0,0 @@
-env: prod
-
-ApiEnum:
-  api-key:
-  api-secret-key:
-  database-url:
-  base-url-open-api: "https://open.lifeemergence.com/smyx-open-api"
-  base-url-open-h5: "http://livemonitor.lifeemergence.com"
-  base-url-health: "https://lifeemergence.com/jeecg-boot"
-
-ConstantEnum:
-  is-debug: false
-  app--id: x1a3s4nwy1s2r4se
-  current--tentant-code: "PEI_NI_AN"
-  feishu-app--id: cli_a93d769369badcb1
-  feishu-app--secret:
-  default--skill-platform-name: ARK_CLAW
-#  default--scene-code: PEI_NI_AN_DEFAULT

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/dao.py

@@ -1,348 +0,0 @@
-#!/usr/bin/env python3
-"""
-本地化轻量级数据库封装
-使用SQLite + SQLAlchemy ORM
-支持基础CRUD操作，通过继承BaseDao快速实现各表的Dao层
-"""
-import datetime
-import sys
-from enum import Enum
-from typing import Any, Dict, List, Optional, Type, TypeVar
-from sqlalchemy import create_engine, Column, Integer, String, DateTime, func, Select, Table, MetaData, select, or_
-from sqlalchemy.orm import declarative_base
-from sqlalchemy.orm import sessionmaker, Session
-from sqlalchemy.sql.expression import text
-
-from skills.smyx_common.scripts.config import ConstantEnum, ApiEnum
-
-from skills.smyx_common.scripts.util import StringUtil, DatetimeUtil, FileUtil
-
-from skills.smyx_common.scripts.base import BaseMixin, BaseDao
-
-# 基础模型类
-Base = declarative_base()
-
-# 泛型类型，用于返回对应模型实例
-T = TypeVar('T', bound=Base)
-
-meta = MetaData()
-
-DATABASE_URL = ApiEnum.DATABASE_URL
-
-
-class BaseModelMixin(BaseMixin):
-
-    @classmethod
-    def load(cls, source: dict):
-        """
-        获取源枚举
-        :param source: 源
-        :return: User
-        """
-        column_names = cls.__table__.columns.keys()
-        user_dict = {k: source.get(StringUtil.snake_to_camel(k)) for k in column_names}
-        user_dict["create_time"] = DatetimeUtil.parse(user_dict["create_time"])
-        user_dict["update_time"] = DatetimeUtil.parse(user_dict["update_time"])
-        model = cls(**user_dict)
-        return model
-
-
-class Dao(BaseDao):
-    """
-    基础Dao类，提供通用的CRUD操作
-    子类只需配置__model__和__tablename__即可使用
-    """
-    __model__: Type[T] = None  # 对应的模型类，子类必须配置
-    __tablename__: str = None  # 表名，子类必须配置
-
-    def get_db_path(self, db_path):
-        import os
-
-        cwd = os.getcwd()
-        workspace = os.path.dirname(cwd)
-        workspace = os.path.dirname(workspace)
-        workspace = os.environ.get('OPENCLAW_WORKSPACE', workspace)
-        parent_dir = os.path.join(workspace, "data")
-        FileUtil.mkdir(parent_dir)
-        db_path = os.path.join(parent_dir, db_path)
-
-        return db_path
-
-    def __init__(self, db_path: str = None):
-        """
-        初始化Dao
-        :param db_path: SQLite数据库文件路径
-        """
-
-        if not db_path:
-            db_path = "smyx-common-claw.db"
-            db_path = self.get_db_path(db_path)
-
-        self.engine = create_engine(f"sqlite:///{db_path}", echo=False)
-
-        # 创建会话工厂
-        self.SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=self.engine)
-        # 初始化表结构
-        self._create_tables()
-        self._alter_tables()
-
-    def _create_tables(self) -> None:
-        """创建所有表结构"""
-        Base.metadata.create_all(bind=self.engine)
-
-    def _alter_tables(self) -> None:
-        """创建所有表结构"""
-        sql_statement = "ALTER TABLE sys_user ADD COLUMN source_id INT;"
-
-        # 3. 执行语句
-        try:
-            with self.engine.connect() as connection:
-                connection.execute(text(sql_statement))
-                connection.commit()  # 对于数据定义语言(DDL)，需要显式提交
-        except Exception as e:
-            connection.rollback()
-            if len(e.args) and "duplicate column name" in e.args[0]:
-                pass
-            else:
-                raise
-
-    def get_session(self) -> Session:
-        """获取数据库会话"""
-        return self.SessionLocal()
-
-    def save(self, model) -> T:
-        """
-        创建新记录
-        :param kwargs: 字段键值对
-        :return: 创建的模型实例
-        """
-
-        try:
-            return self.add(
-                model
-            )
-
-        except Exception as e:
-            return self.update(
-                model
-            )
-
-    def add(self, model) -> T:
-        """
-        创建新记录
-        :param kwargs: 字段键值对
-        :return: 创建的模型实例
-        """
-        session = self.get_session()
-        try:
-            session.add(model)
-            session.commit()
-            session.refresh(model)
-            return model
-        finally:
-            session.close()
-
-    def create(self, **kwargs) -> T:
-        """
-        创建新记录
-        :param kwargs: 字段键值对
-        :return: 创建的模型实例
-        """
-        instance = self.__model__(**kwargs)
-        return self.add(instance)
-
-    def get_by_id(self, record_id: int) -> Optional[T]:
-        """
-        根据ID查询记录
-        :param record_id: 记录ID
-        :return: 模型实例或None
-        """
-        session = self.get_session()
-        try:
-            return session.query(self.__model__).filter(self.__model__.id == record_id).first()
-        finally:
-            session.close()
-
-    def get_by_username(self, username: str) -> Optional[T]:
-        """
-        根据ID查询记录
-        :param record_id: 记录ID
-        :return: 模型实例或None
-        """
-        session = self.get_session()
-        try:
-            or_(
-                self.__model__.del_flag == 0,
-                self.__model__.del_flag.is_(None)  # 关键：使用 .is_(None) 来判断 SQL 的 NULL
-            )
-            return session.query(self.__model__).filter(self.__model__.username == username,
-                                                        or_(
-                                                            self.__model__.del_flag == 0,
-                                                            self.__model__.del_flag.is_(None)
-                                                            # 关键：使用 .is_(None) 来判断 SQL 的 NULL
-                                                        )).first()
-        finally:
-            session.close()
-
-    def list(self, filters: Optional[Dict[str, Any]] = None, limit: Optional[int] = None,
-             offset: Optional[int] = None) -> List[T]:
-        """
-        查询记录列表
-        :param filters: 过滤条件字典，如{"name": "张三", "age": 18}
-        :param limit: 最大返回数量
-        :param offset: 偏移量
-        :return: 模型实例列表
-        """
-        session = self.get_session()
-        try:
-            query = session.query(self.__model__)
-            # .where(self.__model__.id != 2, self.__model__.id == 1))
-
-            if filters:
-                for key, value in filters.items():
-                    query = query.filter(getattr(self.__model__, key) == value)
-
-            if offset:
-                query = query.offset(offset)
-            if limit:
-                query = query.limit(limit)
-
-            return query.all()
-        finally:
-            session.close()
-
-    def update(self, model) -> Optional[T]:
-        """
-        更新记录
-        :param record_id: 记录ID
-        :param kwargs: 要更新的字段键值对
-        :return: 更新后的模型实例或None
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.id == model.id).first()
-            if not instance:
-                return None
-
-            column_names = self.__model__.__table__.columns.keys()
-
-            for key in column_names:
-                value = getattr(model, key)
-                setattr(instance, key, value)
-
-            session.commit()
-            session.refresh(instance)
-            return instance
-        finally:
-            session.close()
-
-    def modify(self, record_id: int, **kwargs) -> Optional[T]:
-        """
-        更新记录
-        :param record_id: 记录ID
-        :param kwargs: 要更新的字段键值对
-        :return: 更新后的模型实例或None
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.id == record_id).first()
-            if not instance:
-                return None
-
-            for key, value in kwargs.items():
-                setattr(instance, key, value)
-
-            session.commit()
-            session.refresh(instance)
-            return instance
-        finally:
-            session.close()
-
-    def update_by_username(self, username: str, **kwargs) -> Optional[T]:
-        """
-        更新记录
-        :param username: 记录ID
-        :param kwargs: 要更新的字段键值对
-        :return: 更新后的模型实例或None
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.username == username).first()
-            if not instance:
-                return None
-
-            for key, value in kwargs.items():
-                setattr(instance, key, value)
-
-            session.commit()
-            session.refresh(instance)
-            return instance
-        finally:
-            session.close()
-
-    def delete(self, record_id: int) -> bool:
-        """
-        删除记录
-        :param record_id: 记录ID
-        :return: 删除成功返回True，失败返回False
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.id == record_id).first()
-            if not instance:
-                return False
-
-            session.delete(instance)
-            session.commit()
-            return True
-        finally:
-            session.close()
-
-    def count(self, filters: Optional[Dict[str, Any]] = None) -> int:
-        """
-        统计记录数量
-        :param filters: 过滤条件字典
-        :return: 记录数量
-        """
-        session = self.get_session()
-        try:
-            query = session.query(func.count(self.__model__.id))
-
-            if filters:
-                for key, value in filters.items():
-                    query = query.filter(getattr(self.__model__, key) == value)
-
-            return query.scalar()
-        finally:
-            session.close()
-
-
-class User(Base, BaseModelMixin):
-    """用户模型"""
-    __tablename__ = "sys_user"
-
-    id = Column(String(32), primary_key=True, index=True)
-    source_id = Column(String(32), comment="源头id")
-    username = Column(String(100), unique=True, index=True, nullable=False, comment="用户名")
-    email = Column(String(45), unique=True, index=True, comment="邮箱")
-    birthday = Column(DateTime, unique=True, index=True, comment="邮箱")
-    sex = Column(Integer, comment="性别")
-    age = Column(Integer, comment="年龄")
-    token = Column(String(500), comment="token")
-    open_token = Column(String(1000), comment="开放token")
-    source = Column(String(50), comment="token")
-    del_flag = Column(Integer, comment="是否删除", default=0)
-    create_time = Column(DateTime, default=func.now(), comment="创建时间")
-    update_time = Column(DateTime, default=func.now(), onupdate=func.now(), comment="更新时间")
-
-    SourceEnum = ConstantEnum.SourceEnum
-
-
-class UserDao(Dao):
-    """用户Dao，继承BaseDao即可拥有所有基础CRUD功能"""
-    __model__ = User
-    __tablename__ = "users"
-
-
-if __name__ == "__main__":
-    pass

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/skill.py

@@ -1,82 +0,0 @@
-#!/usr/bin/env python3
-import os
-import sys
-import subprocess
-
-from .config import ApiEnum as ApiEnumBase, ConstantEnum
-from .base import BaseSkill
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-from .util import FileUtil
-
-from .api_service import ApiService
-
-class Skill(BaseSkill, ApiService):
-
-    def __init__(self):
-        super().__init__()
-
-class AgentSkill(BaseSkill, ApiService):
-
-    def __init__(self):
-        super().__init__()
-
-    def ai_chat(self, prompt: str, session_id: str = None, timeout: int = 120):
-        """
-        通过 subprocess 调用 openclaw agent 命令
-
-        Args:
-            prompt: 分析提示
-            session_id: 会话 ID（可选）
-            timeout: 超时时间（秒）
-
-        Returns:
-            分析结果或会话 ID
-        """
-        import uuid
-
-        # 生成唯一会话 ID
-        if not session_id:
-            entry_script = sys.argv[0]
-            abs_entry_script = os.path.abspath(entry_script)
-            main_name = FileUtil.get_name(abs_entry_script)
-            session_id = f"{main_name}--{uuid.uuid4()}"
-
-        ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent (会话：{session_id})..., prompt:{prompt}")
-
-        # 构建命令
-        cmd = [
-            "openclaw",
-            "agent",
-            "-m", str(prompt),
-            "--session-id", session_id,
-            "--thinking", "minimal",
-            "--timeout", str(timeout)
-        ]
-
-        ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行命令{' '.join(cmd)}")
-
-        try:
-            # 执行命令
-            result = subprocess.run(
-                cmd,
-                capture_output=True,
-                text=True,
-                timeout=timeout + 10
-            )
-
-            if result.stderr:
-                ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行错误:{result.stderr}")
-                return
-
-            output = result.stdout
-            ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行成功:{output}")
-
-            return output
-
-        except subprocess.TimeoutExpired as e:
-            ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 超时（{timeout}秒），任务可能仍在后台运行:{e}")
-        except Exception as e:
-            ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行错误:{e}")
-
-
-skill = Skill()

skills/18072937735/smyx-bird-recognition-analysis/skills/smyx_common/scripts/util.py

