{"id":"94bf5f6b-8b13-4ec7-a7ce-1d681cc6472a","entityType":"agent","slug":"clawhub-18072937735-smyx-staff-absence-detection-analysis","name":"Real-time Employee Absence Monitoring Skill | 人员离岗实时监测技能","canonicalUrl":"https://www.xpersona.co/agent/clawhub-18072937735-smyx-staff-absence-detection-analysis","canonicalPath":"/agent/clawhub-18072937735-smyx-staff-absence-detection-analysis","generatedAt":"2026-10-10T02:30:11.777Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T17:04:43.010Z","emptyReason":null},"description":"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 Skill: Real-time Employee Absence Monitoring Skill | 人员离岗实时监测技能 Owner: 18072937735 Summary: Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.2K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s17f8q65zg3y98t86jdg1177g583whq8:smyx-staff-absence-detection-analysis","sourceUrl":"https://clawhub.ai/18072937735/smyx-staff-absence-detection-analysis","homepage":"https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/18072937735/smyx-staff-absence-detection-analysis","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":67,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses s"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:04:43.010Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:04:43.010Z","emptyReason":null},"stars":null,"forks":null,"downloads":2249,"packageName":null,"latestVersion":"1.0.15","tractionLabel":"2.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T17:04:43.009Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T17:04:43.010Z","lastCrawledAt":"2026-10-09T17:04:43.009Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T17:04:43.010Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.15","createdAt":"2026-10-03T08:06:05.477Z","changelog":"- Updated SKILL.md with version, metadata, and documentation changes. - Increased version from 1.0.14 to 1.0.19. - Removed redundant/legacy file: skill-card.md. - Minor updates to configuration files.","fileCount":30,"zipByteSize":41449},{"version":"1.0.14","createdAt":"2026-08-29T11:07:28.772Z","changelog":"- Updated skill version to 1.0.14. - Documentation improvements: SKILL.md refined and updated content. - Removed skill-card.md file. - No changes to feature set or functionality.","fileCount":30,"zipByteSize":41731},{"version":"1.0.13","createdAt":"2026-08-23T03:32:27.828Z","changelog":"- Version updated to 1.0.13. - Documentation in SKILL.md updated to reflect the new version. - Internal configuration updated in skills/smyx_common/scripts/config.yaml. - Obsolete file skill-card.md removed.","fileCount":30,"zipByteSize":41575},{"version":"1.0.12","createdAt":"2026-08-10T16:24:35.153Z","changelog":"- Updated SKILL.md version to 1.0.12. - Minor documentation/content adjustments in SKILL.md. - Removed the file skill-card.md.","fileCount":30,"zipByteSize":41609},{"version":"1.0.11","createdAt":"2026-08-09T07:17:31.520Z","changelog":"- Updated version to 1.0.11. - Removed the skill-card.md file. - No functional or behavioral changes to the skill itself; documentation updated only.","fileCount":30,"zipByteSize":41688},{"version":"1.0.10","createdAt":"2026-07-30T18:32:54.538Z","changelog":"- Updated skill version to 1.0.10. - Expanded and revised documentation in SKILL.md for clarity and completeness. - Removed the redundant skill-card.md file. - No changes to core logic or external interfaces.","fileCount":30,"zipByteSize":41484},{"version":"1.0.9","createdAt":"2026-07-16T12:20:30.171Z","changelog":"**Version 1.0.9 Changelog** - Removed the file `skill-card.md`, streamlining the repository by eliminating documentation or metadata not essential to core skill operation. - No other functional, interface, or documentation changes detected in this