@@ -1,413 +0,0 @@
-#!/usr/bin/env python3
-import json
-import os
-import traceback
-
-import requests
-from .config import ApiEnum, ConstantEnum, sys, YamlUtil
-
-from .base import BaseUtil
-import time
-import logging
-from typing import Any, Callable, Optional, TypeVar, Dict
-import pydash as _
-
-if ConstantEnum.is_debug():
-    import http.client
-
-    # 【关键代码】开启调试模式
-    http.client.HTTPConnection.debuglevel = 1
-    # 可选：如果你希望日志更整洁，可以配合 logging 模块（否则打印会比较乱）
-    import logging
-
-    logging.basicConfig()
-    logging.getLogger().setLevel(logging.DEBUG)
-    requests_log = logging.getLogger("urllib3")
-    requests_log.setLevel(logging.DEBUG)
-    requests_log.propagate = True
-
-
-class StringUtil(BaseUtil):
-
-    @staticmethod
-    def camel_to_snake(name):
-        import re
-        s1 = re.sub('(.)([A-Z][a-z]+)', r'\1_\2', name)
-        return re.sub('([a-z0-9])([A-Z])', r'\1_\2', s1).lower()
-
-    @staticmethod
-    def snake_to_pascal(name):
-        import re
-        name = re.sub(r'^([a-z])', lambda m: m.group(1).upper(), name)
-        return re.sub(r'_([a-z])', lambda m: m.group(1).upper(), name)
-
-    @staticmethod
-    def snake_to_camel(name):
-        import re
-        # 逻辑：匹配 '_[a-z]' (下划线+小写字母)，将其替换为对应的大写字母（去掉下划线）
-        return re.sub(r'_([a-z])', lambda m: m.group(1).upper(), name)
-
-
-class FileUtil(BaseUtil):
-
-    @staticmethod
-    def get_fullname(path):
-        try:
-            return os.path.basename(path)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            return ""
-
-    @staticmethod
-    def get_name(path):
-        try:
-            return os.path.splitext(os.path.basename(path))[0]
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-    @staticmethod
-    def get_ext(path):
-        try:
-            return os.path.splitext(os.path.basename(path))[1]
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-    @staticmethod
-    def open(path):
-        try:
-            return open(path, 'w', encoding='utf-8')
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-    @staticmethod
-    def mkdir(path):
-        try:
-            os.makedirs(path, exist_ok=True)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-
-class JsonUtil(BaseUtil):
-
-    @staticmethod
-    def stringify(json_obj, default_str=""):
-        try:
-            return json.dumps(json_obj, ensure_ascii=False, indent=2)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            pass
-        return default_str
-
-    @staticmethod
-    def parse(json_str, default_json={}):
-        try:
-            return json.loads(json_str)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            pass
-        return default_json
-
-
-class CommonUtil(BaseUtil):
-
-    @staticmethod
-    def trace_exception_stack(e):
-        if ConstantEnum.is_debug():
-            print(f"❌ 错误描述: {str(e)}, 堆栈跟踪:")
-            traceback.print_stack()
-
-    @staticmethod
-    def polling(
-            action: Callable[[], Any],
-            check_condition: Callable[[Any], bool],
-            on_success: Optional[Callable[[Any], None]] = None,
-            on_retry: Optional[Callable[[Any, int], None]] = None,
-            on_error: Optional[Callable[[Exception], None]] = None,
-            interval: float = 1.0,
-            max_attempts: int = 5,
-            description: str = "轮询任务"
-    ) -> Optional[Any]:
-        """
-        通用的轮询处理函数
-
-        :param action:
-            [必填] 执行动作的回调函数。
-            例如：发送 HTTP 请求、查询数据库状态等。
-            必须返回一个结果对象供 check_condition 使用。
-
-        :param check_condition:
-            [必填] 检查是否结束的回调函数。
-            接收 action 的返回值，返回 True 表示“满足结束条件”，False 表示“继续轮询”。
-            例如：lambda res: res.get('need_refresh') is False
-
-        :param on_success:
-            [可选] 当 check_condition 返回 True 时执行的回调（通常用于记录日志或处理最终数据）。
-
-        :param on_retry:
-            [可选] 当需要继续轮询时执行的回调。
-            参数：(当前结果, 当前尝试次数)。可用于打印进度。
-
-        :param on_error:
-            [可选] 当 action 抛出异常时执行的回调。
-            参数：(异常对象)。
-
-        :param interval:
-            每次轮询之间的等待时间（秒）。
-
-        :param max_attempts:
-            最大尝试次数，防止死循环。
-
-        :param description:
-            任务描述，用于日志输出。
-
-        :return:
-            如果成功，返回 action 的最后一次返回值；如果超时或失败，返回 None。
-        """
-
-        attempts = 0
-
-        print(f"🚀 开始执行 [{description}]...")
-
-        while attempts < max_attempts:
-            attempts += 1
-
-            try:
-                # 1. 执行动作
-                result = action()
-                last_result = result
-
-                # 2. 检查条件
-                if check_condition(result):
-                    print(f"✅ [{description}] 成功！条件已满足 (尝试次数: {attempts}, 耗时{interval * attempts}秒)")
-                    if on_success:
-                        on_success(result)
-                    return result
-
-                # 3. 条件未满足，准备重试
-                if on_retry:
-                    on_retry(result, attempts)
-                else:
-                    # 默认日志行为
-                    print(
-                        f"⏳ [{description}] 条件未满足，{interval}秒后重试... ({attempts}/{max_attempts}, 耗时{interval * attempts}秒)")
-
-                time.sleep(interval)
-
-            except Exception as e:
-                # 4. 异常处理
-                if on_error:
-                    on_error(e)
-                else:
-                    # 默认错误行为：打印错误并继续
-                    logging.error(f"❌ [{description}] 发生异常: {e}")
-                    print(f"⚠️ [{description}] 遇到错误，{interval}秒后重试...")
-
-                time.sleep(interval)
-
-        # 5. 超时处理
-        print(f"⚠️ [{description}] 失败：达到最大尝试次数 ({max_attempts})，强制停止。")
-        return None
-
-    @staticmethod
-    def is_empty(data):
-        # 1. 如果是 None (对应 JSON 的 null)
-        if data is None:
-            return True
-
-        # 2. 如果是字典或列表，且长度为 0 (对应 {} 或 [])
-        if isinstance(data, (dict, list)) and len(data) == 0:
-            return True
-
-
-from datetime import date, datetime
-
-
-class DatetimeUtil(BaseUtil):
-    FORMAT__DATETIME = "%Y-%m-%d %H:%M:%S"
-
-    @staticmethod
-    def now_str():
-        return DatetimeUtil.format(DatetimeUtil.now())
-
-    @staticmethod
-    def today_str():
-        return DatetimeUtil.format_date(DatetimeUtil.today())
-
-    @staticmethod
-    def now():
-        return datetime.now()
-
-    @staticmethod
-    def today():
-        return DatetimeUtil.now().replace(hour=0, minute=0, second=0, microsecond=0)
-
-    @staticmethod
-    def format(date):
-        return date.strftime('%Y-%m-%d %H:%M:%S') if type(date) == datetime else date
-
-    @staticmethod
-    def format_date(date):
-        return date.strftime('%Y-%m-%d') if type(date) == datetime else date
-
-    @staticmethod
-    def parse(date_str):
-        if type(date_str) == int:
-            return datetime.fromtimestamp(date_str)
-        return datetime.strptime(date_str, DatetimeUtil.FORMAT__DATETIME) if type(date_str) == str else date_str
-
-    @staticmethod
-    def timestamp(date=now()):
-        return int(date.timestamp() * 1000)
-
-
-class RequestUtil(BaseUtil):
-    BASE_URL = ApiEnum.BASE_URL_OPEN_API
-    AUTHORIZATION_RETRY_COUNT_MAX = 3
-    authorization_retry_count = 0
-
-    @classmethod
-    def http_post(cls, url, data=None, params=None, headers=None, *args, **argss):
-        return cls.http_request("post", url, data=data, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_put(cls, url, data=None, params=None, headers=None, *args, **argss):
-        return cls.http_request("put", url, data=data, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_delete(cls, url, data=None, params=None, headers=None, *args, **argss):
-        return cls.http_request("delete", url, data=data, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_get(cls, url, params=None, headers=None, *args, **argss):
-        return cls.http_request("get", url, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_request(cls, method, url, data=None, params=None, headers=None, options=None, *args,
-                     timeout=ApiEnum.DEFAULT__REQUEST_TIMEOUT, **argss):
-        def _get_or_create_user(username):
-            _url = ApiEnum.BASE_URL_HEALTH + "/sys/phoneLogin"
-            open_id = username
-            _data = {
-                "silent": 1,
-                "register": 1,
-                "openId": open_id,
-                "mobile": username
-            }
-            try:
-                _response = requests.post(_url, json=_data)
-                if _response.status_code == 200:
-                    _response_json = _response.json()
-                    if _response_json and _response_json.get("success"):
-                        return _response_json and _response_json.get("result")
-            except Exception as _e:
-                CommonUtil.trace_exception_stack(_e)
-            return {}
-
-        try:
-            headers = headers or {}
-            if not url.startswith("https://") and not url.startswith("http://"):
-                url = cls.BASE_URL + url
-            headers['App-Id'] = ConstantEnum.APP__ID
-            # ConstantEnum.CURRENT__USER_NAME = ConstantEnum.CURRENT__OPEN_ID = "ou_86fdd8e0d5f116c18a9dd550abefe6d2"
-            current__user_name = ApiEnum.API_SECRET_KEY or ConstantEnum.CURRENT__USER_NAME or ConstantEnum.CURRENT__OPEN_ID
-            if (not ApiEnum.TOKEN or not ApiEnum.OPEN_TOKEN) and current__user_name:
-                try:
-                    from .dao import UserDao, User
-                    user_dao = UserDao()
-                    found_user = user_dao.get_by_username(current__user_name)
-                    if found_user:
-                        ApiEnum.TOKEN = found_user.token
-                        ApiEnum.OPEN_TOKEN = found_user.open_token
-                    if not ApiEnum.TOKEN or not ApiEnum.OPEN_TOKEN:
-                        new_current_user = _get_or_create_user(current__user_name)
-                        if new_current_user:
-                            ApiEnum.TOKEN = new_current_user.get("token")
-                            ApiEnum.OPEN_TOKEN = new_current_user.get("openToken")
-
-                            current_user_info = new_current_user.get("userInfo")
-                            if current_user_info:
-                                current_user_info["token"] = new_current_user.get("token")
-                                current_user_info["openToken"] = new_current_user.get(
-                                    "openToken")
-                                user_model = User.load(current_user_info)
-
-                                user = user_dao.save(
-                                    user_model
-                                )
-
-                except Exception as e:
-                    CommonUtil.trace_exception_stack(e)
-                    raise
-
-            headers.setdefault("X-Access-Token", ApiEnum.TOKEN)
-            headers.setdefault("X-Api-Key", ApiEnum.API_SECRET_KEY)
-            headers.setdefault("Authorization", ApiEnum.OPEN_TOKEN)
-
-            data = data or {}
-            params = params or {}
-            options = options or {}
-            ConstantEnum.CURRENT__TENTANT_CODE and data.setdefault('tenantCode', ConstantEnum.CURRENT__TENTANT_CODE)
-            ConstantEnum.DEFAULT__SKILL_HUB_NAME and data.setdefault('skillHubName',
-                                                                     ConstantEnum.DEFAULT__SKILL_HUB_NAME)
-            ConstantEnum.DEFAULT__SKILL_PLATFORM_NAME and data.setdefault('skillPlatform',
-                                                                          ConstantEnum.DEFAULT__SKILL_PLATFORM_NAME)
-            if current__user_name:
-                data.setdefault('pnaUserName', current__user_name)
-
-            if bool(options.get("dataAsParams")):
-                params.update(data)
-
-            print(f"🔄 请求拦截, URL:{url}", "method", method, "params", params, "data", data, "headers", headers,
-                  "options", options,
-                  "timeout",
-                  timeout)
-            response = requests.request(method, url, *args, json=data, params=params, headers=headers,
-                                        timeout=int(timeout), **argss)
-            response_text = response.text if ConstantEnum.is_debug() else response
-            if response.status_code == 401 and cls.authorization_retry_count < cls.AUTHORIZATION_RETRY_COUNT_MAX:
-                print(f"❌ 请求拦截, 鉴权:{response_text}, url:{url}", "method", method, "params", params,
-                      "data",
-                      data,
-                      "headers",
-                      headers,
-                      "timeout",
-                      timeout)
-                ApiEnum.TOKEN = ApiEnum.OPEN_TOKEN = None
-                if found_user:
-                    found_user.token = found_user.open_token = None
-                    user_dao.update(found_user)
-                cls.authorization_retry_count += 1
-                return cls.http_request(method, url, data, params, headers, options, *args, timeout=timeout, **argss)
-            elif response.status_code != 200:
-                raise requests.exceptions.RequestException(
-                    response, response=response)
-            response_json = response.json()
-            if not bool(response_json['success']):
-                raise requests.exceptions.RequestException(
-                    response, response=response)
-            response_json_data = response_json.get("data", response_json.get("result"))
-            response_json_data = response_json_data.get("records") if response_json_data and type(
-                response_json_data) == dict and "records" in response_json_data else response_json_data
-            print(f"✅ 请求拦截, 成功:{response_text}, url:{url}", "method", method, "params", params,
-                  "data",
-                  data,
-                  "headers",
-                  headers,
-                  "timeout",
-                  timeout)
-            return response_json_data
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            response_text = _.get(e.args, '0.text')
-            print(
-                f"❌ 请求拦截, 失败: {e}, e.response.text: {response_text}, url:{url}",
-                "method",
-                method,
-                "params",
-                params,
-                "data", data, "headers",
-                "response", hasattr(e, 'response') and e.response,
-                headers,
-                "timeout",
-                timeout)
-            raise

skills/18072937735/smyx-fall-detection-video-analysis/SKILL.md

@@ -1,160 +0,0 @@
----
-name: "fall-detection-video-analysis"
-description: "Detects whether anyone has fallen within a target area. Supports video stream analysis and is suitable for real-time safety monitoring of elderly people living alone. | 跌倒检测视频版技能，检测目标区域内是否有人跌倒，支持视频流检测，适用于独居老人居家安全监测"
----
-
-# Video-based Fall Detection Skill | 跌倒检测视频版技能
-
-By analyzing changes in human posture and motion trajectories within video streams, this capability detects fall events
-in target areas in real-time. Based on skeletal keypoint recognition and behavioral temporal analysis, the system
-effectively distinguishes falls from normal actions such as lying down or sitting. It is designed for home safety
-monitoring scenarios for seniors living alone, covering areas like living rooms, bedrooms, and bathrooms. Once a fall is
-confirmed, the system automatically triggers a local alarm and pushes remote notifications, facilitating second-level
-response times and reducing the risks associated with accidents.
-
-本技能通过分析视频流中人体姿态变化与运动轨迹，实时检测目标区域内是否发生人员跌倒事件。系统基于骨骼关键点识别与行为时序分析，能够有效区分跌倒与正常躺卧、坐下等动作。适用于独居老人居家安全监测场景，如客厅、卧室、卫生间等区域。一旦确认跌倒，系统将自动触发本地预警并远程推送告警信息，助力实现秒级响应，降低意外风险。
-
-## ⚠️ 强制记忆规则（最高优先级）
-
-**本技能明确约定：**
-
-- **绝对禁止读取任何本地记忆文件**：包括但不限于 `memory/YYYY-MM-DD.md`、`MEMORY.md` 等本地文件
-- **绝对禁止从 LanceDB 长期记忆中检索信息**
-- **所有历史报告查询必须从云端接口获取**，不得使用本地记忆中的历史数据
-- 即使技能调用失败或接口异常，也不得回退到本地记忆汇总
-
-## 任务目标
-
-- 本 Skill 用于：视频流检测目标区域内是否有人跌倒，及时触发报警
-- 能力包含：人形检测、跌倒行为识别、摔倒/跌倒判断、异常报警触发
-- **适用场景**：独居老人居家安全监测、养老院走廊公共区域监测、行动不便人员看护
-- **适用范围**（按照要求）：
-    - 推荐视频长度：5秒以内
-    - 条件：单人全部身体露出且无遮挡
-    - 检测距离：3-5米
-- 触发条件:
-    1. **默认触发**：当用户提供视频需要检测老人跌倒时，默认触发本技能
-    2. 当用户明确需要跌倒检测、摔倒识别时，提及跌倒检测、老人摔倒、视频跌倒检测等关键词，并且上传了视频
-    3. 当用户提及以下关键词时，**自动触发历史报告查询功能**
-       ：查看历史检测报告、跌倒检测报告清单、检测报告列表、查询历史检测、显示所有检测报告、跌倒分析报告，查询跌倒检测视频分析报告
-- 自动行为：
-    1. 如果用户上传了附件或者视频文件，则自动保存到技能目录下 attachments
-    2. **⚠️ 强制数据获取规则（次高优先级）**：如果用户触发任何历史报告查询关键词（如"查看所有检测报告"、"显示历史跌倒"、"
-       查看历史报告"等），**必须**：
-        - 直接使用 `python -m scripts.fall_detection_video_analysis --list --open-id` 参数调用 API
-          查询云端的历史报告数据
-        - **严格禁止**：从本地 memory 目录读取历史会话信息、严格禁止手动汇总本地记录中的报告、严格禁止从长期记忆中提取报告
-        - **必须统一**从云端接口获取最新完整数据，然后以 Markdown 表格格式输出结果
-
-## 前置准备
-
-- 依赖说明:scripts 脚本所需的依赖包及版本
-  ```
-  requests>=2.28.0
-  ```
-
-## 检测要求（获得准确结果的前提）
-
-为了获得准确的跌倒检测，请确保：
-
-1. **摄像头固定位置**，覆盖目标监测区域（如客厅、走廊、卫生间）
-2. **检测距离保持在 3-5 米**，目标人物全身完整出镜
-3. **单人场景**，避免多人重叠遮挡，保证跌倒行为清晰可见
-4. 建议视频长度在 **5秒以内**，过长视频建议分段检测
-
-## 操作步骤
-
-### 🔒 open-id 获取流程控制（强制执行，防止遗漏）
-
-**在执行跌倒检测视频分析前，必须按以下优先级顺序获取 open-id：**
-
-```
-第 1 步：【最高优先级】检查技能所在目录的配置文件（优先）
-        路径：skills/smyx_common/scripts/config.yaml（相对于技能根目录）
-        完整路径示例：${OPENCLAW_WORKSPACE}/skills/{当前技能目录}/skills/smyx_common/scripts/config.yaml
-        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id
-        ↓ (未找到/未配置/api-key 为空)
-第 2 步：检查 workspace 公共目录的配置文件
-        路径：${OPENCLAW_WORKSPACE}/skills/smyx_common/scripts/config.yaml
-        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id
-        ↓ (未找到/未配置)
-第 3 步：检查用户是否在消息中明确提供了 open-id
-        ↓ (未提供)
-第 4 步：❗ 必须暂停执行，明确提示用户提供用户名或手机号作为 open-id
-```
-
-**⚠️ 关键约束：**
-
-- **禁止**自行假设,自行推导,自行生成 open-id 值（如 openclaw-control-ui、default、fallvideo123、detectfall456 等）
-- **禁止**跳过 open-id 验证直接调用 API
-- **必须**在获取到有效 open-id 后才能继续执行分析
-- 如果用户拒绝提供 open-id，说明用途（用于保存和查询检测报告记录），并询问是否继续
-
----
-
-- 标准流程:
-    1. **准备监控视频输入**
-        - 提供本地视频文件路径或网络视频 URL
-        - 确保符合：5秒以内、单人全身出镜、无遮挡、3-5米距离
-    2. **获取 open-id（强制执行）**
-        - 按上述流程控制获取 open-id
-        - 如无法获取，必须提示用户提供用户名或手机号
-    3. **执行跌倒检测视频分析**
-        - 调用 `-m scripts.fall_detection_video_analysis` 处理视频（**必须在技能根目录下运行脚本**）
-        - 参数说明:
-            - `--input`: 本地视频文件路径（使用 multipart/form-data 方式上传）
-            - `--url`: 网络视频 URL 地址（API 服务自动下载）
-            - `--open-id`: 当前用户的 open-id（必填，按上述流程获取）
-            - `--list`: 显示历史跌倒检测视频分析报告列表清单（可以输入起始日期参数过滤数据范围）
-            - `--api-key`: API 访问密钥（可选）
-            - `--api-url`: API 服务地址（可选，使用默认值）
-            - `--detail`: 输出详细程度（basic/standard/json，默认 json）
-            - `--output`: 结果输出文件路径（可选）
-    4. **查看分析结果**
-        - 接收结构化的跌倒检测视频分析报告
-        - 包含：视频基本信息、检测结果、是否跌倒、跌倒位置、置信度、是否需要报警
-
-## 资源索引
-
-- 必要脚本：见 [scripts/fall_detection_video_analysis.py](scripts/fall_detection_video_analysis.py)(用途：调用 API
-  进行跌倒检测视频分析，本地文件使用 multipart/form-data 方式上传，网络 URL 由 API 服务自动下载)
-- 配置文件：见 [scripts/config.py](scripts/config.py)(用途：配置 API 地址、默认参数和格式限制)
-- 领域参考：见 [references/api_doc.md](references/api_doc.md)(何时读取：需要了解 API 接口详细规范和错误码时)
-
-## 注意事项
-
-- 仅在需要时读取参考文档，保持上下文简洁
-- 支持格式：mp4/avi/mov，最大 100MB
-- API 密钥可选，如果通过参数传入则必须确保调用鉴权成功，否则忽略鉴权
-- **⚠️ 重要提醒**：本检测结果仅供安全预警参考，不能替代人工确认，发现跌倒报警请立即联系家人或医护人员现场确认
-- 禁止临时生成脚本，只能用技能本身的脚本
-- 传入的网路地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载
-- 当显示历史分析报告清单的时候，从数据 json 中提取字段 reportImageUrl 作为超链接地址，使用 Markdown 表格格式输出，包含"
-  报告名称"、"检测结果"、"是否报警"、"检测时间"、"点击查看"五列，其中"报告名称"列使用`跌倒检测视频报告-{记录id}`形式拼接, "
-  点击查看"列使用
-  `[🔗 查看报告](reportImageUrl)`
-  格式的超链接，用户点击即可直接跳转到对应的完整报告页面。
-- 表格输出示例：
-  | 报告名称 | 检测结果 | 是否报警 | 检测时间 | 点击查看 |
-  |----------|----------|----------|----------|----------|
-  | 跌倒检测视频报告 -20260329003600001 | 未检测到跌倒 | 否 | 2026-03-29 00:
-  36 | [🔗 查看报告](https://example.com/report?id=xxx) |
-
-## 使用示例
-
-```bash
-# 检测本地监控视频（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.fall_detection_video_analysis --input /path/to/fall_detect.mp4 --open-id openclaw-control-ui
-
-# 检测网络视频（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.fall_detection_video_analysis --url https://example.com/detect.mp4 --open-id openclaw-control-ui
-
-# 显示历史检测报告/显示检测报告清单列表/显示历史跌倒检测（自动触发关键词：查看历史检测报告、历史报告、检测报告清单等）
-python -m scripts.fall_detection_video_analysis --list --open-id openclaw-control-ui
-
-# 输出精简报告
-python -m scripts.fall_detection_video_analysis --input fall_detect.mp4 --open-id your-open-id --detail basic
-
-# 保存结果到文件
-python -m scripts.fall_detection_video_analysis --input fall_detect.mp4 --open-id your-open-id --output result.json
-```

skills/18072937735/smyx-fall-detection-video-analysis/_meta.json

@@ -1,11 +0,0 @@
-{
-  "owner": "18072937735",
-  "slug": "smyx-fall-detection-video-analysis",
-  "displayName": "Video-based Fall Detection Skill | 跌倒检测视频版技能",
-  "latest": {
-    "version": "1.0.0",
-    "publishedAt": 1776257210180,
-    "commit": "https://github.com/openclaw/skills/commit/b0fcda692ea20ee98eed52d76845ba4687cefc48"
-  },
-  "history": []
-}

skills/18072937735/smyx-fall-detection-video-analysis/references/api_doc.md

@@ -1,21 +0,0 @@
-# API 接口文档
-
-此处用于存放跌倒检测视频分析 API 的接口文档，待后续补充。
-
-## 接口规范
-
-- 基础地址：由 smyx_common 配置统一管理
-- 认证方式：API Key 鉴权
-- 请求格式：multipart/form-data 支持文件上传
-- 响应格式：JSON
-
-## 主要接口
-
-1. `/web/ai-analysis/v2/start-common-ai-analysis` - 启动AI分析任务
-2. `/web/ai-analysis/v2/get-common-ai-analysis-result` - 获取分析结果
-3. `/web/ai-analysis/page-common-ai-analysis-result` - 分页查询历史报告
-4. `/ai/order/api/getReportDetailExport?id={id}` - 导出完整报告
-
-## 场景代码
-
-- `OPEN_FALL_DETECTION_VIDEO_ANALYSIS` - 开放平台跌倒检测视频分析

skills/18072937735/smyx-fall-detection-video-analysis/scripts/__init__.py

@@ -1 +0,0 @@
-# Pet Analysis scripts package

skills/18072937735/smyx-fall-detection-video-analysis/scripts/api_service.py

@@ -1,53 +0,0 @@
-#!/usr/bin/env python3
-
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-from skills.smyx_common.scripts.util import RequestUtil
-
-
-class ApiService(ApiServiceBase):
-
-    def __init__(self):
-        super().__init__()
-        self.analysis_url = ApiEnum.ANALYSIS_URL
-
-    def analysis_result(self, *args, **argss):
-        return self.http_post(ApiEnum.ANALYSIS_RESULT_URL, *args, **argss)
-
-    def analysis(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        options = {
-            "dataAsParams": True
-        }
-        # params.setdefault("scene", scene_code)
-        # 添加宠物类型参数
-        if ConstantEnum.DEFAULT__PET_TYPE:
-            params.setdefault("petType", ConstantEnum.DEFAULT__PET_TYPE)
-        return self.http_post(self.analysis_url, options=options, *args, **argss)
-
-    def page(self, pageNum=None, pageSize=None, *args, **argss):
-        data = argss.setdefault("data", {})
-        data.setdefault("orderBy", {
-            "fieldName": "createTime",
-            "isAsc": False
-        })
-        return super().page(ApiEnum.PAGE_URL, pageNum, pageSize, *args, **argss)
-
-    def list(self, *args, **argss):
-        return super().list(None, *args, **argss)
-
-    def add(self, item: dict):
-        return super().add(ApiEnum.ADD_URL, item)
-
-    def edit(self, item: dict):
-        return super().edit(ApiEnum.EDIT_URL, item)
-
-    def delete(self, cameraSn):
-        data = {
-            "cameraSn": cameraSn
-        }
-        return super().delete(ApiEnum.DELETE_URL, data, options={"dataAsParams": True})

skills/18072937735/smyx-fall-detection-video-analysis/scripts/config.py

@@ -1,24 +0,0 @@
-#!/usr/bin/env python3
-# 跌倒检测视频版工具配置文件
-import os
-import sys
-
-from enum import Enum
-
-from skills.smyx_common.scripts.config import ConstantEnum as ConstantEnumBase
-
-from skills.face_analysis.scripts.config import ApiEnum as ApiEnumParent, ConstantEnum as ConstantEnumParent, \
-    ApiEnumCommonAiMixin
-
-SceneCodeEnum = ConstantEnumBase.SceneCodeEnum
-
-
-class ApiEnum(ApiEnumCommonAiMixin, ApiEnumParent):
-    pass
-
-
-class ConstantEnum(ConstantEnumParent):
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-        ConstantEnumParent.DEFAULT__SCENE_CODE = SceneCodeEnum.FALL_DETECTION_VIDEO_ANALYSIS.value

skills/18072937735/smyx-fall-detection-video-analysis/scripts/config.yaml

@@ -1 +0,0 @@
-{}

skills/18072937735/smyx-fall-detection-video-analysis/scripts/fall_detection_video_analysis.py

@@ -1,97 +0,0 @@
-#!/usr/bin/env python3
-import sys
-import os
-
-current_dir = os.path.dirname(os.path.abspath(__file__))
-parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(current_dir)))
-sys.path.insert(0, parent_dir)
-
-import argparse
-import json
-import mimetypes
-import traceback
-from datetime import datetime
-
-import requests
-import sys
-import os
-
-from .config import *
-
-from .skill import skill
-
-from skills.smyx_common.scripts.util import RequestUtil
-
-
-def detect_fall(input_path=None, url=None, api_url=None, api_key=None, output_level=None):
-    input_path = input_path or url
-    return skill.get_output_analysis(input_path)
-
-
-def show_analyze_list(open_id, start_time=None, end_time=None):
-    output_content = skill.get_output_analysis_list()
-    return output_content
-
-
-def main():
-    parser = argparse.ArgumentParser(description="跌倒检测视频分析工具")
-    parser.add_argument("--input", help="本地视频文件路径")
-    parser.add_argument("--url", help="网络视频URL地址")
-    parser.add_argument("--open-id", required=True, help="当前用户的OpenID/UserId/用户名/手机号")
-    parser.add_argument("--list", action='store_true', help="显示跌倒检测视频分析列表清单")
-    parser.add_argument("--api-url", help="服务端API地址")
-    parser.add_argument("--api-key", help="API访问密钥（必需）")
-    parser.add_argument("--output", help="结果输出文件路径")
-    parser.add_argument("--detail", choices=["basic", "standard", "json"],
-                        default=ConstantEnum.DEFAULT__OUTPUT_LEVEL,
-                        help="输出详细程度")
-    parser.add_argument("--export-env-only", action='store_true',
-                        help="仅输出 export 命令设置环境变量，不执行分析")
-
-    args = parser.parse_args()
-
-    try:
-        if args.open_id:
-            # 设置 Python 进程内的环境变量
-            ConstantEnumBase.CURRENT__OPEN_ID = args.open_id
-
-        # 检查必需参数
-        if args.list:
-            open_id = ConstantEnum.CURRENT__OPEN_ID
-            result = show_analyze_list(open_id)
-            print(result)
-            exit(0)
-
-        # 检查必需参数
-        if not args.input and not args.url:
-            print("❌ 错误: 必须提供 --input 或 --url 参数")
-            exit(1)
-
-        print("🔍 正在检测跌倒，请稍候...")
-        output_content = detect_fall(
-            input_path=args.input,
-            url=args.url,
-            api_url=args.api_url,
-            api_key=args.api_key,
-            output_level=args.detail
-        )
-
-        print(output_content)
-
-        # 保存到文件
-        if args.output:
-            with open(args.output, "w", encoding="utf-8") as f:
-                if args.detail == "full":
-                    json.dump(result, f, ensure_ascii=False, indent=2)
-                else:
-                    f.write(output_content)
-            print(f"✅ 结果已保存到: {args.output}")
-
-    except Exception as e:
-        traceback.print_stack()
-        print(f"❌ 跌倒检测视频分析失败: {str(e)}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()

skills/18072937735/smyx-fall-detection-video-analysis/scripts/skill.py

@@ -1,23 +0,0 @@
-#!/usr/bin/env python3
-import json
-
-from .config import ApiEnum, ConstantEnum
-
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-from skills.face_analysis.scripts.skill import Skill as SkillParent
-from skills.smyx_common.scripts.util import JsonUtil
-
-
-class Skill(SkillParent):
-    def __init__(self):
-        super().__init__()
-
-    def get_output_analysis_content_head(self, result=None):
-        return f"📊 跌倒检测视频分析结构化结果"
-
-    def get_output_analysis_content_foot(self, result):
-        pass
-
-
-skill = Skill()

skills/18072937735/smyx-fall-detection-video-analysis/skills/face_analysis/README.md

@@ -1,86 +0,0 @@
-# 中医面诊分析工具 (face-analysis)
-
-## 技能介绍
-这是一个基于AI的中医面诊分析技能，可以通过面部视频自动分析健康状况，返回结构化的诊断结果和养生建议。
-
-## 快速开始
-### 1. 配置API信息
-编辑 `scripts/config.py`，设置你的API地址和密钥：
-```python
-DEFAULT_API_URL = "https://your-api-server.com/api/v1/face-analysis"
-DEFAULT_API_KEY = "your-api-key-here"
-```
-
-### 2. 分析本地视频
-```bash
-python scripts/face_analysis.py --input /path/to/your/video.mp4
-```
-
-### 3. 分析网络视频
-```bash
-python scripts/face_analysis.py --url https://example.com/video.mp4
-```
-
-## 功能特性
-- ✅ 支持本地MP4视频上传
-- ✅ 支持网络视频URL分析
-- ✅ 三种输出详细程度：精简/标准/完整
-- ✅ 结构化JSON结果输出
-- ✅ 自动保存结果到文件
-- ✅ 内置视频格式和大小校验
-
-## 目录结构
-```
-face-analysis/
-├── SKILL.md              # 技能说明文件（系统自动加载）
-├── README.md             # 本说明文件
-├── scripts/
-│   ├── face_analysis.py  # 主程序
-│   └── config.py         # 配置文件
-├── references/
-│   ├── api_doc.md        # API接口文档
-│   ├── tcm_theory.md     # 中医面诊理论参考
-│   └── faq.md            # 常见问题
-└── assets/
-    └── template.json     # 返回结果模板
-```
-
-## 使用示例
-### 标准输出
-```
-📊 中医面诊分析报告
-==================================================
-⏰ 分析时间: 2026-03-10 15:30:00
-🎯 人脸检测: success (置信度: 95分)
-
-🔍 诊断结果:
-  整体体质: 平和质
-  脏腑状况:
-    liver: 正常
-    heart: 轻微火旺
-    spleen: 略虚
-    lung: 正常
-    kidney: 正常
-  面色分析: 微黄
-  对应提示: 脾胃功能略弱
-
-⚠️ 健康警示:
-  ⚠️  注意休息，避免熬夜
-
-💡 养生建议:
-  💡 饮食清淡，减少辛辣食物摄入
-  💡 保持规律作息，每晚11点前入睡
-  💡 适当进行有氧运动，如散步、太极拳
-==================================================
-```
-
-### 输出到JSON文件
-```bash
-python scripts/face_analysis.py --input video.mp4 --detail full --output result.json
-```
-
-## 注意事项
-1. 视频要求：清晰正面面部，光线充足，时长5-30秒为宜
-2. 支持格式：mp4、avi、mov，最大100MB
-3. API需要自行部署或接入第三方服务
-4. 结果仅供参考，不能替代专业医生诊断

skills/18072937735/smyx-fall-detection-video-analysis/skills/face_analysis/references/api_doc.md

@@ -1,69 +0,0 @@
-# API接口文档
-
-## 接口地址
-`POST https://your-api-server.com/api/v1/face-analysis`
-
-## 请求头
-| 字段 | 必选 | 说明 |
-|------|------|------|
-| X-API-Key | 是 | API访问密钥 |
-| Content-Type | 是 | multipart/form-data（文件上传）或 application/json（URL模式） |
-
-## 请求参数
-### 1. 文件上传模式
-| 字段 | 类型 | 必选 | 说明 |
-|------|------|------|------|
-| video | file | 是 | MP4视频文件 |
-| detail_level | string | 否 | 输出详细程度：basic/standard/full，默认standard |
-
-### 2. URL模式
-| 字段 | 类型 | 必选 | 说明 |
-|------|------|------|------|
-| video_url | string | 是 | 可公开访问的视频URL |
-| detail_level | string | 否 | 输出详细程度：basic/standard/full，默认standard |
-
-## 响应格式
-```json
-{
-  "code": 200,
-  "message": "success",
-  "data": {
-    "analysis_time": "2026-03-10 15:30:00",
-    "face_detection": {
-      "status": "success",
-      "face_count": 1,
-      "quality_score": 95
-    },
-    "diagnosis": {
-      "overall_constitution": "平和质",
-      "organ_condition": {
-        "liver": "正常",
-        "heart": "轻微火旺",
-        "spleen": "略虚",
-        "lung": "正常",
-        "kidney": "正常"
-      },
-      "color_analysis": {
-        "complexion": "微黄",
-        "correspondence": "脾胃功能略弱"
-      }
-    },
-    "health_warnings": [
-      "注意休息，避免熬夜"
-    ],
-    "suggestions": [
-      "饮食清淡，减少辛辣食物摄入"
-    ]
-  }
-}
-```
-
-## 错误码说明
-| 错误码 | 说明 |
-|--------|------|
-| 400 | 请求参数错误 |
-| 401 | API密钥无效 |
-| 403 | 权限不足 |
-| 413 | 文件过大 |
-| 415 | 不支持的文件格式 |
-| 500 | 服务器内部错误 |

skills/18072937735/smyx-fall-detection-video-analysis/skills/face_analysis/requirements.txt

@@ -1,3 +0,0 @@
-pydash==8.0.6
-SQLAlchemy==2.0.46
-yaml==6.0.3

skills/18072937735/smyx-fall-detection-video-analysis/skills/face_analysis/scripts/api_service.py

@@ -1,52 +0,0 @@
-#!/usr/bin/env python3
-
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-
-class ApiService(ApiServiceBase):
-
-    def __init__(self):
-        super().__init__()
-        self.analysis_url = ApiEnum.ANALYSIS_URL
-
-    def analysis_result(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        scene_code and params.setdefault("sceneCode", scene_code)
-        return self.http_post(ApiEnum.ANALYSIS_RESULT_URL, *args, **argss)
-
-    def analysis(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        options = {
-            "dataAsParams": True
-        }
-        scene_code and params.setdefault("sceneCode", scene_code)
-        params.setdefault("appCategory", ConstantEnum.DEFAULT__APP_CATEGORY)
-        return self.http_post(self.analysis_url, options=options, *args, **argss)
-
-    def page(self, pageNum=None, pageSize=None, *args, **argss):
-        data = argss.setdefault("data", {})
-        ConstantEnum.DEFAULT__SCENE_CODE and data.setdefault("sceneCode", ConstantEnum.DEFAULT__SCENE_CODE)
-        data.setdefault("orderBy", {
-            "fieldName": "createTime",
-            "isAsc": False
-        })
-        return super().page(ApiEnum.PAGE_URL, pageNum, pageSize, *args, **argss)
-
-    def list(self, *args, **argss):
-        return super().list(None, *args, **argss)
-
-    def add(self, item: dict):
-        return super().add(ApiEnum.ADD_URL, item)
-
-    def edit(self, item: dict):
-        return super().edit(ApiEnum.EDIT_URL, item)
-
-    def delete(self, cameraSn):
-        data = {
-            "cameraSn": cameraSn
-        }
-        return super().delete(ApiEnum.DELETE_URL, data, options={"dataAsParams": True})

skills/18072937735/smyx-fall-detection-video-analysis/skills/face_analysis/scripts/config.py

@@ -1,40 +0,0 @@
-#!/usr/bin/env python3
-# 中医面诊分析工具配置文件
-import os
-import sys
-
-from enum import Enum
-
-from skills.smyx_common.scripts.config import ApiEnum as ApiEnumBase, ConstantEnum as ConstantEnumBase
-
-SceneCodeEnum = ConstantEnumBase.SceneCodeEnum
-
-
-class ApiEnum(ApiEnumBase):
-    ANALYSIS_URL = "/web/health-analysis/v2/start-health-analysis"
-
-    ANALYSIS_RESULT_URL = "/web/health-analysis/get-health-analysis-result"
-
-    PAGE_URL = "/web/health-analysis/page-health-analysis-result"
-
-    DETAIL_EXPORT_URL = ApiEnumBase.BASE_URL_HEALTH + "/health/order/api/getReportDetailExport?id="
-
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-
-
-class ApiEnumCommonAiMixin:
-
-    @classmethod
-    def init(cls, config=None):
-        parent = super()
-        if hasattr(parent, "init"):
-            parent.init(config)
-        ApiEnum.ANALYSIS_URL = "/web/ai-analysis/v2/start-common-ai-analysis"
-        ApiEnum.ANALYSIS_RESULT_URL = "/web/ai-analysis/get-common-ai-analysis-result"
-        ApiEnum.PAGE_URL = "/web/ai-analysis/page-common-ai-analysis-result"
-
-
-class ConstantEnum(ConstantEnumBase):
-    DEFAULT__APP_CATEGORY = "PEI_NI_AN"

skills/18072937735/smyx-fall-detection-video-analysis/skills/face_analysis/scripts/config.yaml

@@ -1 +0,0 @@
-{}

skills/18072937735/smyx-fall-detection-video-analysis/skills/face_analysis/scripts/face_analysis.py

@@ -1,205 +0,0 @@
-#!/usr/bin/env python3
-import sys
-import os
-
-current_dir = os.path.dirname(os.path.abspath(__file__))
-parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(current_dir)))
-sys.path.insert(0, parent_dir)
-
-import argparse
-import json
-import mimetypes
-import traceback
-from datetime import datetime
-
-import requests
-import sys
-import os
-
-from .config import *
-
-from .skill import skill
-
-# import_path_common()
-from skills.smyx_common.scripts.util import RequestUtil
-
-# 从config导入常量
-SUPPORTED_FORMATS = ConstantEnum.SUPPORTED_FORMATS
-MAX_FILE_SIZE_MB = ConstantEnum.MAX_FILE_SIZE_MB
-
-
-def validate_file(file_path):
-    """验证输入文件是否合法"""
-    if not os.path.exists(file_path):
-        raise FileNotFoundError(f"文件不存在: {file_path}")
-
-    if not os.access(file_path, os.R_OK):
-        raise PermissionError(f"文件没有读权限: {file_path}")
-
-    ext = os.path.splitext(file_path)[1].lower()[1:]
-    if ext not in SUPPORTED_FORMATS:
-        raise ValueError(f"不支持的文件格式，支持的格式: {', '.join(SUPPORTED_FORMATS)}")
-
-    file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
-    if file_size_mb > MAX_FILE_SIZE_MB:
-        raise ValueError(f"文件过大，最大支持 {MAX_FILE_SIZE_MB}MB，当前文件大小: {file_size_mb:.1f}MB")
-
-    return True
-
-
-def analyze_video(input_path=None, url=None, api_url=None, api_key=None, output_level=None):
-    """调用API分析视频"""
-    if not input_path and not url:
-        raise ValueError("必须提供本地视频路径(--input)或网络视频URL(--url)")
-    try:
-        input_path = input_path or url
-        return skill.get_output_analysis(input_path)
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def show_analyze_list(open_id, start_time=None, end_time=None):
-    # if not open_id:
-    #     raise ValueError("必须提供本用户的OpenId/UserId")
-
-    try:
-        output_content = skill.get_output_analysis_list()
-        return output_content
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def get_analysis_export_url(request_id=None):
-    """调用API分析视频"""
-    if not request_id:
-        return ""
-    return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-
-def format_result(result, output_level="standard"):
-    """格式化输出结果"""
-    if output_level == "json":
-        result_id = None
-        # if result.get('success'):
-        if result is not None:
-            result_json = result
-            result_id = result_json.get('id', {})
-            result_json = json.dumps(result_json.get('faceAnalysisResponse', {}), ensure_ascii=False, indent=2)
-        else:
-            # result_json = json.dumps(result, ensure_ascii=False, indent=2)
-            return "⚠️ 暂无分析结果"
-        return f"""
-📊 面诊分析结构化结果
-{result_json}
-""", result_id
-    elif output_level == "basic":
-        # 精简输出
-        data = result.get('data', {})
-        diagnosis = data.get('diagnosis', {})
-        return f"""
-📊 面诊分析结果
-{'=' * 40}
-整体体质: {diagnosis.get('overall_constitution', '未知')}
-主要状况: {', '.join([f'{k}: {v}' for k, v in diagnosis.get('organ_condition', {}).items() if v != '正常'])}
-健康提示: {data.get('health_warnings', ['无特殊警示'])[0] if data.get('health_warnings') else '无特殊警示'}
-        """
-    elif output_level == "standard":
-        # 标准输出
-        data = result.get('data', {})
-        diagnosis = data.get('diagnosis', {})
-        face_detection = data.get('face_detection', {})
-
-        organ_status = "\n".join([f"  {k}: {v}" for k, v in diagnosis.get('organ_condition', {}).items()])
-        warnings = "\n".join([f"  ⚠️  {item}" for item in data.get('health_warnings', [])])
-        suggestions = "\n".join([f"  💡 {item}" for item in data.get('suggestions', [])])
-
-        return f"""
-📊 中医面诊分析报告
-{'=' * 50}
-⏰ 分析时间: {data.get('analysis_time', '未知')}
-🎯 人脸检测: {face_detection.get('status', '未知')} (置信度: {face_detection.get('quality_score', 0)}分)
-
-🔍 诊断结果:
-  整体体质: {diagnosis.get('overall_constitution', '未知')}
-  脏腑状况:
-{organ_status}
-  面色分析: {diagnosis.get('color_analysis', {}).get('complexion', '未知')}
-  对应提示: {diagnosis.get('color_analysis', {}).get('correspondence', '未知')}
-
-⚠️ 健康警示:
-{warnings}
-
-💡 养生建议:
-{suggestions}
-{'=' * 50}
-        """
-    else:
-        # 完整输出（JSON格式）
-        return json.dumps(result, ensure_ascii=False, indent=2)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="中医面诊分析工具")
-    parser.add_argument("--input", help="本地MP4视频文件路径")
-    parser.add_argument("--url", help="网络视频MP4的URL地址")
-    parser.add_argument("--open-id", required=True, help="当前用户的OpenID/UserId/用户名/手机号")
-    parser.add_argument("--list", action='store_true', help="显示面诊视频历史列表清单")
-    parser.add_argument("--api-url", help="服务端API地址")
-    parser.add_argument("--api-key", help="API访问密钥（必需）")
-    parser.add_argument("--output", help="结果输出文件路径")
-    parser.add_argument("--detail", choices=["basic", "standard", "json"],
-                        default=ConstantEnum.DEFAULT__OUTPUT_LEVEL,
-                        help="输出详细程度")
-    parser.add_argument("--export-env-only", action='store_true',
-                        help="仅输出 export 命令设置环境变量，不执行分析")
-
-    args = parser.parse_args()
-
-    try:
-        if args.open_id:
-            ConstantEnumBase.CURRENT__OPEN_ID = args.open_id
-
-        # 检查必需参数
-        if args.list:
-            open_id = ConstantEnum.CURRENT__OPEN_ID
-            result = show_analyze_list(open_id)
-            print(result)
-            exit(0)
-
-        # 检查必需参数
-        if not args.input and not args.url:
-            print("❌ 错误: 必须提供 --input 或 --url 参数")
-            exit(1)
-
-        print("🔍 正在分析面诊视频，请稍候...")
-        output_content = analyze_video(
-            input_path=args.input,
-            url=args.url,
-            api_url=args.api_url,
-            api_key=args.api_key,
-            output_level=args.detail
-        )
-
-        print(output_content)
-
-        # 保存到文件
-        if args.output:
-            with open(args.output, "w", encoding="utf-8") as f:
-                if args.detail == "full":
-                    json.dump(result, f, ensure_ascii=False, indent=2)
-                else:
-                    f.write(output_content)
-            print(f"✅ 结果已保存到: {args.output}")
-
-    except Exception as e:
-        traceback.print_stack()
-        print(f"❌ 面诊分析失败: {str(e)}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()