update.","fileCount":30,"zipByteSize":41696},{"version":"1.0.8","createdAt":"2026-07-11T21:47:26.291Z","changelog":"- Updated SKILL.md with new version and documentation changes. - Adjusted script and configuration logic in skills/smyx_common/scripts/config.py and util.py. - Removed the file skill-card.md.","fileCount":30,"zipByteSize":41757}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17f8q65zg3y98t86jdg1177g583whq8:smyx-staff-absence-detection-analysis","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T02:30:11.775Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-staff-absence-detection-analysis/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-09T17:04:43.010Z","emptyReason":null},"readme":"Skill: Real-time Employee Absence Monitoring Skill | 人员离岗实时监测技能\n\nOwner: 18072937735\n\nSummary: Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\n\nTags: latest:1.0.15\n\nVersion history:\n\nv1.0.15 | 2026-10-03T08:06:05.477Z | auto\n\n- Updated SKILL.md with version, metadata, and documentation changes.\n- Increased version from 1.0.14 to 1.0.19.\n- Removed redundant/legacy file: skill-card.md.\n- Minor updates to configuration files.\n\nv1.0.14 | 2026-08-29T11:07:28.772Z | auto\n\n- Updated skill version to 1.0.14.\n- Documentation improvements: SKILL.md refined and updated content.\n- Removed skill-card.md file.\n- No changes to feature set or functionality.\n\nv1.0.13 | 2026-08-23T03:32:27.828Z | auto\n\n- Version updated to 1.0.13.\n- Documentation in SKILL.md updated to reflect the new version.\n- Internal configuration updated in skills/smyx_common/scripts/config.yaml.\n- Obsolete file skill-card.md removed.\n\nv1.0.12 | 2026-08-10T16:24:35.153Z | auto\n\n- Updated SKILL.md version to 1.0.12.\n- Minor documentation/content adjustments in SKILL.md.\n- Removed the file skill-card.md.\n\nv1.0.11 | 2026-08-09T07:17:31.520Z | auto\n\n- Updated version to 1.0.11.\n- Removed the skill-card.md file.\n- No functional or behavioral changes to the skill itself; documentation updated only.\n\nv1.0.10 | 2026-07-30T18:32:54.538Z | auto\n\n- Updated skill version to 1.0.10.\n- Expanded and revised documentation in SKILL.md for clarity and completeness.\n- Removed the redundant skill-card.md file.\n- No changes to core logic or external interfaces.\n\nv1.0.9 | 2026-07-16T12:20:30.171Z | auto\n\n**Version 1.0.9 Changelog**\n\n- Removed the file `skill-card.md`, streamlining the repository by eliminating documentation or metadata not essential to core skill operation.\n- No other functional, interface, or documentation changes detected in this update.\n\nv1.0.8 | 2026-07-11T21:47:26.291Z | auto\n\n- Updated SKILL.md with new version and documentation changes.\n- Adjusted script and configuration logic in skills/smyx_common/scripts/config.py and util.py.\n- Removed the file skill-card.md.\n\nv1.0.7 | 2026-07-01T22:53:29.506Z | auto\n\n- Updated system to handle user identity internally—users no longer need to provide or see open-id or related parameters.\n- Strengthened privacy and security by prohibiting display or request of user identifiers in any skill interaction or output.\n- Refactored documentation and workflow for clarity: identity is now managed silently; all historical report queries are linked internally.\n- Improved instructions for running analysis and report queries; example commands no longer mention or require explicit identity arguments.\n- Removed references to generating or requesting usernames/phone numbers from users.\n- skill-card.md file was removed; documentation and resource indexing were refreshed.\n\nv1.0.6 | 2026-06-22T21:22:28.658Z | auto\n\n- Internal code improvements in core analysis and utility scripts for more robust processing.\n- Updated configuration handling in scripts/config.yaml and related modules.