skills/18072937735/smyx-fall-detection-video-analysis/skills/face_analysis/scripts/skill.py

@@ -1,267 +0,0 @@
-#!/usr/bin/env python3
-import datetime
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-
-from .api_service import ApiService
-
-from skills.smyx_common.scripts.util import CommonUtil, JsonUtil
-from skills.smyx_common.scripts.config import ApiEnum as ApiEnumBase
-from skills.smyx_common.scripts.base import BaseSkill
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-
-class Skill(BaseSkill, ApiService):
-    def __init__(self):
-        super().__init__()
-
-    def get_output_analysis_content_body(self, result=None):
-        result_json = result
-
-        result_json_pure_text = result_json.get("pureText")
-        if result_json_pure_text:
-            result_json = JsonUtil.parse(result_json_pure_text, result_json_pure_text)
-
-        result_json_common_ai_response = result_json.get("commonAiResponse")
-        if result_json_common_ai_response:
-            result_json = result_json_common_ai_response
-
-        result_json_health_ai_response = result_json.get("healthAiResponse")
-        if result_json_health_ai_response:
-            result_json = result_json_health_ai_response
-
-        result_json = JsonUtil.stringify(result_json, result_json)
-        return result_json
-
-    def get_output_analysis_content_head(self, result=None):
-        return f"📊 面诊分析结构化结果"
-
-    def get_output_analysis_content_foot(self, result):
-        result_id = result.get('id', {})
-        output_content_export_url = ApiEnum.DETAIL_EXPORT_URL + result_id
-        return f"🔗 获取报告导出图片链接: {output_content_export_url}"
-
-    def get_output_analysis_content(self, result):
-        if result is not None:
-            output_content = self.get_output_analysis_content_body(result) or ""
-            output_content_head = self.get_output_analysis_content_head(result)
-            output_content_foot = self.get_output_analysis_content_foot(result)
-            #       d
-            if output_content_head:
-                output_content = f"""
-{output_content_head}
-""" + output_content
-            if output_content_foot:
-                output_content += f"""
-{output_content_foot}
-"""
-        else:
-            output_content = "⚠️ 暂无分析结果"
-        return output_content
-
-    def get_output_analysis(self, input_path, params={}):
-        response = self.get_analysis(
-            input_path, params
-        )
-
-        def _analysis_result():
-            return self.analysis_result(
-                data=response
-            )
-
-        new_response = CommonUtil.polling(_analysis_result,
-                                          check_condition=lambda res: res.get('needPageRefresh') is False, interval=5,
-                                          max_attempts=24)
-
-        output_content = self.get_output_analysis_content(new_response)
-        return output_content
-
-    def get_analysis(self, input_path, params={}):
-        import mimetypes
-
-        def _validate_file(file_path):
-            """验证输入文件是否合法"""
-            if not os.path.exists(file_path):
-                raise FileNotFoundError(f"文件不存在: {file_path}")
-
-            if not os.access(file_path, os.R_OK):
-                raise PermissionError(f"文件没有读权限: {file_path}")
-
-            ext = os.path.splitext(file_path)[1].lower()[1:]
-            if ext not in ConstantEnum.SUPPORTED_FORMATS:
-                raise ValueError(f"不支持的文件格式，支持的格式: {', '.join(ConstantEnum.SUPPORTED_FORMATS)}")
-
-            file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
-            if file_size_mb > ConstantEnum.MAX_FILE_SIZE_MB:
-                raise ValueError(
-                    f"文件过大，最大支持 {ConstantEnum.MAX_FILE_SIZE_MB}MB，当前文件大小: {file_size_mb:.1f}MB")
-
-            return True
-
-        files = None
-
-        if not input_path:
-            raise ValueError("必须提供本地视频路径(--input)或网络视频URL(--url)")
-
-        if (input_path.startswith("http://") or input_path.startswith("https://")):
-            params.update({
-                "videoUrl": input_path
-            })
-        else:
-            _validate_file(input_path)
-
-            # 自动检测 MIME 类型
-            mime_type, _ = mimetypes.guess_type(input_path)
-            if mime_type is None:
-                mime_type = 'application/octet-stream'
-
-            # 读取文件内容
-            with open(input_path, 'rb') as f:
-                file_content = f.read()
-
-            # 构建 multipart/form-data 格式的请求
-            files = {
-                'file': (os.path.basename(input_path), file_content, mime_type)
-            }
-
-        response = self.analysis(
-            params=params,
-            files=files
-        )
-
-        return response
-
-    def get_output_analysis_list(self, pageNum=None, pageSize=None, *args, **argss):
-        """获取面诊报告清单
-        优化规则：只要API服务接口返回面诊报告清单，直接输出API返回的结果，
-        无需汇总上下文中的面诊分析报告，以接口返回为准
-        """
-
-        def _get_analysis_export_url(request_id=None):
-            if not request_id:
-                return ""
-            return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-        response = self.page(pageNum, pageSize, *args, **argss)
-
-        if response:
-            for item in response:
-                if item.get("commonAiResponse") or item.get("healthAiResponse"):
-                    item["reportImageUrl"] = _get_analysis_export_url(item.get("id"))
-
-        response_text = JsonUtil.stringify(response)
-
-        if response_text:
-            return f"""📊 分析报告记录列表(结构化结果)"
-{response_text}
-"""
-        else:
-            return "⚠️ 暂无分析报告记录"
-
-    def __get_output_analysis_list(self, pageNum=None, pageSize=None, *args, **argss):
-        """获取面诊报告清单
-        优化规则：只要API服务接口返回面诊报告清单，直接输出API返回的结果，
-        无需汇总上下文中的面诊分析报告，以接口返回为准
-        """
-
-        def _get_analysis_export_url(request_id=None):
-            if not request_id:
-                return ""
-            return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-        # open_id 仅用于本地识别，不传给API - 参数已经在argss中，page方法会正确处理
-        open_id = argss.pop('open_id', None)
-        # if not open_id:
-        #     return "⚠️ 错误：缺少 open_id 参数"
-
-        # 获取总页数，然后循环获取所有页
-        output_all = ""
-        # 先获取第一页来获取总页数
-        # page 方法在基类中已经处理过，我们需要兼容两种返回结果：
-        # 1. 完整响应：{"success": true, "data": {"records": [...], "total": ...}}
-        # 2. 已经提取好的数据：直接返回 data 对象或 records 列表
-        response = self.page(pageNum or 1, pageSize or 30, *args, **argss)
-
-        if response is None:
-            return "⚠️ 获取报告列表失败：response is None"
-
-        # 兼容处理：不同版本的基类返回不同格式
-        if isinstance(response, list):
-            # 基类直接返回了 records 列表，无法获取分页信息，直接使用
-            records = response
-            total = len(records)
-            pages = 1
-        elif isinstance(response, dict):
-            # 完整响应格式
-            if not response.get('success'):
-                error_msg = response.get('errorMsg', '未知错误')
-                return f"⚠️ 获取报告列表失败：{error_msg}"
-            data = response.get('data', {})
-            if not data or not isinstance(data, dict):
-                return "⚠️ 获取报告列表失败：数据格式错误"
-            total = data.get('total', 0)
-            pages = data.get('pages', 1)
-            records = data.get('records', [])
-        else:
-            return f"⚠️ 获取报告列表失败：response type={type(response)}"
-
-        if not records:
-            return "⚠️ 暂无面诊分析报告记录"
-
-        output_all = f"📋 历史面诊分析报告清单（共 {total} 份）\n\n"
-        output_all += "| 报告名称 | 分析时间 | 体质判断 | 点击查看 |\n"
-        output_all += "|----------|----------|----------|----------|\n"
-
-        # 处理第一页
-        for item in records:
-            if not isinstance(item, dict):
-                continue
-            report_id = item.get('id', '')
-            create_time = item.get('createTimeString', '未知时间')
-            # 提取体质判断 - 优先从 healthAiResponse 获取，如果没有再从 faceAnalysisResponse 获取
-            health_ai = item.get('healthAiResponse', {}) or {}
-            if health_ai:
-                health_assessment = health_ai.get('healthAssessment', {}) or {}
-                subject = health_assessment.get('subject', '未知')
-            else:
-                face_ai = item.get('faceAnalysisResponse', {}) or {}
-                health_assessment = face_ai.get('healthAssessment', {}) or {}
-                subject = health_assessment.get('subject', '未知')
-            report_name = f"面诊分析报告-{report_id}"
-            report_url = _get_analysis_export_url(report_id)
-            output_all += f"| {report_name} | {create_time} | {subject} | [🔗 查看报告]({report_url}) |\n"
-
-        # 处理剩余页
-        for current_page in range(2, pages + 1):
-            response = self.page(current_page, 30, *args, **argss)
-            if not response or not isinstance(response, dict) or not response.get('success'):
-                continue
-            data = response.get('data', {})
-            if not data or not isinstance(data, dict):
-                continue
-            records = data.get('records', [])
-            for item in records:
-                if not isinstance(item, dict):
-                    continue
-                report_id = item.get('id', '')
-                create_time = item.get('createTimeString', '未知时间')
-                # 提取体质判断 - 优先从 healthAiResponse 获取，如果没有再从 faceAnalysisResponse 获取
-                health_ai = item.get('healthAiResponse', {}) or {}
-                if health_ai:
-                    health_assessment = health_ai.get('healthAssessment', {}) or {}
-                    subject = health_assessment.get('subject', '未知')
-                else:
-                    face_ai = item.get('faceAnalysisResponse', {}) or {}
-                    health_assessment = face_ai.get('healthAssessment', {}) or {}
-                    subject = health_assessment.get('subject', '未知')
-                report_name = f"面诊分析报告-{report_id}"
-                report_url = _get_analysis_export_url(report_id)
-                output_all += f"| {report_name} | {create_time} | {subject} | [🔗 查看报告]({report_url}) |\n"
-
-        output_all += "\n> 注：面诊分析结果仅供健康参考，不能替代专业医疗诊断。"
-        return output_all
-
-
-skill = Skill()

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/requirements.txt

@@ -1,127 +0,0 @@
-altgraph==0.17.5
-annotated-doc==0.0.4
-annotated-types==0.7.0
-anyio==4.12.1
-APScheduler==3.11.2
-astroid==3.1.0
-Authlib==1.6.6
-blinker==1.4
-cachetools==6.2.6
-certifi==2026.1.4
-cffi==2.0.0
-chardet==5.2.0
-charset-normalizer==3.4.4
-click==8.3.1
-coverage==7.13.2
-coze-workload-identity==0.1.7
-cozeloop==0.1.19
-cryptography==3.4.8
-Cython==3.2.4
-dbus-python==1.2.18
-dill==0.4.1
-distro==1.7.0
-distro-info==1.1+ubuntu0.2
-et_xmlfile==2.0.0
-fastapi==0.121.2
-gitdb==4.0.12
-gitignore_parser==0.1.13
-GitPython==3.1.45
-greenlet==3.3.1
-h11==0.16.0
-httpcore==1.0.9
-httplib2==0.20.2
-httpx==0.28.1
-httpx-ws==0.8.2
-idna==3.11
-importlib-metadata==4.6.4
-inflect==7.5.0
-iniconfig==2.3.0
-isort==5.13.2
-jeepney==0.7.1
-Jinja2==3.1.6
-jiter==0.12.0
-jsonpatch==1.33
-jsonpointer==3.0.0
-keyring==23.5.0
-langchain==1.0.3
-langchain-core==1.0.2
-langchain-openai==1.0.1
-langgraph==1.0.2
-langgraph-checkpoint==3.0.0
-langgraph-prebuilt==1.0.2
-langgraph-sdk==0.2.9
-langsmith==0.4.39
-launchpadlib==1.10.16
-lazr.restfulclient==0.14.4
-lazr.uri==1.0.6
-markdown-it-py==4.0.0
-MarkupSafe==3.0.3
-mccabe==0.7.0
-mdurl==0.1.2
-more-itertools==8.10.0
-numpy==2.4.1
-oauthlib==3.2.0
-openai==2.16.0
-openpyxl==3.1.5
-orjson==3.11.5
-ormsgpack==1.12.2
-packaging==25.0
-pandas==2.3.3
-platformdirs==4.5.1
-pluggy==1.6.0
-psutil==7.1.3
-psycopg2-binary==2.9.11
-pycparser==3.0
-pydantic==2.12.4
-pydantic_core==2.41.5
-pydash==8.0.6
-Pygments==2.19.2
-PyGObject==3.42.1
-pyinstaller==6.18.0
-pyinstaller-hooks-contrib==2026.0
-PyJWT==2.10.1
-pylint==3.1.0
-PyMySQL==1.1.2
-pyparsing==2.4.7
-pytest==9.0.1
-pytest-asyncio==1.3.0
-pytest-cov==7.0.0
-pytest-mock==3.15.1
-python-apt==2.4.0+ubuntu4.1
-python-dateutil==2.9.0.post0
-pytz==2025.2
-PyYAML==6.0.3
-regex==2026.1.15
-requests==2.32.5
-requests-toolbelt==1.0.0
-rich==14.2.0
-SecretStorage==3.3.1
-setuptools==80.9.0
-six==1.16.0
-smmap==5.0.2
-sniffio==1.3.1
-sqlacodegen==3.2.0
-SQLAlchemy==2.0.46
-starlette==0.49.3
-supervisor==4.2.1
-tenacity==9.1.2
-tiktoken==0.12.0
-tomlkit==0.14.0
-tqdm==4.67.1
-typeguard==4.4.4
-typing-inspection==0.4.2
-typing_extensions==4.15.0
-tzdata==2025.3
-tzlocal==5.3.1
-unattended-upgrades==0.1
-urllib3==2.6.3
-uvicorn==0.38.0
-wadllib==1.3.6
-watchdog==6.0.0
-websockets==15.0.1
-wheel==0.45.1
-wsproto==1.3.2
-xlrd==2.0.2
-xxhash==3.6.0
-zipp==1.0.0
-zstandard==0.25.0

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/__init__.py

@@ -1,8 +0,0 @@
-from .util import RequestUtil, CommonUtil, DatetimeUtil
-from .base import *
-
-__all__ = [
-    'RequestUtil',
-    'CommonUtil',
-    'BaseUtil'
-]

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/api_service.py

@@ -1,96 +0,0 @@
-#!/usr/bin/env python3
-
-from .config import ApiEnum
-
-from .base import BaseApiService
-from .util import RequestUtil, CommonUtil
-
-
-class ApiService(BaseApiService):
-
-    def __init__(self):
-        super().__init__()
-
-    def get_download_url(self, tosKey, expireSeconds=3600):
-        return RequestUtil.http_post(
-            ApiEnum.GET_DOWNLOAD_URL__URL,
-            params={
-                "tosKey": tosKey,
-                "expireSeconds": expireSeconds * 24
-            }
-        )
-
-    def page(self, url, pageNum=None, pageSize=None, *args, **argss):
-        data = args[0] if len(args) > 0 else argss.get('data') if argss.get('data') is not None else {}
-        if pageNum is None:
-            pageNum = 1
-        if pageSize is None:
-            pageSize = ApiEnum.DEFAULT__PAGE_SIZE
-        paramsPage = {
-            'pageNum': int(pageNum),
-            'pageSize': int(pageSize)
-        }
-        data.update({
-            "page": paramsPage
-        })
-        if not CommonUtil.is_empty(data):
-            if (len(args) == 0):
-                argss.setdefault("data", data)
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def list(self, url=None, *args, **argss):
-        if url is not None:
-            argss["url"] = url
-        return self.page(1, ApiEnum.DEFAULT__PAGE_SIZE_MAX, *args, **argss)
-
-    def add(self, url=None, *args, **argss):
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def edit(self, url=None, *args, **argss):
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def delete(self, url=None, *args, **argss):
-        response = RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-        return response
-
-    def http_post(self, url=None, *args, **argss):
-        return RequestUtil.http_post(
-            url,
-            *args, **argss
-        )
-
-    def http_put(self, url=None, *args, **argss):
-        return RequestUtil.http_put(
-            url,
-            *args, **argss
-        )
-
-    def http_get(self, url=None, *args, **argss):
-        return RequestUtil.http_get(
-            url,
-            *args, **argss
-        )
-
-        return response
-
-    def http_delete(self, url=None, *args, **argss):
-        return RequestUtil.http_delete(
-            url,
-            *args, **argss
-        )
-        return response