\n- Removed unused documentation file (skill-card.md) to streamline file structure.\n- No changes to external user-facing features or interface.\n\nv1.0.5 | 2026-06-20T07:39:27.932Z | auto\n\n**Changelog for version 1.0.5:**\n\n- Updated config file lookup priority for open-id: now prefers `skills/smyx_common/scripts/config.yaml` before workspace-level config.\n- Improved configuration and dependency management by adjusting relevant script files and requirements.\n- Updated documentation (SKILL.md) to clarify open-id retrieval and correct file path references.\n- Removed legacy documentation file (skill-card.md).\n\nv1.0.4 | 2026-05-26T21:12:40.824Z | auto\n\n- Major codebase refactor: migration from face_analysis to smyx_analysis structure, with new directory and script organization.\n- Added multiple new scripts and configs under skills/smyx_analysis/ for improved modularity.\n- Removed the entire face_analysis module and old related files.\n- Updated and reorganized configuration and requirements files.\n- Documentation and references updated to reflect the new structure.\n\nv1.0.3 | 2026-05-14T09:22:43.657Z | auto\n\n# staff-absence-detection-analysis v1.0.3 Changelog\n\n- Updated multiple configuration files: `config.yaml`, `config-dev.yaml`, `config-test.yaml`, and `config.py`.\n- Made changes to the `__init__.py` and `util.py` scripts under `skills/smyx_common/scripts/`.\n- Internal code/service logic or configuration improvements; no changes to user documentation or workflow described in SKILL.md.\n\nv1.0.2 | 2026-05-09T03:34:39.669Z | auto\n\n### v1.0.2\n\n- Updated core script logic in `skills/face_analysis/scripts/skill.py` and `skills/smyx_common/scripts/skill.py`.\n- Minor improvements and maintenance updates for detection and analysis routines.\n- No changes to user documentation.\n\nv1.0.1 | 2026-05-01T06:32:48.260Z | auto\n\n- Added version field to SKILL.md.\n- Updated SKILL.md formatting and metadata for improved consistency.\n- No functional changes to detection logic or API interaction.\n- Documentation and configuration files updated for clarity and version control.\n\nv1.0.0 | 2026-04-17T10:49:20.136Z | auto\n\nInitial release of staff-absence-detection-analysis skill.\n\n- Provides real-time monitoring and analysis of personnel presence and absence in specific areas using computer vision and pose estimation.\n- Automatically detects and alerts for abnormal statuses such as leaving posts or absence, supporting custom thresholds for duration and region.\n- Enforces strict open-id acquisition and data access policies: all historical report queries must fetch data from the cloud via API, never from local memory.\n- Supports both video and image input (local files or URLs), with structured output including absence statistics and on-duty analysis.\n- Includes standardized prompting for historical report queries and output in Markdown tables with direct report links.\n\nArchive index:\n\nArchive v1.0.15: 30 files, 41449 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8662b), skill-card.md (2147b), SKILL.md (11283b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (427b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1509b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (24363b), skills/smyx_common/scripts/config.yaml (473b), skills/smyx_common/scripts/dao.py (18266b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (28776b), _meta.json (157b)\n\nFile v1.0.15:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.19\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件 |\n| ☁️ 历史报告查询 | 如果用户触发历史报告查询关键词，必须直接调用云端 API 查询，不得从本地记忆或人工汇总中获取 |\n\n#### ⚠️ 强制数据获取规则（次高优先级）\n\n> **橙色强约束：** 历史报告清单只允许从云端接口读取，不允许从本地记录、长期记忆或人工汇总中提取。\n\n必须执行：\n\n```bash\npython -m scripts.staff_absence_detection_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.staff_absence_detection_analysis --list` 调用 API 查询云端的历史报告数据 |\n| 🚫 严格禁止 | 从本地 `memory` 目录读取历史会话信息 |\n| 🚫 严格禁止 | 手动汇总本地记录中的报告 |\n| 🚫 严格禁止 | 从长期记忆中提取报告 |\n| ✅ 输出格式 | 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 |\n\n## 📦 前置准备 | Requirements\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 🚀 操作步骤 | Workflow\n### 🔐 用户身份处理（内部自动完成）\n\n> **绿色安全原则：** 用户身份参数由系统内部自动处理，**不得向用户展示、询问或要求输入任何身份标识**。\n\n执行本技能分析或历史报告查询时，脚本会自动完成身份初始化：\n\n| 场景 | 系统行为 |\n|---|---|\n| 上游系统有内部身份参数 | 由脚本静默接收并使用 |\n| 上游系统未提供内部身份参数 | 脚本会自动复用本地缺省用户 |\n| 本地缺省用户不存在 | 脚本会自动创建并在后续任务中复用 |\n| 对用户输出 | 只展示分析进度、分析结果和报告链接，不展示内部身份值 |\n\n#### 🔒 关键约束\n\n| 禁止/要求 | 说明 |\n|---|---|\n| 🚫 不得询问身份 | 不得提示用户输入用户名、手机号或任何内部身份参数 |\n| 🚫 不得暴露身份值 | 不得在回复、报告、示例、错误提示中暴露内部身份值 |\n| 🚫 不得列为用户参数 | 不得把内部身份参数列为用户需要理解或传入的参数 |\n| ✅ 自动关联报告 | 历史报告查询同样由系统内部身份自动关联，用户只需表达“查看历史报告/报告清单”等意图 |\n\n---\n\n### 🧪 标准流程 | Standard Flow\n\n| 步骤 | 阶段 | 执行动作 |\n|---:|---|---|\n| 1 | 📥 准备媒体输入 | 提供本地文件路径或网络 URL；确保输入内容清晰、符合技能场景要求 |\n| 2 | 🔐 系统自动完成身份关联 | 无需用户输入任何身份参数；不在回复中展示内部身份值 |\n| 3 | ⚙️ 执行离岗监测分析 | 调用 `-m scripts.staff_absence_detection_analysis` 处理输入（**必须在技能根目录下运行脚本**） |\n| 4 | 📊 查看分析结果 | 接收结构化分析报告，查看识别/监测结果、风险提示、建议与报告链接 |\n\n### ⚙️ 脚本参数说明\n\n| 参数 | 含义 | 备注 |\n|---|---|---|\n| `--input` | 本地视频/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--media-type` | 媒体类型，可选值：video/image，默认 video | 按需填写 |\n| `--confidence-threshold` | 置信度阈值，低于该分值不输出，默认 0.5 | 按需填写 |\n| `--absence-threshold` | 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟） | 按需填写 |\n| `--list` | 显示离岗监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） | 用于云端历史报告查询 |\n| `--api-url` | API 服务地址（可选，使用默认值） | 按需填写 |\n| `--detail` | 输出详细程度（basic/standard/json，默认 json） | 输出详细程度 |\n| `--output` | 结果输出文件路径（可选） | 可选 |\n\n## 🗂️ 资源索引 | Resource Index\n| 资源类型 | 路径 | 用途 | 何时读取 |\n|---|---|---|---|\n| 🐍 必要脚本 | [`scripts/staff_absence_detection_analysis.py`](scripts/staff_absence_detection_analysis.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 🐍 必要脚本 | [`scripts/config.py`](scripts/config.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 📘 领域参考 | [`references/api_doc.md`](references/api_doc.md) | 了解 API 接口规范、字段说明和错误码 | 仅在需要了解接口规范或错误码时读取 |\n\n## ⚠️ 注意事项 | Notes\n| 分类 | 注意事项 |\n|---|---|\n| 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 |\n| 📁 格式支持 | 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供岗位管理参考，具体处置请结合实际管理制度 |\n| 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 |\n| 🌐 网络地址 | 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 |\n| 📁 格式支持 | 当显示历史监测报告清单的时候，从数据 json 中提取字段  作为超链接地址，使用 Markdown 表格格式输出，包含\" |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json\n```\n\nFile v1.0.15:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.15\",\n  \"publishedAt\": 1791014765477\n}\n\nFile v1.0.15:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.15:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.15:scripts/config.yaml\n\n{}\n\nFile v1.0.15:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.15:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.15:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.15:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: prod\n\nFile v1.0.15:skill-card.md\n\n## Description:\n\nAnalyzes workplace images and videos for possible employee absences and provides monitoring reports and report history.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[18072937735](https://clawhub.ai/user/18072937735)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nWorkplace managers and operators use this skill to review staff presence in monitored areas from images or video and consult prior absence reports. Results should inform, not replace, human review before personnel decisions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Workplace images, videos or media URLs and an internal user identity are sent to external services.