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/base.py

@@ -1,33 +0,0 @@
-class BaseUtil:
-    pass
-
-
-class BaseMixin:
-    pass
-
-
-class BaseDao:
-    pass
-
-
-class BaseService:
-    def __init__(self):
-        super().__init__()
-
-
-class BaseApiService(BaseService):
-    INSTANCE = None
-
-    def __init__(self):
-        super().__init__()
-
-    @classmethod
-    def get_instance(cls):
-        if cls.INSTANCE is None:
-            cls.INSTANCE = cls()
-        return cls.INSTANCE
-
-
-class BaseSkill:
-    def __init__(self):
-        super().__init__()

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/config-dev.yaml

@@ -1,7 +0,0 @@
-ApiEnum:
-  base-url-open-api: "http://192.168.1.234:9601/smyx-open-api"
-  base-url-open-h5: "http://192.168.1.234:4100"
-  base-url-health: "http://192.168.1.234:8080/jeecg-boot"
-
-ConstantEnum:
-  is-debug: true

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/config-test.yaml

@@ -1,7 +0,0 @@
-ApiEnum:
-  base-url-open-api: "https://livemonitortest.lifeemergence.com/smyx-open-api"
-  base-url-open-h5: "http://livemonitortest.lifeemergence.com"
-  base-url-health: "https://healthtest.lifeemergence.com/jeecg-boot"
-
-ConstantEnum:
-  is-debug: true

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/config.py

@@ -1,240 +0,0 @@
-#!/usr/bin/env python3
-import os
-import sys
-from enum import Enum
-from typing import Dict
-import inspect
-
-import yaml
-import platform
-
-
-class YamlUtil:
-
-    @staticmethod
-    def load(path, config: Dict = {}) -> Dict:
-        try:
-            if not os.path.exists(path):
-                os.makedirs(os.path.dirname(path), exist_ok=True)
-                with open(path, "w", encoding="utf-8") as f:
-                    yaml.dump(config, f, default_flow_style=False, allow_unicode=True)
-                return config
-            with open(path, "r", encoding="utf-8") as f:
-                config = yaml.safe_load(f) or {}
-                for key, value in config.items():
-                    if key not in config:
-                        config[key] = value
-                return config
-        except:
-            pass
-        return config
-
-    @staticmethod
-    def save(path, config: Dict) -> Dict:
-        try:
-            with open(path, "w", encoding="utf-8") as f:
-                yaml.dump(config, f, default_flow_style=False, allow_unicode=True)
-        except:
-            pass
-        return config
-
-
-class BaseEnum:
-
-    def __init_subclass__(cls, **kwargs):
-        super().__init_subclass__(**kwargs)
-        clsModule = cls.__module__
-        cls_path = inspect.getfile(cls)
-        clsFullName = f"{cls.__module__}.{cls.__name__}"
-        cls_dirpath = os.path.dirname(cls_path)  # .../src
-        clsModulePath = clsModule.replace(".", "\\")
-        current_dir = os.path.dirname(os.path.abspath(__file__))  # .../src
-        config_path = os.path.join(cls_dirpath, "config.yaml")
-        config = YamlUtil.load(config_path)
-        cls.init(config)
-        env = config.get("env")
-        if env:
-            env_config_path = os.path.join(cls_dirpath, f"config-{env}.yaml")
-            env_config = YamlUtil.load(env_config_path)
-            cls.init(env_config)
-
-    @classmethod
-    def init(cls, config=None):
-        clsName = cls.__name__
-        clsConfig = config and config.get(clsName)
-        if clsConfig:
-            for config_key, config_value in clsConfig.items():
-                new_config_key = config_key = config_key.upper().replace("-", "_")
-                if hasattr(cls, new_config_key):
-                    setattr(cls, new_config_key, config_value)
-
-
-class ApiEnum(BaseEnum):
-    API_KEY = None
-
-    API_SECRET_KEY = None
-
-    DATABASE_URL = ""
-
-    BASE_URL_OPEN_API = ""
-
-    BASE_URL_OPEN_H5 = ""
-
-    BASE_URL_HEALTH = ""
-
-    OPEN_TOKEN = ""
-
-    TOKEN = ""
-
-    DEFAULT__REQUEST_TIMEOUT = 120
-
-    DEFAULT__PAGE_SIZE = 5
-
-    DEFAULT__PAGE_SIZE_MAX = 65536
-
-    GET_DOWNLOAD_URL__URL = BASE_URL_OPEN_API + "/api/tos/get-download-url"
-
-
-class ConstantEnum(BaseEnum):
-    class SourceEnum(Enum):
-        ARK_CLAW = "ARK_CLAW"
-        JVS_CLAW = "JVS_CLAW"
-        LIGHT_CLAW = "LIGHT_CLAW"
-        WUHONG = "WUHONG"
-        COZE = "COZE"
-        SKILL_HUB = "SKILL_HUB"
-        CLAW_HUB = "CLAW_HUB"
-        FEISHU = "FEISHU"
-        DINGTALK = "DINGTALK"
-        WEIXIN = "WEIXIN"
-        YUANBAO = "YUANBAO"
-        WECOM = "WECOM"
-        QQBOT = "QQBOT"
-
-    APP__ID = ""
-
-    APP__SOURCE = SourceEnum.CLAW_HUB.value
-
-    IS_DEBUG = False
-
-    CURRENT__OPEN_ID = ""
-
-    CURRENT__USER_NAME = ""
-
-    CURRENT__TENTANT_CODE = ""
-
-    FEISHU_APP__ID = ""
-
-    FEISHU_APP__SECRET = ""
-
-    FEISHU_APP__RECEIVE_ID = ""
-
-    DEFAULT__SCENE_CODE = ""
-
-    DEFAULT__SKILL_HUB_NAME = APP__SOURCE
-
-    DEFAULT__SKILL_PLATFORM_NAME = ""
-
-    DEFAULT__OUTPUT_LEVEL = "json"
-
-    SUPPORTED_FORMATS = ["mp4", "avi", "mov"]
-
-    MAX_FILE_SIZE_MB = 10
-
-    @staticmethod
-    def is_debug():
-        return platform.system() != 'Linux' and ConstantEnum.IS_DEBUG
-
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-        openclaw_sender_open_id = os.environ.get("OPENCLAW_SENDER_OPEN_ID")
-        openclaw_sender_username = os.environ.get("OPENCLAW_SENDER_USERNAME")
-        feishu_open_id = os.environ.get("FEISHU_OPEN_ID")
-        if openclaw_sender_open_id:
-            cls.CURRENT__OPEN_ID = openclaw_sender_open_id
-        if openclaw_sender_username:
-            cls.CURRENT__USER_NAME = openclaw_sender_username
-        if feishu_open_id:
-            cls.FEISHU_APP__RECEIVE_ID = feishu_open_id
-
-    class SceneCodeEnum(Enum):
-        # 开放 #
-        OPEN_HEALTH_AI_ANALYSIS = "OPEN_HEALTH_AI_ANALYSIS"
-        OPEN_PERSON_RISK_ANALYSIS = "OPEN_PERSON_RISK_ANALYSIS"
-        # 智眸 #
-        PUBLIC_AREA_AI_ANALYSIS = "PUBLIC_AREA_AI_ANALYSIS"
-        PERSONNEL_LEAVE_POST_MONITORING = "PERSONNEL_LEAVE_POST_MONITORING"
-        CRAWL_MONITOR = "CRAWL_MONITOR"
-        # 陪你安 #
-        PEI_NI_AN_DEFAULT = "PEI_NI_AN_DEFAULT"
-        PET_ANALYSIS = "PET_ANALYSIS"
-        CRAWL_ANALYSIS = "CRAWL_ANALYSIS"
-        AQUARIUM_ANALYSIS = "AQUARIUM_ANALYSIS"
-        PSYCHOLOGY_ANALYSIS = "PSYCHOLOGY_ANALYSIS"
-        AUTISM_ANALYSIS = "AUTISM_ANALYSIS"
-        DIET_ANALYSIS = "DIET_ANALYSIS"
-        DRIVE_ANALYSIS = "DRIVE_ANALYSIS"
-        SPORT_ANALYSIS = "SPORT_ANALYSIS"
-        EMOTION_ANALYSIS = "EMOTION_ANALYSIS"
-        STUDY_ANALYSIS = "STUDY_ANALYSIS"
-        INFANT_SAFETY_MONITORING_ANALYSIS = "INFANT_SAFETY_MONITORING"
-        PHONE_USAGE_MONITORING_ANALYSIS = "PHONE_USAGE_MONITORING"
-        INCONTINENCE_ALERT_ANALYSIS = "INCONTINENCE_ALERT"
-        RESPIRATORY_SYMPTOM_RECOGNITION_ANALYSIS = "RESPIRATORY_SYMPTOM_RECOGNITION"
-        ELECTRIC_VEHICLE_DETECTION_ANALYSIS = "ELECTRIC_VEHICLE_DETECTION"
-        SMOKING_DETECTION_ANALYSIS = "SMOKING_DETECTION"
-        PET_DETECTION_FEEDER_ANALYSIS = "PET_DETECTION_FEEDER"
-        PET_HEALTH_MONITORING_ANALYSIS = "PET_HEALTH_MONITORING"
-        STROKE_RISK_SCREENING_ANALYSIS = "STROKE_RISK_SCREENING"
-        HUMAN_DETECTION_ANALYSIS = "HUMAN_DETECTION"
-        STRANGER_RECOGNITION_ANALYSIS = "STRANGER_RECOGNITION"
-        FOCUS_ANALYSIS_ANALYSIS = "FOCUS_ANALYSIS"
-        HUMAN_POSTURE_RECOGNITION_ANALYSIS = "HUMAN_POSTURE_RECOGNITION"
-        HUMAN_EMOTION_RECOGNITION_ANALYSIS = "HUMAN_EMOTION_RECOGNITION"
-        FIRE_SMOKE_DETECTION_ANALYSIS = "FIRE_SMOKE_DETECTION"
-        BASIC_OBJECT_DETECTION_ANALYSIS = "BASIC_OBJECT_DETECTION"
-        CHILD_DANGEROUS_BEHAVIOR_RECOGNITION_ANALYSIS = "CHILD_DANGEROUS_BEHAVIOR_RECOGNITION"
-        PET_RESTRICTED_AREA_WARNING_ANALYSIS = "PET_RESTRICTED_AREA_WARNING"
-        SLEEP_QUALITY_ANALYSIS_ANALYSIS = "SLEEP_QUALITY_ANALYSIS"
-        PET_DETECTION_ANALYSIS = "PET_DETECTION"
-        PSYCHOLOGICAL_STRESS_ASSESSMENT_ANALYSIS = "PSYCHOLOGICAL_STRESS_ASSESSMENT"
-        VISUAL_QA_ANALYSIS = "VISUAL_QA"
-        PET_BODY_HEALTH_ANALYSIS = "PET_BODY_HEALTH_ANALYSIS"
-        PET_BEHAVIOR_DETECTION_ANALYSIS = "PET_BEHAVIOR_DETECTION"
-        INFANT_SUFFOCATION_WARNING_ANALYSIS = "INFANT_SUFFOCATION_WARNING"
-        STRANGER_APPROACH_WARNING_ANALYSIS = "STRANGER_APPROACH_WARNING"
-        IMAGE_QUALITY_DETECTION_ANALYSIS = "IMAGE_QUALITY_DETECTION"
-        CHILD_EMOTION_RECOGNITION_ANALYSIS = "CHILD_EMOTION_RECOGNITION"
-        OUTDOOR_MONITORING_ANALYSIS = "OUTDOOR_MONITORING"
-        FALL_DETECTION_IMAGE_ANALYSIS = "FALL_DETECTION_IMAGE"
-        CUSTOM_TIMELAPSE_ANALYSIS = "CUSTOM_TIMELAPSE"
-        CONTACTLESS_VITAL_SIGNS_MONITORING_ANALYSIS = "CONTACTLESS_VITAL_SIGNS_MONITORING"
-        VIDEO_SEARCH_ANALYSIS = "VIDEO_SEARCH"
-        FAMILIAR_PERSON_RECOGNITION_ANALYSIS = "FAMILIAR_PERSON_RECOGNITION"
-        TCM_CONSTITUTION_RECOGNITION_ANALYSIS = "TCM_CONSTITUTION_RECOGNITION"
-        CONTACTLESS_HEALTH_RISK_DETECTION_ANALYSIS = "CONTACTLESS_HEALTH_RISK_DETECTION"
-        UNACCOMPANIED_MONITORING_ANALYSIS = "UNACCOMPANIED_MONITORING"
-        ELDERLY_FALL_DETECTION_ANALYSIS = "ELDERLY_FALL_DETECTION"
-        PARKINSON_EPILEPSY_BEHAVIOR_RECOGNITION_ANALYSIS = "PARKINSON_EPILEPSY_BEHAVIOR_RECOGNITION"
-        PET_BREED_INDIVIDUAL_RECOGNITION_ANALYSIS = "PET_BREED_INDIVIDUAL_RECOGNITION"
-        ELDERLY_BED_EXIT_WANDERING_MONITORING_ANALYSIS = "ELDERLY_BED_EXIT_WANDERING_MONITORING"
-        ARRHYTHMIA_EARLY_WARNING_ANALYSIS = "ARRHYTHMIA_EARLY_WARNING"
-        FIRE_DETECTION_ANALYSIS = "FIRE_DETECTION"
-        VISUAL_SUMMARY_ANALYSIS = "VISUAL_SUMMARY"
-        PACKAGE_DETECTION_ANALYSIS = "PACKAGE_DETECTION"
-        INFANT_BLANKET_KICK_MONITORING_ANALYSIS = "INFANT_BLANKET_KICK_MONITORING"
-        PET_CALMING_TRIGGER_ANALYSIS = "PET_CALMING_TRIGGER"
-        CAT_FACE_RECOGNITION_ANALYSIS = "CAT_FACE_RECOGNITION"
-        INFANT_SLEEP_MONITORING_ANALYSIS = "INFANT_SLEEP_MONITORING"
-        VIRTUAL_FENCE_INTRUSION_WARNING_ANALYSIS = "VIRTUAL_FENCE_INTRUSION_WARNING"
-        FALL_DETECTION_VIDEO_ANALYSIS = "FALL_DETECTION_VIDEO"
-        INFANT_CRY_ANALYSIS = "INFANT_CRY_ANALYSIS"
-        PET_VOCAL_EMOTION_ANALYSIS = "PET_VOCAL_EMOTION_ANALYSIS"
-        BIRD_RECOGNITION_ANALYSIS = "BIRD_RECOGNITION"
-        FRAUD_CALL_IDENTIFICATION = "FRAUD_CALL_IDENTIFICATION"
-        PLANT_SPECIES_RECOGNITION = "PLANT_SPECIES_RECOGNITION"
-        PLANT_GROWTH_STAGE_RECOGNITION = "PLANT_GROWTH_STAGE_RECOGNITION"
-        PLANT_DISEASE_RECOGNITION = "PLANT_DISEASE_RECOGNITION"
-        PLANT_NUTRITION_DIAGNOSIS = "PLANT_NUTRITION_DIAGNOSIS"
-        PLANT_WILTING_MONITORING = "PLANT_WILTING_MONITORING"

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/config.yaml

@@ -1,18 +0,0 @@
-env: prod
-
-ApiEnum:
-  api-key:
-  api-secret-key:
-  database-url:
-  base-url-open-api: "https://open.lifeemergence.com/smyx-open-api"
-  base-url-open-h5: "http://livemonitor.lifeemergence.com"
-  base-url-health: "https://lifeemergence.com/jeecg-boot"
-
-ConstantEnum:
-  is-debug: false
-  app--id: x1a3s4nwy1s2r4se
-  current--tentant-code: "PEI_NI_AN"
-  feishu-app--id: cli_a93d769369badcb1
-  feishu-app--secret:
-  default--skill-platform-name: ARK_CLAW
-#  default--scene-code: PEI_NI_AN_DEFAULT