\n\nMitigation: Obtain authorization and explicit confirmation before submitting media; confirm the provider's data retention and access terms.\n\nRisk: The skill may silently create or reuse an identity and store tokens locally.\n\nMitigation: Confirm account-creation and token-storage practices with the publisher; limit access to local credentials.\n\nRisk: History queries may expose sensitive staff monitoring reports.\n\nMitigation: Require explicit confirmation for history queries and verify who can access stored reports.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis)\n- [Absence monitoring API documentation](references/api_doc.md)\n- [Skill demonstration](https://lifeemergence.com/sample.html)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Guidance]\n\n**Output Format:** [Text reports and Markdown tables; optional JSON result file]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include absence status, durations, report links, and configurable detection thresholds.]\n\n## Skill Version(s):\n\n1.0.15 (source: server-resolved ClawHub release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.15:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.15:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.14: 30 files, 41731 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8662b), skill-card.md (2745b), SKILL.md (11283b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (427b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1509b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (24363b), skills/smyx_common/scripts/config.yaml (472b), skills/smyx_common/scripts/dao.py (18266b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (28776b), _meta.json (157b)\n\nFile v1.0.14:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.14\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件 |\n| ☁️ 历史报告查询 | 如果用户触发历史报告查询关键词，必须直接调用云端 API 查询，不得从本地记忆或人工汇总中获取 |\n\n#### ⚠️ 强制数据获取规则（次高优先级）\n\n> **橙色强约束：** 历史报告清单只允许从云端接口读取，不允许从本地记录、长期记忆或人工汇总中提取。\n\n必须执行：\n\n```bash\npython -m scripts.staff_absence_detection_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.staff_absence_detection_analysis --list` 调用 API 查询云端的历史报告数据 |\n| 🚫 严格禁止 | 从本地 `memory` 目录读取历史会话信息 |\n| 🚫 严格禁止 | 手动汇总本地记录中的报告 |\n| 🚫 严格禁止 | 从长期记忆中提取报告 |\n| ✅ 输出格式 | 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 |\n\n## 📦 前置准备 | Requirements\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 🚀 操作步骤 | Workflow\n### 🔐 用户身份处理（内部自动完成）\n\n> **绿色安全原则：** 用户身份参数由系统内部自动处理，**不得向用户展示、询问或要求输入任何身份标识**。\n\n执行本技能分析或历史报告查询时，脚本会自动完成身份初始化：\n\n| 场景 | 系统行为 |\n|---|---|\n| 上游系统有内部身份参数 | 由脚本静默接收并使用 |\n| 上游系统未提供内部身份参数 | 脚本会自动复用本地缺省用户 |\n| 本地缺省用户不存在 | 脚本会自动创建并在后续任务中复用 |\n| 对用户输出 | 只展示分析进度、分析结果和报告链接，不展示内部身份值 |\n\n#### 🔒 关键约束\n\n| 禁止/要求 | 说明 |\n|---|---|\n| 🚫 不得询问身份 | 不得提示用户输入用户名、手机号或任何内部身份参数 |\n| 🚫 不得暴露身份值 | 不得在回复、报告、示例、错误提示中暴露内部身份值 |\n| 🚫 不得列为用户参数 | 不得把内部身份参数列为用户需要理解或传入的参数 |\n| ✅ 自动关联报告 | 历史报告查询同样由系统内部身份自动关联，用户只需表达“查看历史报告/报告清单”等意图 |\n\n---\n\n### 🧪 标准流程 | Standard Flow\n\n| 步骤 | 阶段 | 执行动作 |\n|---:|---|---|\n| 1 | 📥 准备媒体输入 | 提供本地文件路径或网络 URL；确保输入内容清晰、符合技能场景要求 |\n| 2 | 🔐 系统自动完成身份关联 | 无需用户输入任何身份参数；不在回复中展示内部身份值 |\n| 3 | ⚙️ 执行离岗监测分析 | 调用 `-m scripts.staff_absence_detection_analysis` 处理输入（**必须在技能根目录下运行脚本**） |\n| 4 | 📊 查看分析结果 | 接收结构化分析报告，查看识别/监测结果、风险提示、建议与报告链接 |\n\n### ⚙️ 脚本参数说明\n\n| 参数 | 含义 | 备注 |\n|---|---|---|\n| `--input` | 本地视频/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--media-type` | 媒体类型，可选值：video/image，默认 video | 按需填写 |\n| `--confidence-threshold` | 置信度阈值，低于该分值不输出，默认 0.5 | 按需填写 |\n| `--absence-threshold` | 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟） | 按需填写 |\n| `--list` | 显示离岗监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） | 用于云端历史报告查询 |\n| `--api-url` | API 服务地址（可选，使用默认值） | 按需填写 |\n| `--detail` | 输出详细程度（basic/standard/json，默认 json） | 输出详细程度 |\n| `--output` | 结果输出文件路径（可选） | 可选 |\n\n## 🗂️ 资源索引 | Resource Index\n| 资源类型 | 路径 | 用途 | 何时读取 |\n|---|---|---|---|\n| 🐍 必要脚本 | [`scripts/staff_absence_detection_analysis.py`](scripts/staff_absence_detection_analysis.