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/dao.py

@@ -1,348 +0,0 @@
-#!/usr/bin/env python3
-"""
-本地化轻量级数据库封装
-使用SQLite + SQLAlchemy ORM
-支持基础CRUD操作，通过继承BaseDao快速实现各表的Dao层
-"""
-import datetime
-import sys
-from enum import Enum
-from typing import Any, Dict, List, Optional, Type, TypeVar
-from sqlalchemy import create_engine, Column, Integer, String, DateTime, func, Select, Table, MetaData, select, or_
-from sqlalchemy.orm import declarative_base
-from sqlalchemy.orm import sessionmaker, Session
-from sqlalchemy.sql.expression import text
-
-from skills.smyx_common.scripts.config import ConstantEnum, ApiEnum
-
-from skills.smyx_common.scripts.util import StringUtil, DatetimeUtil, FileUtil
-
-from skills.smyx_common.scripts.base import BaseMixin, BaseDao
-
-# 基础模型类
-Base = declarative_base()
-
-# 泛型类型，用于返回对应模型实例
-T = TypeVar('T', bound=Base)
-
-meta = MetaData()
-
-DATABASE_URL = ApiEnum.DATABASE_URL
-
-
-class BaseModelMixin(BaseMixin):
-
-    @classmethod
-    def load(cls, source: dict):
-        """
-        获取源枚举
-        :param source: 源
-        :return: User
-        """
-        column_names = cls.__table__.columns.keys()
-        user_dict = {k: source.get(StringUtil.snake_to_camel(k)) for k in column_names}
-        user_dict["create_time"] = DatetimeUtil.parse(user_dict["create_time"])
-        user_dict["update_time"] = DatetimeUtil.parse(user_dict["update_time"])
-        model = cls(**user_dict)
-        return model
-
-
-class Dao(BaseDao):
-    """
-    基础Dao类，提供通用的CRUD操作
-    子类只需配置__model__和__tablename__即可使用
-    """
-    __model__: Type[T] = None  # 对应的模型类，子类必须配置
-    __tablename__: str = None  # 表名，子类必须配置
-
-    def get_db_path(self, db_path):
-        import os
-
-        cwd = os.getcwd()
-        workspace = os.path.dirname(cwd)
-        workspace = os.path.dirname(workspace)
-        workspace = os.environ.get('OPENCLAW_WORKSPACE', workspace)
-        parent_dir = os.path.join(workspace, "data")
-        FileUtil.mkdir(parent_dir)
-        db_path = os.path.join(parent_dir, db_path)
-
-        return db_path
-
-    def __init__(self, db_path: str = None):
-        """
-        初始化Dao
-        :param db_path: SQLite数据库文件路径
-        """
-
-        if not db_path:
-            db_path = "smyx-common-claw.db"
-            db_path = self.get_db_path(db_path)
-
-        self.engine = create_engine(f"sqlite:///{db_path}", echo=False)
-
-        # 创建会话工厂
-        self.SessionLocal = sessionmaker(autocommit=False, autoflush=False, bind=self.engine)
-        # 初始化表结构
-        self._create_tables()
-        self._alter_tables()
-
-    def _create_tables(self) -> None:
-        """创建所有表结构"""
-        Base.metadata.create_all(bind=self.engine)
-
-    def _alter_tables(self) -> None:
-        """创建所有表结构"""
-        sql_statement = "ALTER TABLE sys_user ADD COLUMN source_id INT;"
-
-        # 3. 执行语句
-        try:
-            with self.engine.connect() as connection:
-                connection.execute(text(sql_statement))
-                connection.commit()  # 对于数据定义语言(DDL)，需要显式提交
-        except Exception as e:
-            connection.rollback()
-            if len(e.args) and "duplicate column name" in e.args[0]:
-                pass
-            else:
-                raise
-
-    def get_session(self) -> Session:
-        """获取数据库会话"""
-        return self.SessionLocal()
-
-    def save(self, model) -> T:
-        """
-        创建新记录
-        :param kwargs: 字段键值对
-        :return: 创建的模型实例
-        """
-
-        try:
-            return self.add(
-                model
-            )
-
-        except Exception as e:
-            return self.update(
-                model
-            )
-
-    def add(self, model) -> T:
-        """
-        创建新记录
-        :param kwargs: 字段键值对
-        :return: 创建的模型实例
-        """
-        session = self.get_session()
-        try:
-            session.add(model)
-            session.commit()
-            session.refresh(model)
-            return model
-        finally:
-            session.close()
-
-    def create(self, **kwargs) -> T:
-        """
-        创建新记录
-        :param kwargs: 字段键值对
-        :return: 创建的模型实例
-        """
-        instance = self.__model__(**kwargs)
-        return self.add(instance)
-
-    def get_by_id(self, record_id: int) -> Optional[T]:
-        """
-        根据ID查询记录
-        :param record_id: 记录ID
-        :return: 模型实例或None
-        """
-        session = self.get_session()
-        try:
-            return session.query(self.__model__).filter(self.__model__.id == record_id).first()
-        finally:
-            session.close()
-
-    def get_by_username(self, username: str) -> Optional[T]:
-        """
-        根据ID查询记录
-        :param record_id: 记录ID
-        :return: 模型实例或None
-        """
-        session = self.get_session()
-        try:
-            or_(
-                self.__model__.del_flag == 0,
-                self.__model__.del_flag.is_(None)  # 关键：使用 .is_(None) 来判断 SQL 的 NULL
-            )
-            return session.query(self.__model__).filter(self.__model__.username == username,
-                                                        or_(
-                                                            self.__model__.del_flag == 0,
-                                                            self.__model__.del_flag.is_(None)
-                                                            # 关键：使用 .is_(None) 来判断 SQL 的 NULL
-                                                        )).first()
-        finally:
-            session.close()
-
-    def list(self, filters: Optional[Dict[str, Any]] = None, limit: Optional[int] = None,
-             offset: Optional[int] = None) -> List[T]:
-        """
-        查询记录列表
-        :param filters: 过滤条件字典，如{"name": "张三", "age": 18}
-        :param limit: 最大返回数量
-        :param offset: 偏移量
-        :return: 模型实例列表
-        """
-        session = self.get_session()
-        try:
-            query = session.query(self.__model__)
-            # .where(self.__model__.id != 2, self.__model__.id == 1))
-
-            if filters:
-                for key, value in filters.items():
-                    query = query.filter(getattr(self.__model__, key) == value)
-
-            if offset:
-                query = query.offset(offset)
-            if limit:
-                query = query.limit(limit)
-
-            return query.all()
-        finally:
-            session.close()
-
-    def update(self, model) -> Optional[T]:
-        """
-        更新记录
-        :param record_id: 记录ID
-        :param kwargs: 要更新的字段键值对
-        :return: 更新后的模型实例或None
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.id == model.id).first()
-            if not instance:
-                return None
-
-            column_names = self.__model__.__table__.columns.keys()
-
-            for key in column_names:
-                value = getattr(model, key)
-                setattr(instance, key, value)
-
-            session.commit()
-            session.refresh(instance)
-            return instance
-        finally:
-            session.close()
-
-    def modify(self, record_id: int, **kwargs) -> Optional[T]:
-        """
-        更新记录
-        :param record_id: 记录ID
-        :param kwargs: 要更新的字段键值对
-        :return: 更新后的模型实例或None
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.id == record_id).first()
-            if not instance:
-                return None
-
-            for key, value in kwargs.items():
-                setattr(instance, key, value)
-
-            session.commit()
-            session.refresh(instance)
-            return instance
-        finally:
-            session.close()
-
-    def update_by_username(self, username: str, **kwargs) -> Optional[T]:
-        """
-        更新记录
-        :param username: 记录ID
-        :param kwargs: 要更新的字段键值对
-        :return: 更新后的模型实例或None
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.username == username).first()
-            if not instance:
-                return None
-
-            for key, value in kwargs.items():
-                setattr(instance, key, value)
-
-            session.commit()
-            session.refresh(instance)
-            return instance
-        finally:
-            session.close()
-
-    def delete(self, record_id: int) -> bool:
-        """
-        删除记录
-        :param record_id: 记录ID
-        :return: 删除成功返回True，失败返回False
-        """
-        session = self.get_session()
-        try:
-            instance = session.query(self.__model__).filter(self.__model__.id == record_id).first()
-            if not instance:
-                return False
-
-            session.delete(instance)
-            session.commit()
-            return True
-        finally:
-            session.close()
-
-    def count(self, filters: Optional[Dict[str, Any]] = None) -> int:
-        """
-        统计记录数量
-        :param filters: 过滤条件字典
-        :return: 记录数量
-        """
-        session = self.get_session()
-        try:
-            query = session.query(func.count(self.__model__.id))
-
-            if filters:
-                for key, value in filters.items():
-                    query = query.filter(getattr(self.__model__, key) == value)
-
-            return query.scalar()
-        finally:
-            session.close()
-
-
-class User(Base, BaseModelMixin):
-    """用户模型"""
-    __tablename__ = "sys_user"
-
-    id = Column(String(32), primary_key=True, index=True)
-    source_id = Column(String(32), comment="源头id")
-    username = Column(String(100), unique=True, index=True, nullable=False, comment="用户名")
-    email = Column(String(45), unique=True, index=True, comment="邮箱")
-    birthday = Column(DateTime, unique=True, index=True, comment="邮箱")
-    sex = Column(Integer, comment="性别")
-    age = Column(Integer, comment="年龄")
-    token = Column(String(500), comment="token")
-    open_token = Column(String(1000), comment="开放token")
-    source = Column(String(50), comment="token")
-    del_flag = Column(Integer, comment="是否删除", default=0)
-    create_time = Column(DateTime, default=func.now(), comment="创建时间")
-    update_time = Column(DateTime, default=func.now(), onupdate=func.now(), comment="更新时间")
-
-    SourceEnum = ConstantEnum.SourceEnum
-
-
-class UserDao(Dao):
-    """用户Dao，继承BaseDao即可拥有所有基础CRUD功能"""
-    __model__ = User
-    __tablename__ = "users"
-
-
-if __name__ == "__main__":
-    pass

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/skill.py

@@ -1,82 +0,0 @@
-#!/usr/bin/env python3
-import os
-import sys
-import subprocess
-
-from .config import ApiEnum as ApiEnumBase, ConstantEnum
-from .base import BaseSkill
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-from .util import FileUtil
-
-from .api_service import ApiService
-
-class Skill(BaseSkill, ApiService):
-
-    def __init__(self):
-        super().__init__()
-
-class AgentSkill(BaseSkill, ApiService):
-
-    def __init__(self):
-        super().__init__()
-
-    def ai_chat(self, prompt: str, session_id: str = None, timeout: int = 120):
-        """
-        通过 subprocess 调用 openclaw agent 命令
-
-        Args:
-            prompt: 分析提示
-            session_id: 会话 ID（可选）
-            timeout: 超时时间（秒）
-
-        Returns:
-            分析结果或会话 ID
-        """
-        import uuid
-
-        # 生成唯一会话 ID
-        if not session_id:
-            entry_script = sys.argv[0]
-            abs_entry_script = os.path.abspath(entry_script)
-            main_name = FileUtil.get_name(abs_entry_script)
-            session_id = f"{main_name}--{uuid.uuid4()}"
-
-        ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent (会话：{session_id})..., prompt:{prompt}")
-
-        # 构建命令
-        cmd = [
-            "openclaw",
-            "agent",
-            "-m", str(prompt),
-            "--session-id", session_id,
-            "--thinking", "minimal",
-            "--timeout", str(timeout)
-        ]
-
-        ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行命令{' '.join(cmd)}")
-
-        try:
-            # 执行命令
-            result = subprocess.run(
-                cmd,
-                capture_output=True,
-                text=True,
-                timeout=timeout + 10
-            )
-
-            if result.stderr:
-                ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行错误:{result.stderr}")
-                return
-
-            output = result.stdout
-            ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行成功:{output}")
-
-            return output
-
-        except subprocess.TimeoutExpired as e:
-            ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 超时（{timeout}秒），任务可能仍在后台运行:{e}")
-        except Exception as e:
-            ConstantEnum.is_debug() and print(f"🤖 正在调用 openclaw agent 执行错误:{e}")
-
-
-skill = Skill()

skills/18072937735/smyx-fall-detection-video-analysis/skills/smyx_common/scripts/util.py

@@ -1,413 +0,0 @@
-#!/usr/bin/env python3
-import json
-import os
-import traceback
-
-import requests
-from .config import ApiEnum, ConstantEnum, sys, YamlUtil
-
-from .base import BaseUtil
-import time
-import logging
-from typing import Any, Callable, Optional, TypeVar, Dict
-import pydash as _
-
-if ConstantEnum.is_debug():
-    import http.client
-
-    # 【关键代码】开启调试模式
-    http.client.HTTPConnection.debuglevel = 1
-    # 可选：如果你希望日志更整洁，可以配合 logging 模块（否则打印会比较乱）
-    import logging
-
-    logging.basicConfig()
-    logging.getLogger().setLevel(logging.DEBUG)
-    requests_log = logging.getLogger("urllib3")
-    requests_log.setLevel(logging.DEBUG)
-    requests_log.propagate = True
-
-
-class StringUtil(BaseUtil):
-
-    @staticmethod
-    def camel_to_snake(name):
-        import re
-        s1 = re.sub('(.)([A-Z][a-z]+)', r'\1_\2', name)
-        return re.sub('([a-z0-9])([A-Z])', r'\1_\2', s1).lower()
-
-    @staticmethod
-    def snake_to_pascal(name):
-        import re
-        name = re.sub(r'^([a-z])', lambda m: m.group(1).upper(), name)
-        return re.sub(r'_([a-z])', lambda m: m.group(1).upper(), name)
-
-    @staticmethod
-    def snake_to_camel(name):
-        import re
-        # 逻辑：匹配 '_[a-z]' (下划线+小写字母)，将其替换为对应的大写字母（去掉下划线）
-        return re.sub(r'_([a-z])', lambda m: m.group(1).upper(), name)
-
-
-class FileUtil(BaseUtil):
-
-    @staticmethod
-    def get_fullname(path):
-        try:
-            return os.path.basename(path)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            return ""
-
-    @staticmethod
-    def get_name(path):
-        try:
-            return os.path.splitext(os.path.basename(path))[0]
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-    @staticmethod
-    def get_ext(path):
-        try:
-            return os.path.splitext(os.path.basename(path))[1]
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-    @staticmethod
-    def open(path):
-        try:
-            return open(path, 'w', encoding='utf-8')
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-    @staticmethod
-    def mkdir(path):
-        try:
-            os.makedirs(path, exist_ok=True)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-
-
-class JsonUtil(BaseUtil):
-
-    @staticmethod
-    def stringify(json_obj, default_str=""):
-        try:
-            return json.dumps(json_obj, ensure_ascii=False, indent=2)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            pass
-        return default_str
-
-    @staticmethod
-    def parse(json_str, default_json={}):
-        try:
-            return json.loads(json_str)
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            pass
-        return default_json
-
-
-class CommonUtil(BaseUtil):
-
-    @staticmethod
-    def trace_exception_stack(e):
-        if ConstantEnum.is_debug():
-            print(f"❌ 错误描述: {str(e)}, 堆栈跟踪:")
-            traceback.print_stack()
-
-    @staticmethod
-    def polling(
-            action: Callable[[], Any],
-            check_condition: Callable[[Any], bool],
-            on_success: Optional[Callable[[Any], None]] = None,
-            on_retry: Optional[Callable[[Any, int], None]] = None,
-            on_error: Optional[Callable[[Exception], None]] = None,
-            interval: float = 1.0,
-            max_attempts: int = 5,
-            description: str = "轮询任务"
-    ) -> Optional[Any]:
-        """
-        通用的轮询处理函数
-
-        :param action:
-            [必填] 执行动作的回调函数。
-            例如：发送 HTTP 请求、查询数据库状态等。
-            必须返回一个结果对象供 check_condition 使用。
-
-        :param check_condition:
-            [必填] 检查是否结束的回调函数。
-            接收 action 的返回值，返回 True 表示“满足结束条件”，False 表示“继续轮询”。
-            例如：lambda res: res.get('need_refresh') is False
-
-        :param on_success:
-            [可选] 当 check_condition 返回 True 时执行的回调（通常用于记录日志或处理最终数据）。
-
-        :param on_retry:
-            [可选] 当需要继续轮询时执行的回调。
-            参数：(当前结果, 当前尝试次数)。可用于打印进度。
-
-        :param on_error:
-            [可选] 当 action 抛出异常时执行的回调。
-            参数：(异常对象)。
-
-        :param interval:
-            每次轮询之间的等待时间（秒）。
-
-        :param max_attempts:
-            最大尝试次数，防止死循环。
-
-        :param description:
-            任务描述，用于日志输出。
-
-        :return:
-            如果成功，返回 action 的最后一次返回值；如果超时或失败，返回 None。
-        """
-
-        attempts = 0
-
-        print(f"🚀 开始执行 [{description}]...")
-
-        while attempts < max_attempts:
-            attempts += 1
-
-            try:
-                # 1. 执行动作
-                result = action()
-                last_result = result
-
-                # 2. 检查条件
-                if check_condition(result):
-                    print(f"✅ [{description}] 成功！条件已满足 (尝试次数: {attempts}, 耗时{interval * attempts}秒)")
-                    if on_success:
-                        on_success(result)
-                    return result
-
-                # 3. 条件未满足，准备重试
-                if on_retry:
-                    on_retry(result, attempts)
-                else:
-                    # 默认日志行为
-                    print(
-                        f"⏳ [{description}] 条件未满足，{interval}秒后重试... ({attempts}/{max_attempts}, 耗时{interval * attempts}秒)")
-
-                time.sleep(interval)
-
-            except Exception as e:
-                # 4. 异常处理
-                if on_error:
-                    on_error(e)
-                else:
-                    # 默认错误行为：打印错误并继续
-                    logging.error(f"❌ [{description}] 发生异常: {e}")
-                    print(f"⚠️ [{description}] 遇到错误，{interval}秒后重试...")
-
-                time.sleep(interval)
-
-        # 5. 超时处理
-        print(f"⚠️ [{description}] 失败：达到最大尝试次数 ({max_attempts})，强制停止。")
-        return None
-
-    @staticmethod
-    def is_empty(data):
-        # 1. 如果是 None (对应 JSON 的 null)
-        if data is None:
-            return True
-
-        # 2. 如果是字典或列表，且长度为 0 (对应 {} 或 [])
-        if isinstance(data, (dict, list)) and len(data) == 0:
-            return True
-
-
-from datetime import date, datetime
-
-
-class DatetimeUtil(BaseUtil):
-    FORMAT__DATETIME = "%Y-%m-%d %H:%M:%S"
-
-    @staticmethod
-    def now_str():
-        return DatetimeUtil.format(DatetimeUtil.now())
-
-    @staticmethod
-    def today_str():
-        return DatetimeUtil.format_date(DatetimeUtil.today())
-
-    @staticmethod
-    def now():
-        return datetime.now()
-
-    @staticmethod
-    def today():
-        return DatetimeUtil.now().replace(hour=0, minute=0, second=0, microsecond=0)
-
-    @staticmethod
-    def format(date):
-        return date.strftime('%Y-%m-%d %H:%M:%S') if type(date) == datetime else date
-
-    @staticmethod
-    def format_date(date):
-        return date.strftime('%Y-%m-%d') if type(date) == datetime else date
-
-    @staticmethod
-    def parse(date_str):
-        if type(date_str) == int:
-            return datetime.fromtimestamp(date_str)
-        return datetime.strptime(date_str, DatetimeUtil.FORMAT__DATETIME) if type(date_str) == str else date_str
-
-    @staticmethod
-    def timestamp(date=now()):
-        return int(date.timestamp() * 1000)
-
-
-class RequestUtil(BaseUtil):
-    BASE_URL = ApiEnum.BASE_URL_OPEN_API
-    AUTHORIZATION_RETRY_COUNT_MAX = 3
-    authorization_retry_count = 0
-
-    @classmethod
-    def http_post(cls, url, data=None, params=None, headers=None, *args, **argss):
-        return cls.http_request("post", url, data=data, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_put(cls, url, data=None, params=None, headers=None, *args, **argss):
-        return cls.http_request("put", url, data=data, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_delete(cls, url, data=None, params=None, headers=None, *args, **argss):
-        return cls.http_request("delete", url, data=data, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_get(cls, url, params=None, headers=None, *args, **argss):
-        return cls.http_request("get", url, params=params, headers=headers, *args, **argss)
-
-    @classmethod
-    def http_request(cls, method, url, data=None, params=None, headers=None, options=None, *args,
-                     timeout=ApiEnum.DEFAULT__REQUEST_TIMEOUT, **argss):
-        def _get_or_create_user(username):
-            _url = ApiEnum.BASE_URL_HEALTH + "/sys/phoneLogin"
-            open_id = username
-            _data = {
-                "silent": 1,
-                "register": 1,
-                "openId": open_id,
-                "mobile": username
-            }
-            try:
-                _response = requests.post(_url, json=_data)
-                if _response.status_code == 200:
-                    _response_json = _response.json()
-                    if _response_json and _response_json.get("success"):
-                        return _response_json and _response_json.get("result")
-            except Exception as _e:
-                CommonUtil.trace_exception_stack(_e)
-            return {}
-
-        try:
-            headers = headers or {}
-            if not url.startswith("https://") and not url.startswith("http://"):
-                url = cls.BASE_URL + url
-            headers['App-Id'] = ConstantEnum.APP__ID
-            # ConstantEnum.CURRENT__USER_NAME = ConstantEnum.CURRENT__OPEN_ID = "ou_86fdd8e0d5f116c18a9dd550abefe6d2"
-            current__user_name = ApiEnum.API_SECRET_KEY or ConstantEnum.CURRENT__USER_NAME or ConstantEnum.CURRENT__OPEN_ID
-            if (not ApiEnum.TOKEN or not ApiEnum.OPEN_TOKEN) and current__user_name:
-                try:
-                    from .dao import UserDao, User
-                    user_dao = UserDao()
-                    found_user = user_dao.get_by_username(current__user_name)
-                    if found_user:
-                        ApiEnum.TOKEN = found_user.token
-                        ApiEnum.OPEN_TOKEN = found_user.open_token
-                    if not ApiEnum.TOKEN or not ApiEnum.OPEN_TOKEN:
-                        new_current_user = _get_or_create_user(current__user_name)
-                        if new_current_user:
-                            ApiEnum.TOKEN = new_current_user.get("token")
-                            ApiEnum.OPEN_TOKEN = new_current_user.get("openToken")
-
-                            current_user_info = new_current_user.get("userInfo")
-                            if current_user_info:
-                                current_user_info["token"] = new_current_user.get("token")
-                                current_user_info["openToken"] = new_current_user.get(
-                                    "openToken")
-                                user_model = User.load(current_user_info)
-
-                                user = user_dao.save(
-                                    user_model
-                                )
-
-                except Exception as e:
-                    CommonUtil.trace_exception_stack(e)
-                    raise
-
-            headers.setdefault("X-Access-Token", ApiEnum.TOKEN)
-            headers.setdefault("X-Api-Key", ApiEnum.API_SECRET_KEY)
-            headers.setdefault("Authorization", ApiEnum.OPEN_TOKEN)
-
-            data = data or {}
-            params = params or {}
-            options = options or {}
-            ConstantEnum.CURRENT__TENTANT_CODE and data.setdefault('tenantCode', ConstantEnum.CURRENT__TENTANT_CODE)
-            ConstantEnum.DEFAULT__SKILL_HUB_NAME and data.setdefault('skillHubName',
-                                                                     ConstantEnum.DEFAULT__SKILL_HUB_NAME)
-            ConstantEnum.DEFAULT__SKILL_PLATFORM_NAME and data.setdefault('skillPlatform',
-                                                                          ConstantEnum.DEFAULT__SKILL_PLATFORM_NAME)
-            if current__user_name:
-                data.setdefault('pnaUserName', current__user_name)
-
-            if bool(options.get("dataAsParams")):
-                params.update(data)
-
-            print(f"🔄 请求拦截, URL:{url}", "method", method, "params", params, "data", data, "headers", headers,
-                  "options", options,
-                  "timeout",
-                  timeout)
-            response = requests.request(method, url, *args, json=data, params=params, headers=headers,
-                                        timeout=int(timeout), **argss)
-            response_text = response.text if ConstantEnum.is_debug() else response
-            if response.status_code == 401 and cls.authorization_retry_count < cls.AUTHORIZATION_RETRY_COUNT_MAX:
-                print(f"❌ 请求拦截, 鉴权:{response_text}, url:{url}", "method", method, "params", params,
-                      "data",
-                      data,
-                      "headers",
-                      headers,
-                      "timeout",
-                      timeout)
-                ApiEnum.TOKEN = ApiEnum.OPEN_TOKEN = None
-                if found_user:
-                    found_user.token = found_user.open_token = None
-                    user_dao.update(found_user)
-                cls.authorization_retry_count += 1
-                return cls.http_request(method, url, data, params, headers, options, *args, timeout=timeout, **argss)
-            elif response.status_code != 200:
-                raise requests.exceptions.RequestException(
-                    response, response=response)
-            response_json = response.json()
-            if not bool(response_json['success']):
-                raise requests.exceptions.RequestException(
-                    response, response=response)
-            response_json_data = response_json.get("data", response_json.get("result"))
-            response_json_data = response_json_data.get("records") if response_json_data and type(
-                response_json_data) == dict and "records" in response_json_data else response_json_data
-            print(f"✅ 请求拦截, 成功:{response_text}, url:{url}", "method", method, "params", params,
-                  "data",
-                  data,
-                  "headers",
-                  headers,
-                  "timeout",
-                  timeout)
-            return response_json_data
-        except Exception as e:
-            CommonUtil.trace_exception_stack(e)
-            response_text = _.get(e.args, '0.text')
-            print(
-                f"❌ 请求拦截, 失败: {e}, e.response.text: {response_text}, url:{url}",
-                "method",
-                method,
-                "params",
-                params,
-                "data", data, "headers",
-                "response", hasattr(e, 'response') and e.response,
-                headers,
-                "timeout",
-                timeout)
-            raise