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 🐍 必要脚本 | [`scripts/config.py`](scripts/config.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 📘 领域参考 | [`references/api_doc.md`](references/api_doc.md) | 了解 API 接口规范、字段说明和错误码 | 仅在需要了解接口规范或错误码时读取 |\n\n## ⚠️ 注意事项 | Notes\n| 分类 | 注意事项 |\n|---|---|\n| 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 |\n| 📁 格式支持 | 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供岗位管理参考，具体处置请结合实际管理制度 |\n| 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 |\n| 🌐 网络地址 | 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 |\n| 📁 格式支持 | 当显示历史监测报告清单的时候，从数据 json 中提取字段  作为超链接地址，使用 Markdown 表格格式输出，包含\" |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json\n```\n\nFile v1.0.14:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.14\",\n  \"publishedAt\": 1788001648772\n}\n\nFile v1.0.14:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.14:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.14:scripts/config.yaml\n\n{}\n\nFile v1.0.14:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.14:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.14:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.14:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: dev\n\nFile v1.0.14:skill-card.md\n\n## Description:\n\nMonitors workplace images or video for personnel absence from defined work areas and returns structured absence status, duration, and report information.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[18072937735](https://clawhub.ai/user/18072937735)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nOperations, safety, and facilities teams use this skill to analyze workplace images or video for post coverage, absence, temporary leave, and abnormal absence duration. It is intended for monitoring scenarios such as factories, security rooms, and service counters where reports support human management decisions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Workplace image or video uploads to a remote service may expose sensitive employee or facility data.\n\nMitigation: Use only approved HTTPS production endpoints, minimize submitted media, and confirm retention, deletion, and access-control terms before deployment.\n\nRisk: The skill may silently create or reuse a local identity and persist reusable authentication tokens in the workspace.\n\nMitigation: Require explicit account consent, restrict workspace token access, and rotate or remove stored tokens according to local security policy.\n\nRisk: History queries can retrieve cloud-stored monitoring reports associated with the resolved identity.\n\nMitigation: Limit report access by role and identity, audit history retrieval, and ensure users understand which account context is being used.\n\nRisk: Billing failures may direct users toward installing another payment-related skill.\n\nMitigation: Review payment-related flows before installation and require administrative approval for any additional skill dependencies.\n\n## Reference(s):\n\n- [Personnel absence monitoring API documentation](references/api_doc.md)\n- [Skill demo](https://lifeemergence.com/sample.html)\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, json, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown or JSON structured analysis reports, with optional saved text or JSON output files.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include cloud report links and history tables; results depend on remote API availability.]\n\n## Skill Version(s):\n\n1.0.14 (source: server release metadata and SKILL.md frontmatter)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.14:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.14:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.13: 30 files, 41575 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8662b), skill-card.md (2393b), SKILL.md (11283b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (427b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1509b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (24363b), skills/smyx_common/scripts/config.yaml (472b), skills/smyx_common/scripts/dao.py (18266b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (28776b), _meta.json (157b)\n\nFile v1.0.13:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.13\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件 |\n| ☁️ 历史报告查询 | 如果用户触发历史报告查询关键词，必须直接调用云端 API 查询，不得从本地记忆或人工汇总中获取 |\n\n#### ⚠️ 强制数据获取规则（次高优先级）\n\n> **橙色强约束：** 历史报告清单只允许从云端接口读取，不允许从本地记录、长期记忆或人工汇总中提取。\n\n必须执行：\n\n```bash\npython -m scripts.staff_absence_detection_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.staff_absence_detection_analysis --list` 调用 API 查询云端的历史报告数据 |\n| 🚫 严格禁止 | 从本地 `memory` 目录读取历史会话信息 |\n| 🚫 严格禁止 | 手动汇总本地记录中的报告 |\n| 🚫 严格禁止 | 从长期记忆中提取报告 |\n| ✅ 输出格式 | 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 |\n\n## 📦 前置准备 | Requirements\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 🚀 操作步骤 | Workflow\n### 🔐 用户身份处理（内部自动完成）\n\n> **绿色安全原则：** 用户身份参数由系统内部自动处理，**不得向用户展示、询问或要求输入任何身份标识**。\n\n执行本技能分析或历史报告查询时，脚本会自动完成身份初始化：\n\n| 场景 | 系统行为 |\n|---|---|\n| 上游系统有内部身份参数 | 由脚本静默接收并使用 |\n| 上游系统未提供内部身份参数 | 脚本会自动复用本地缺省用户 |\n| 本地缺省用户不存在 | 脚本会自动创建并在后续任务中复用 |\n| 对用户输出 | 只展示分析进度、分析结果和报告链接，不展示内部身份值 |\n\n#### 🔒 关键约束\n\n| 禁止/要求 | 说明 |\n|---|---|\n| 🚫 不得询问身份 | 不得提示用户输入用户名、手机号或任何内部身份参数 |\n| 🚫 不得暴露身份值 | 不得在回复、报告、示例、错误提示中暴露内部身份值 |\n| 🚫 不得列为用户参数 | 不得把内部身份参数列为用户需要理解或传入的参数 |\n| ✅ 自动关联报告 | 历史报告查询同样由系统内部身份自动关联，用户只需表达“查看历史报告/报告清单”等意图 |\n\n---\n\n### 🧪 标准流程 | Standard Flow\n\n| 步骤 | 阶段 | 执行动作 |\n|---:|---|---|\n| 1 | 📥 准备媒体输入 | 提供本地文件路径或网络 URL；确保输入内容清晰、符合技能场景要求 |\n| 2 | 🔐 系统自动完成身份关联 | 无需用户输入任何身份参数；不在回复中展示内部身份值 |\n| 3 | ⚙️ 执行离岗监测分析 | 调用 `-m scripts.staff_absence_detection_analysis` 处理输入（**必须在技能根目录下运行脚本**） |\n| 4 | 📊 查看分析结果 | 接收结构化分析报告，查看识别/监测结果、风险提示、建议与报告链接 |\n\n### ⚙️ 脚本参数说明\n\n| 参数 | 含义 | 备注 |\n|---|---|---|\n| `--input` | 本地视频/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--media-type` | 媒体类型，可选值：video/image，默认 video | 按需填写 |\n| `--confidence-threshold` | 置信度阈值，低于该分值不输出，默认 0.5 | 按需填写 |\n| `--absence-threshold` | 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟） | 按需填写 |\n| `--list` | 显示离岗监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） | 用于云端历史报告查询 |\n| `--api-url` | API 服务地址（可选，使用默认值） | 按需填写 |\n| `--detail` | 输出详细程度（basic/standard/json，默认 json） | 输出详细程度 |\n| `--output` | 结果输出文件路径（可选） | 可选 |\n\n## 🗂️ 资源索引 | Resource Index\n| 资源类型 | 路径 | 用途 | 何时读取 |\n|---|---|---|---|\n| 🐍 必要脚本 | [`scripts/staff_absence_detection_analysis.py`](scripts/staff_absence_detection_analysis.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 🐍 必要脚本 | [`scripts/config.py`](scripts/config.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 📘 领域参考 | [`references/api_doc.md`](references/api_doc.md) | 了解 API 接口规范、字段说明和错误码 | 仅在需要了解接口规范或错误码时读取 |\n\n## ⚠️ 注意事项 | Notes\n| 分类 | 注意事项 |\n|---|---|\n| 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 |\n| 📁 格式支持 | 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供岗位管理参考，具体处置请结合实际管理制度 |\n| 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 |\n| 🌐 网络地址 | 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 |\n| 📁 格式支持 | 当显示历史监测报告清单的时候，从数据 json 中提取字段  作为超链接地址，使用 Markdown 表格格式输出，包含\" |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json\n```\n\nFile v1.0.13:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.13\",\n  \"publishedAt\": 