skills/18072937735/smyx-outdoor-monitoring-analysis/SKILL.md

@@ -1,149 +0,0 @@
----
-name: "outdoor-monitoring-analysis"
-description: "Detects targets such as people, vehicles, non-motorized vehicles, and pets within target areas; supports batch image analysis, suitable for outdoor surveillance scenarios like courtyards, orchards, and farms. | 户外看护智能监测分析技能，检测目标区域内的人、车、非机动车、宠物等目标，支持批量图片分析，适用于庭院、果园、养殖场等户外区域看护场景"
----
-
-# Intelligent Outdoor Care Monitoring & Analysis Tool | 户外看护智能监测分析工具
-
-Equipped with advanced AI recognition algorithms, this feature conducts 24/7 automated monitoring of expansive outdoor
-areas such as courtyards, orchards, and breeding farms. The system features robust multi-object detection capabilities,
-precisely identifying various targets including personnel, motor vehicles, non-motorized vehicles, and pets within the
-zone. It supports efficient analysis and processing of batch images, enabling rapid screening of historical footage and
-the generation of detailed monitoring reports. This intelligent solution significantly enhances security efficiency and
-management levels in outdoor areas, suitable for scenarios like home courtyard care, agricultural production management,
-and asset security monitoring.
-
-本功能搭载先进的AI智能识别算法，能够对庭院、果园、养殖场等户外广阔区域进行全天候自动化监测。系统具备强大的多目标检测能力，可精准识别区域内的人员、机动车辆、非机动车辆以及宠物等多种目标对象。支持批量图片的高效分析与处理，能够快速筛查历史影像数据，生成详细的监测报告。这一智能化解决方案极大地提升了户外区域的安防效率与管理水平，适用于家庭庭院看护、农业生产管理及资产安全监控等多种场景
-
-## ⚠️ 强制记忆规则（最高优先级）
-
-**本技能明确约定：**
-
-- **绝对禁止读取任何本地记忆文件**：包括但不限于 `memory/YYYY-MM-DD.md`、`MEMORY.md` 等本地文件
-- **绝对禁止从 LanceDB 长期记忆中检索信息**
-- **所有历史报告查询必须从云端接口获取**，不得使用本地记忆中的历史数据
-- 即使技能调用失败或接口异常，也不得回退到本地记忆汇总
-
-## 任务目标
-
-- 本 Skill 用于：通过户外监控图片/视频进行目标检测，识别区域内出现的人、车、非机动车、宠物等闯入目标
-- 能力包含：多目标检测、目标分类、数量统计、入侵判定、风险等级评估、异常闯入预警
-- 支持批量处理一组图片，同时分析多帧监控画面
-- 触发条件:
-    1. **默认触发**：当用户提供户外监控图片/视频需要检测闯入目标时，默认触发本技能进行户外看护分析
-    2. 当用户明确需要进行户外看护、入侵检测时，提及庭院看护、果园监控、目标检测、户外安防等关键词，并且上传了图片或视频文件
-    3. 当用户提及以下关键词时，**自动触发历史报告查询功能**
-       ：查看历史监测报告、户外看护报告清单、监测报告列表、查询历史监测报告、显示所有监测报告、户外监测分析报告，查询户外看护智能监测分析报告
-- 自动行为：
-    1. 如果用户上传了附件或者图片/视频文件，则自动保存到技能目录下 attachments
-    2. **⚠️ 强制数据获取规则（次高优先级）**：如果用户触发任何历史报告查询关键词（如"查看所有监测报告"、"显示所有看护报告"、"
-       查看历史报告"等），**必须**：
-        - 直接使用 `python -m scripts.outdoor_monitoring --list --open-id` 参数调用 API
-          查询云端的历史报告数据
-        - **严格禁止**：从本地 memory 目录读取历史会话信息、严格禁止手动汇总本地记录中的报告、严格禁止从长期记忆中提取报告
-        - **必须统一**从云端接口获取最新完整数据，然后以 Markdown 表格格式输出结果
-
-## 前置准备
-
-- 依赖说明:scripts 脚本所需的依赖包及版本
-  ```
-  requests>=2.28.0
-  ```
-
-## 操作步骤
-
-### 🔒 open-id 获取流程控制（强制执行，防止遗漏）
-
-**在执行户外看护分析前，必须按以下优先级顺序获取 open-id：**
-
-```
-第 1 步：【最高优先级】检查技能所在目录的配置文件（优先）
-        路径：skills/smyx_common/scripts/config.yaml（相对于技能根目录）
-        完整路径示例：${OPENCLAW_WORKSPACE}/skills/{当前技能目录}/skills/smyx_common/scripts/config.yaml
-        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id
-        ↓ (未找到/未配置/api-key 为空)
-第 2 步：检查 workspace 公共目录的配置文件
-        路径：${OPENCLAW_WORKSPACE}/skills/smyx_common/scripts/config.yaml
-        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id
-        ↓ (未找到/未配置)
-第 3 步：检查用户是否在消息中明确提供了 open-id
-        ↓ (未提供)
-第 4 步：❗ 必须暂停执行，明确提示用户提供用户名或手机号作为 open-id
-```
-
-**⚠️ 关键约束：**
-
-- **禁止**自行假设,自行推导,自行生成 open-id 值（如 openclaw-control-ui、default、outdoor123、monitor456 等）
-- **禁止**跳过 open-id 验证直接调用 API
-- **必须**在获取到有效 open-id 后才能继续执行分析
-- 如果用户拒绝提供 open-id，说明用途（用于保存和查询监测报告记录），并询问是否继续
-
----
-
-- 标准流程:
-    1. **准备图片/视频输入**
-        - 提供本地图片/视频文件路径或网络 URL
-        - 支持批量上传一组图片同时分析
-        - 确保监控画面覆盖完整目标监测区域
-    2. **获取 open-id（强制执行）**
-        - 按上述流程控制获取 open-id
-        - 如无法获取，必须提示用户提供用户名或手机号
-    3. **执行户外看护智能监测分析**
-        - 调用 `-m scripts.outdoor_monitoring` 处理输入（**必须在技能根目录下运行脚本**）
-        - 参数说明:
-            - `--input`: 本地图片/视频文件路径（使用 multipart/form-data 方式上传）
-            - `--url`: 网络图片/视频 URL 地址（API 服务自动下载）
-            - `--open-id`: 当前用户的 open-id（必填，按上述流程获取）
-            - `--list`: 显示历史户外看护监测分析报告列表清单（可以输入起始日期参数过滤数据范围）
-            - `--api-key`: API 访问密钥（可选）
-            - `--api-url`: API 服务地址（可选，使用默认值）
-            - `--detail`: 输出详细程度（basic/standard/json，默认 json）
-            - `--output`: 结果输出文件路径（可选）
-    4. **查看分析结果**
-        - 接收结构化的户外看护智能监测分析报告
-        - 包含：监控基本信息、检测到的目标类型、目标数量、位置分布、是否异常闯入、风险等级、处置建议
-
-## 资源索引
-
-- 必要脚本：见 [scripts/outdoor_monitoring.py](scripts/outdoor_monitoring.py)(用途：调用 API 进行户外看护智能监测分析，本地文件使用
-  multipart/form-data 方式上传，网络 URL 由 API 服务自动下载)
-- 配置文件：见 [scripts/config.py](scripts/config.py)(用途：配置 API 地址、默认参数和格式限制)
-- 领域参考：见 [references/api_doc.md](references/api_doc.md)(何时读取：需要了解 API 接口详细规范和错误码时)
-
-## 注意事项
-
-- 仅在需要时读取参考文档，保持上下文简洁
-- 支持格式：jpg/jpeg/png/mp4/avi/mov，最大 100MB，支持批量图片分析
-- API 密钥可选，如果通过参数传入则必须确保调用鉴权成功，否则忽略鉴权
-- 分析结果仅供安防参考，不能替代专业安保措施，发现可疑闯入请及时报警
-- 禁止临时生成脚本，只能用技能本身的脚本
-- 传入的网路地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载
-- 当显示历史分析报告清单的时候，从数据 json 中提取字段 reportImageUrl 作为超链接地址，使用 Markdown 表格格式输出，包含"
-  报告名称"、"输入类型"、"分析时间"、"检测目标数"、"风险等级"、"点击查看"六列，其中"报告名称"列使用`户外看护监测分析报告-{记录id}`
-  形式拼接, "点击查看"列使用
-  `[🔗 查看报告](reportImageUrl)`
-  格式的超链接，用户点击即可直接跳转到对应的完整报告页面。
-- 表格输出示例：
-  | 报告名称 | 输入类型 | 分析时间 | 检测目标数 | 风险等级 | 点击查看 |
-  |----------|----------|----------|------------|----------|----------|
-  | 户外看护监测分析报告 -20260328221000001 | 多图 | 2026-03-28 22:10:00 | 2人+1车 |
-  中风险 | [🔗 查看报告](https://example.com/report?id=xxx) |
-
-## 使用示例
-
-```bash
-# 分析单张监控图片（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.outdoor_monitoring --input /path/to/yard.jpg --open-id openclaw-control-ui
-
-# 分析网络监控视频（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）
-python -m scripts.outdoor_monitoring --url https://example.com/garden.mp4 --open-id openclaw-control-ui
-
-# 显示历史分析报告/显示分析报告清单列表/显示历史监测报告（自动触发关键词：查看历史监测报告、历史报告、监测报告清单等）
-python -m scripts.outdoor_monitoring --list --open-id openclaw-control-ui
-
-# 输出精简报告
-python -m scripts.outdoor_monitoring --input capture.jpg --open-id your-open-id --detail basic
-
-# 保存结果到文件
-python -m scripts.outdoor_monitoring --input capture.jpg --open-id your-open-id --output result.json
-```

skills/18072937735/smyx-outdoor-monitoring-analysis/_meta.json

@@ -1,11 +0,0 @@
-{
-  "owner": "18072937735",
-  "slug": "smyx-outdoor-monitoring-analysis",
-  "displayName": "Intelligent Outdoor Care Monitoring & Analysis Tool | 户外看护智能监测分析工具",
-  "latest": {
-    "version": "1.0.0",
-    "publishedAt": 1776314371084,
-    "commit": "https://github.com/openclaw/skills/commit/539926e12970ba32a8d97826203327b8ffaee85d"
-  },
-  "history": []
-}

skills/18072937735/smyx-outdoor-monitoring-analysis/references/api_doc.md

@@ -1,21 +0,0 @@
-# API 接口文档
-
-此处用于存放户外看护智能监测分析 API 的接口文档，待后续补充。
-
-## 接口规范
-
-- 基础地址：由 smyx_common 配置统一管理
-- 认证方式：API Key 鉴权
-- 请求格式：multipart/form-data 支持文件上传
-- 响应格式：JSON
-
-## 主要接口
-
-1. `/web/ai-analysis/v2/start-common-ai-analysis` - 启动AI分析任务
-2. `/web/ai-analysis/v2/get-common-ai-analysis-result` - 获取分析结果
-3. `/web/ai-analysis/page-common-ai-analysis-result` - 分页查询历史报告
-4. `/ai/order/api/getReportDetailExport?id={id}` - 导出完整报告
-
-## 场景代码
-
-- `OPEN_OUTDOOR_MONITORING_ANALYSIS` - 开放平台户外看护监测分析

skills/18072937735/smyx-outdoor-monitoring-analysis/scripts/__init__.py

@@ -1 +0,0 @@
-# Pet Analysis scripts package

skills/18072937735/smyx-outdoor-monitoring-analysis/scripts/api_service.py

@@ -1,53 +0,0 @@
-#!/usr/bin/env python3
-
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-from skills.smyx_common.scripts.util import RequestUtil
-
-
-class ApiService(ApiServiceBase):
-
-    def __init__(self):
-        super().__init__()
-        self.analysis_url = ApiEnum.ANALYSIS_URL
-
-    def analysis_result(self, *args, **argss):
-        return self.http_post(ApiEnum.ANALYSIS_RESULT_URL, *args, **argss)
-
-    def analysis(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        options = {
-            "dataAsParams": True
-        }
-        # params.setdefault("scene", scene_code)
-        # 添加宠物类型参数
-        if ConstantEnum.DEFAULT__PET_TYPE:
-            params.setdefault("petType", ConstantEnum.DEFAULT__PET_TYPE)
-        return self.http_post(self.analysis_url, options=options, *args, **argss)
-
-    def page(self, pageNum=None, pageSize=None, *args, **argss):
-        data = argss.setdefault("data", {})
-        data.setdefault("orderBy", {
-            "fieldName": "createTime",
-            "isAsc": False
-        })
-        return super().page(ApiEnum.PAGE_URL, pageNum, pageSize, *args, **argss)
-
-    def list(self, *args, **argss):
-        return super().list(None, *args, **argss)
-
-    def add(self, item: dict):
-        return super().add(ApiEnum.ADD_URL, item)
-
-    def edit(self, item: dict):
-        return super().edit(ApiEnum.EDIT_URL, item)
-
-    def delete(self, cameraSn):
-        data = {
-            "cameraSn": cameraSn
-        }
-        return super().delete(ApiEnum.DELETE_URL, data, options={"dataAsParams": True})

skills/18072937735/smyx-outdoor-monitoring-analysis/scripts/config.py

@@ -1,24 +0,0 @@
-#!/usr/bin/env python3
-# 户外看护智能监测分析工具配置文件
-import os
-import sys
-
-from enum import Enum
-
-from skills.smyx_common.scripts.config import ConstantEnum as ConstantEnumBase
-
-from skills.face_analysis.scripts.config import ApiEnum as ApiEnumParent, ConstantEnum as ConstantEnumParent, \
-    ApiEnumCommonAiMixin
-
-SceneCodeEnum = ConstantEnumBase.SceneCodeEnum
-
-
-class ApiEnum(ApiEnumCommonAiMixin, ApiEnumParent):
-    pass
-
-
-class ConstantEnum(ConstantEnumParent):
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-        ConstantEnumParent.DEFAULT__SCENE_CODE = SceneCodeEnum.OUTDOOR_MONITORING_ANALYSIS.value

skills/18072937735/smyx-outdoor-monitoring-analysis/scripts/config.yaml

@@ -1 +0,0 @@
-{}

skills/18072937735/smyx-outdoor-monitoring-analysis/scripts/outdoor_monitoring.py

@@ -1,97 +0,0 @@
-#!/usr/bin/env python3
-import sys
-import os
-
-current_dir = os.path.dirname(os.path.abspath(__file__))
-parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(current_dir)))
-sys.path.insert(0, parent_dir)
-
-import argparse
-import json
-import mimetypes
-import traceback
-from datetime import datetime
-
-import requests
-import sys
-import os
-
-from .config import *
-
-from .skill import skill
-
-from skills.smyx_common.scripts.util import RequestUtil
-
-
-def analyze_monitor(input_path=None, url=None, api_url=None, api_key=None, output_level=None):
-    input_path = input_path or url
-    return skill.get_output_analysis(input_path)
-
-
-def show_analyze_list(open_id, start_time=None, end_time=None):
-    output_content = skill.get_output_analysis_list()
-    return output_content
-
-
-def main():
-    parser = argparse.ArgumentParser(description="户外看护智能监测分析工具")
-    parser.add_argument("--input", help="本地图片/视频文件路径")
-    parser.add_argument("--url", help="网络图片/视频URL地址")
-    parser.add_argument("--open-id", required=True, help="当前用户的OpenID/UserId/用户名/手机号")
-    parser.add_argument("--list", action='store_true', help="显示户外看护监测分析列表清单")
-    parser.add_argument("--api-url", help="服务端API地址")
-    parser.add_argument("--api-key", help="API访问密钥（必需）")
-    parser.add_argument("--output", help="结果输出文件路径")
-    parser.add_argument("--detail", choices=["basic", "standard", "json"],
-                        default=ConstantEnum.DEFAULT__OUTPUT_LEVEL,
-                        help="输出详细程度")
-    parser.add_argument("--export-env-only", action='store_true',
-                        help="仅输出 export 命令设置环境变量，不执行分析")
-
-    args = parser.parse_args()
-
-    try:
-        if args.open_id:
-            # 设置 Python 进程内的环境变量
-            ConstantEnumBase.CURRENT__OPEN_ID = args.open_id
-
-        # 检查必需参数
-        if args.list:
-            open_id = ConstantEnum.CURRENT__OPEN_ID
-            result = show_analyze_list(open_id)
-            print(result)
-            exit(0)
-
-        # 检查必需参数
-        if not args.input and not args.url:
-            print("❌ 错误: 必须提供 --input 或 --url 参数")
-            exit(1)
-
-        print("🔍 正在监测户外目标，请稍候...")
-        output_content = analyze_monitor(
-            input_path=args.input,
-            url=args.url,
-            api_url=args.api_url,
-            api_key=args.api_key,
-            output_level=args.detail
-        )
-
-        print(output_content)
-
-        # 保存到文件
-        if args.output:
-            with open(args.output, "w", encoding="utf-8") as f:
-                if args.detail == "full":
-                    json.dump(result, f, ensure_ascii=False, indent=2)
-                else:
-                    f.write(output_content)
-            print(f"✅ 结果已保存到: {args.output}")
-
-    except Exception as e:
-        traceback.print_stack()
-        print(f"❌ 户外看护监测分析失败: {str(e)}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()

skills/18072937735/smyx-outdoor-monitoring-analysis/scripts/skill.py

@@ -1,23 +0,0 @@
-#!/usr/bin/env python3
-import json
-
-from .config import ApiEnum, ConstantEnum
-
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-from skills.face_analysis.scripts.skill import Skill as SkillParent
-from skills.smyx_common.scripts.util import JsonUtil
-
-
-class Skill(SkillParent):
-    def __init__(self):
-        super().__init__()
-
-    def get_output_analysis_content_head(self, result=None):
-        return f"📊 户外看护智能监测分析结构化结果"
-
-    def get_output_analysis_content_foot(self, result):
-        pass
-
-
-skill = Skill()

skills/18072937735/smyx-outdoor-monitoring-analysis/skills/face_analysis/README.md

@@ -1,86 +0,0 @@
-# 中医面诊分析工具 (face-analysis)
-
-## 技能介绍
-这是一个基于AI的中医面诊分析技能，可以通过面部视频自动分析健康状况，返回结构化的诊断结果和养生建议。
-
-## 快速开始
-### 1. 配置API信息
-编辑 `scripts/config.py`，设置你的API地址和密钥：
-```python
-DEFAULT_API_URL = "https://your-api-server.com/api/v1/face-analysis"
-DEFAULT_API_KEY = "your-api-key-here"
-```
-
-### 2. 分析本地视频
-```bash
-python scripts/face_analysis.py --input /path/to/your/video.mp4
-```
-
-### 3. 分析网络视频
-```bash
-python scripts/face_analysis.py --url https://example.com/video.mp4
-```
-
-## 功能特性
-- ✅ 支持本地MP4视频上传
-- ✅ 支持网络视频URL分析
-- ✅ 三种输出详细程度：精简/标准/完整
-- ✅ 结构化JSON结果输出
-- ✅ 自动保存结果到文件
-- ✅ 内置视频格式和大小校验
-
-## 目录结构
-```
-face-analysis/
-├── SKILL.md              # 技能说明文件（系统自动加载）
-├── README.md             # 本说明文件
-├── scripts/
-│   ├── face_analysis.py  # 主程序
-│   └── config.py         # 配置文件
-├── references/
-│   ├── api_doc.md        # API接口文档
-│   ├── tcm_theory.md     # 中医面诊理论参考
-│   └── faq.md            # 常见问题
-└── assets/
-    └── template.json     # 返回结果模板
-```
-
-## 使用示例
-### 标准输出
-```
-📊 中医面诊分析报告
-==================================================
-⏰ 分析时间: 2026-03-10 15:30:00
-🎯 人脸检测: success (置信度: 95分)
-
-🔍 诊断结果:
-  整体体质: 平和质
-  脏腑状况:
-    liver: 正常
-    heart: 轻微火旺
-    spleen: 略虚
-    lung: 正常
-    kidney: 正常
-  面色分析: 微黄
-  对应提示: 脾胃功能略弱
-
-⚠️ 健康警示:
-  ⚠️  注意休息，避免熬夜
-
-💡 养生建议:
-  💡 饮食清淡，减少辛辣食物摄入
-  💡 保持规律作息，每晚11点前入睡
-  💡 适当进行有氧运动，如散步、太极拳
-==================================================
-```
-
-### 输出到JSON文件
-```bash
-python scripts/face_analysis.py --input video.mp4 --detail full --output result.json
-```
-
-## 注意事项
-1. 视频要求：清晰正面面部，光线充足，时长5-30秒为宜
-2. 支持格式：mp4、avi、mov，最大100MB
-3. API需要自行部署或接入第三方服务
-4. 结果仅供参考，不能替代专业医生诊断

skills/18072937735/smyx-outdoor-monitoring-analysis/skills/face_analysis/references/api_doc.md

@@ -1,69 +0,0 @@
-# API接口文档
-
-## 接口地址
-`POST https://your-api-server.com/api/v1/face-analysis`
-
-## 请求头
-| 字段 | 必选 | 说明 |
-|------|------|------|
-| X-API-Key | 是 | API访问密钥 |
-| Content-Type | 是 | multipart/form-data（文件上传）或 application/json（URL模式） |
-
-## 请求参数
-### 1. 文件上传模式
-| 字段 | 类型 | 必选 | 说明 |
-|------|------|------|------|
-| video | file | 是 | MP4视频文件 |
-| detail_level | string | 否 | 输出详细程度：basic/standard/full，默认standard |
-
-### 2. URL模式
-| 字段 | 类型 | 必选 | 说明 |
-|------|------|------|------|
-| video_url | string | 是 | 可公开访问的视频URL |
-| detail_level | string | 否 | 输出详细程度：basic/standard/full，默认standard |
-
-## 响应格式
-```json
-{
-  "code": 200,
-  "message": "success",
-  "data": {
-    "analysis_time": "2026-03-10 15:30:00",
-    "face_detection": {
-      "status": "success",
-      "face_count": 1,
-      "quality_score": 95
-    },
-    "diagnosis": {
-      "overall_constitution": "平和质",
-      "organ_condition": {
-        "liver": "正常",
-        "heart": "轻微火旺",
-        "spleen": "略虚",
-        "lung": "正常",
-        "kidney": "正常"
-      },
-      "color_analysis": {
-        "complexion": "微黄",
-        "correspondence": "脾胃功能略弱"
-      }
-    },
-    "health_warnings": [
-      "注意休息，避免熬夜"
-    ],
-    "suggestions": [
-      "饮食清淡，减少辛辣食物摄入"
-    ]
-  }
-}
-```
-
-## 错误码说明
-| 错误码 | 说明 |
-|--------|------|
-| 400 | 请求参数错误 |
-| 401 | API密钥无效 |
-| 403 | 权限不足 |
-| 413 | 文件过大 |
-| 415 | 不支持的文件格式 |
-| 500 | 服务器内部错误 |

skills/18072937735/smyx-outdoor-monitoring-analysis/skills/face_analysis/requirements.txt

@@ -1,3 +0,0 @@
-pydash==8.0.6
-SQLAlchemy==2.0.46
-yaml==6.0.3

skills/18072937735/smyx-outdoor-monitoring-analysis/skills/face_analysis/scripts/api_service.py

@@ -1,52 +0,0 @@
-#!/usr/bin/env python3
-
-import os
-import sys
-
-from .config import ApiEnum, ConstantEnum
-from skills.smyx_common.scripts.api_service import ApiService as ApiServiceBase
-
-
-class ApiService(ApiServiceBase):
-
-    def __init__(self):
-        super().__init__()
-        self.analysis_url = ApiEnum.ANALYSIS_URL
-
-    def analysis_result(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        scene_code and params.setdefault("sceneCode", scene_code)
-        return self.http_post(ApiEnum.ANALYSIS_RESULT_URL, *args, **argss)
-
-    def analysis(self, scene_code=ConstantEnum.DEFAULT__SCENE_CODE, *args, **argss):
-        params = argss.setdefault("params", {})
-        options = {
-            "dataAsParams": True
-        }
-        scene_code and params.setdefault("sceneCode", scene_code)
-        params.setdefault("appCategory", ConstantEnum.DEFAULT__APP_CATEGORY)
-        return self.http_post(self.analysis_url, options=options, *args, **argss)
-
-    def page(self, pageNum=None, pageSize=None, *args, **argss):
-        data = argss.setdefault("data", {})
-        ConstantEnum.DEFAULT__SCENE_CODE and data.setdefault("sceneCode", ConstantEnum.DEFAULT__SCENE_CODE)
-        data.setdefault("orderBy", {
-            "fieldName": "createTime",
-            "isAsc": False
-        })
-        return super().page(ApiEnum.PAGE_URL, pageNum, pageSize, *args, **argss)
-
-    def list(self, *args, **argss):
-        return super().list(None, *args, **argss)
-
-    def add(self, item: dict):
-        return super().add(ApiEnum.ADD_URL, item)
-
-    def edit(self, item: dict):
-        return super().edit(ApiEnum.EDIT_URL, item)
-
-    def delete(self, cameraSn):
-        data = {
-            "cameraSn": cameraSn
-        }
-        return super().delete(ApiEnum.DELETE_URL, data, options={"dataAsParams": True})

skills/18072937735/smyx-outdoor-monitoring-analysis/skills/face_analysis/scripts/config.py

@@ -1,40 +0,0 @@
-#!/usr/bin/env python3
-# 中医面诊分析工具配置文件
-import os
-import sys
-
-from enum import Enum
-
-from skills.smyx_common.scripts.config import ApiEnum as ApiEnumBase, ConstantEnum as ConstantEnumBase
-
-SceneCodeEnum = ConstantEnumBase.SceneCodeEnum
-
-
-class ApiEnum(ApiEnumBase):
-    ANALYSIS_URL = "/web/health-analysis/v2/start-health-analysis"
-
-    ANALYSIS_RESULT_URL = "/web/health-analysis/get-health-analysis-result"
-
-    PAGE_URL = "/web/health-analysis/page-health-analysis-result"
-
-    DETAIL_EXPORT_URL = ApiEnumBase.BASE_URL_HEALTH + "/health/order/api/getReportDetailExport?id="
-
-    @classmethod
-    def init(cls, config=None):
-        super().init(config)
-
-
-class ApiEnumCommonAiMixin:
-
-    @classmethod
-    def init(cls, config=None):
-        parent = super()
-        if hasattr(parent, "init"):
-            parent.init(config)
-        ApiEnum.ANALYSIS_URL = "/web/ai-analysis/v2/start-common-ai-analysis"
-        ApiEnum.ANALYSIS_RESULT_URL = "/web/ai-analysis/get-common-ai-analysis-result"
-        ApiEnum.PAGE_URL = "/web/ai-analysis/page-common-ai-analysis-result"
-
-
-class ConstantEnum(ConstantEnumBase):
-    DEFAULT__APP_CATEGORY = "PEI_NI_AN"

skills/18072937735/smyx-outdoor-monitoring-analysis/skills/face_analysis/scripts/config.yaml

@@ -1 +0,0 @@
-{}

skills/18072937735/smyx-outdoor-monitoring-analysis/skills/face_analysis/scripts/face_analysis.py

@@ -1,205 +0,0 @@
-#!/usr/bin/env python3
-import sys
-import os
-
-current_dir = os.path.dirname(os.path.abspath(__file__))
-parent_dir = os.path.dirname(os.path.dirname(os.path.dirname(current_dir)))
-sys.path.insert(0, parent_dir)
-
-import argparse
-import json
-import mimetypes
-import traceback
-from datetime import datetime
-
-import requests
-import sys
-import os
-
-from .config import *
-
-from .skill import skill
-
-# import_path_common()
-from skills.smyx_common.scripts.util import RequestUtil
-
-# 从config导入常量
-SUPPORTED_FORMATS = ConstantEnum.SUPPORTED_FORMATS
-MAX_FILE_SIZE_MB = ConstantEnum.MAX_FILE_SIZE_MB
-
-
-def validate_file(file_path):
-    """验证输入文件是否合法"""
-    if not os.path.exists(file_path):
-        raise FileNotFoundError(f"文件不存在: {file_path}")
-
-    if not os.access(file_path, os.R_OK):
-        raise PermissionError(f"文件没有读权限: {file_path}")
-
-    ext = os.path.splitext(file_path)[1].lower()[1:]
-    if ext not in SUPPORTED_FORMATS:
-        raise ValueError(f"不支持的文件格式，支持的格式: {', '.join(SUPPORTED_FORMATS)}")
-
-    file_size_mb = os.path.getsize(file_path) / (1024 * 1024)
-    if file_size_mb > MAX_FILE_SIZE_MB:
-        raise ValueError(f"文件过大，最大支持 {MAX_FILE_SIZE_MB}MB，当前文件大小: {file_size_mb:.1f}MB")
-
-    return True
-
-
-def analyze_video(input_path=None, url=None, api_url=None, api_key=None, output_level=None):
-    """调用API分析视频"""
-    if not input_path and not url:
-        raise ValueError("必须提供本地视频路径(--input)或网络视频URL(--url)")
-    try:
-        input_path = input_path or url
-        return skill.get_output_analysis(input_path)
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def show_analyze_list(open_id, start_time=None, end_time=None):
-    # if not open_id:
-    #     raise ValueError("必须提供本用户的OpenId/UserId")
-
-    try:
-        output_content = skill.get_output_analysis_list()
-        return output_content
-
-    except requests.exceptions.RequestException as e:
-        traceback.print_stack()
-        raise Exception(f"API请求失败: {str(e)}")
-
-
-def get_analysis_export_url(request_id=None):
-    """调用API分析视频"""
-    if not request_id:
-        return ""
-    return ApiEnum.DETAIL_EXPORT_URL + request_id
-
-
-def format_result(result, output_level="standard"):
-    """格式化输出结果"""
-    if output_level == "json":
-        result_id = None
-        # if result.get('success'):
-        if result is not None:
-            result_json = result
-            result_id = result_json.get('id', {})
-            result_json = json.dumps(result_json.get('faceAnalysisResponse', {}), ensure_ascii=False, indent=2)
-        else:
-            # result_json = json.dumps(result, ensure_ascii=False, indent=2)
-            return "⚠️ 暂无分析结果"
-        return f"""
-📊 面诊分析结构化结果
-{result_json}
-""", result_id
-    elif output_level == "basic":
-        # 精简输出
-        data = result.get('data', {})
-        diagnosis = data.get('diagnosis', {})
-        return f"""
-📊 面诊分析结果
-{'=' * 40}
-整体体质: {diagnosis.get('overall_constitution', '未知')}
-主要状况: {', '.join([f'{k}: {v}' for k, v in diagnosis.get('organ_condition', {}).items() if v != '正常'])}
-健康提示: {data.get('health_warnings', ['无特殊警示'])[0] if data.get('health_warnings') else '无特殊警示'}
-        """
-    elif output_level == "standard":
-        # 标准输出
-        data = result.get('data', {})
-        diagnosis = data.get('diagnosis', {})
-        face_detection = data.get('face_detection', {})
-
-        organ_status = "\n".join([f"  {k}: {v}" for k, v in diagnosis.get('organ_condition', {}).items()])
-        warnings = "\n".join([f"  ⚠️  {item}" for item in data.get('health_warnings', [])])
-        suggestions = "\n".join([f"  💡 {item}" for item in data.get('suggestions', [])])
-
-        return f"""
-📊 中医面诊分析报告
-{'=' * 50}
-⏰ 分析时间: {data.get('analysis_time', '未知')}
-🎯 人脸检测: {face_detection.get('status', '未知')} (置信度: {face_detection.get('quality_score', 0)}分)
-
-🔍 诊断结果:
-  整体体质: {diagnosis.get('overall_constitution', '未知')}
-  脏腑状况:
-{organ_status}
-  面色分析: {diagnosis.get('color_analysis', {}).get('complexion', '未知')}
-  对应提示: {diagnosis.get('color_analysis', {}).get('correspondence', '未知')}
-
-⚠️ 健康警示:
-{warnings}
-
-💡 养生建议:
-{suggestions}
-{'=' * 50}
-        """
-    else:
-        # 完整输出（JSON格式）
-        return json.dumps(result, ensure_ascii=False, indent=2)
-
-
-def main():
-    parser = argparse.ArgumentParser(description="中医面诊分析工具")
-    parser.add_argument("--input", help="本地MP4视频文件路径")
-    parser.add_argument("--url", help="网络视频MP4的URL地址")
-    parser.add_argument("--open-id", required=True, help="当前用户的OpenID/UserId/用户名/手机号")
-    parser.add_argument("--list", action='store_true', help="显示面诊视频历史列表清单")
-    parser.add_argument("--api-url", help="服务端API地址")
-    parser.add_argument("--api-key", help="API访问密钥（必需）")
-    parser.add_argument("--output", help="结果输出文件路径")
-    parser.add_argument("--detail", choices=["basic", "standard", "json"],
-                        default=ConstantEnum.DEFAULT__OUTPUT_LEVEL,
-                        help="输出详细程度")
-    parser.add_argument("--export-env-only", action='store_true',
-                        help="仅输出 export 命令设置环境变量，不执行分析")
-
-    args = parser.parse_args()
-
-    try:
-        if args.open_id:
-            ConstantEnumBase.CURRENT__OPEN_ID = args.open_id
-
-        # 检查必需参数
-        if args.list:
-            open_id = ConstantEnum.CURRENT__OPEN_ID
-            result = show_analyze_list(open_id)
-            print(result)
-            exit(0)
-
-        # 检查必需参数
-        if not args.input and not args.url:
-            print("❌ 错误: 必须提供 --input 或 --url 参数")
-            exit(1)
-
-        print("🔍 正在分析面诊视频，请稍候...")
-        output_content = analyze_video(
-            input_path=args.input,
-            url=args.url,
-            api_url=args.api_url,
-            api_key=args.api_key,
-            output_level=args.detail
-        )
-
-        print(output_content)
-
-        # 保存到文件
-        if args.output:
-            with open(args.output, "w", encoding="utf-8") as f:
-                if args.detail == "full":
-                    json.dump(result, f, ensure_ascii=False, indent=2)
-                else:
-                    f.write(output_content)
-            print(f"✅ 结果已保存到: {args.output}")
-
-    except Exception as e:
-        traceback.print_stack()
-        print(f"❌ 面诊分析失败: {str(e)}")
-        exit(1)
-
-
-if __name__ == "__main__":
-    main()