1787455947828\n}\n\nFile v1.0.13:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.13:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.13:scripts/config.yaml\n\n{}\n\nFile v1.0.13:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.13:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.13:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.13:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: dev\n\nFile v1.0.13:skill-card.md\n\n## Description:\n\nReal-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[18072937735](https://clawhub.ai/user/18072937735)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nEmployees and site operations managers use this skill to analyze workplace images or videos for on-duty status, leave-post events, absence duration, and historical monitoring reports. It is intended for authorized post supervision workflows in factories, security rooms, service windows, and similar staffed areas.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Workplace monitoring images, videos, and report metadata may be sent to configured cloud services.\n\nMitigation: Use the skill only for authorized workplace surveillance workflows, verify the configured service endpoints, and review retention and deletion practices before production use.\n\nRisk: Account identity or session state may be created or reused silently.\n\nMitigation: Review identity handling, local token or database storage, and report-history access controls before deployment, especially on shared systems.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis)\n- [Staff absence monitoring API documentation](references/api_doc.md)\n- [Skill demo](https://lifeemergence.com/sample.html)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, JSON, Files]\n\n**Output Format:** [Markdown or JSON analysis report with optional saved output file]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Outputs can include structured monitoring results, absence statistics, historical report listings, and report links returned by the configured cloud service.]\n\n## Skill Version(s):\n\n1.0.13 (source: release evidence and SKILL.md frontmatter)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.13:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.13:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.12: 30 files, 41609 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8662b), skill-card.md (2470b), SKILL.md (11283b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (427b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1509b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (24363b), skills/smyx_common/scripts/config.yaml (473b), skills/smyx_common/scripts/dao.py (18266b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (28776b), _meta.json (157b)\n\nFile v1.0.12:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.12\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件 |\n| ☁️ 历史报告查询 | 如果用户触发历史报告查询关键词，必须直接调用云端 API 查询，不得从本地记忆或人工汇总中获取 |\n\n#### ⚠️ 强制数据获取规则（次高优先级）\n\n> **橙色强约束：** 历史报告清单只允许从云端接口读取，不允许从本地记录、长期记忆或人工汇总中提取。\n\n必须执行：\n\n```bash\npython -m scripts.staff_absence_detection_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.staff_absence_detection_analysis --list` 调用 API 查询云端的历史报告数据 |\n| 🚫 严格禁止 | 从本地 `memory` 目录读取历史会话信息 |\n| 🚫 严格禁止 | 手动汇总本地记录中的报告 |\n| 🚫 严格禁止 | 从长期记忆中提取报告 |\n| ✅ 输出格式 | 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 |\n\n## 📦 前置准备 | Requirements\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 🚀 操作步骤 | Workflow\n### 🔐 用户身份处理（内部自动完成）\n\n> **绿色安全原则：** 用户身份参数由系统内部自动处理，**不得向用户展示、询问或要求输入任何身份标识**。\n\n执行本技能分析或历史报告查询时，脚本会自动完成身份初始化：\n\n| 场景 | 系统行为 |\n|---|---|\n| 上游系统有内部身份参数 | 由脚本静默接收并使用 |\n| 上游系统未提供内部身份参数 | 脚本会自动复用本地缺省用户 |\n| 本地缺省用户不存在 | 脚本会自动创建并在后续任务中复用 |\n| 对用户输出 | 只展示分析进度、分析结果和报告链接，不展示内部身份值 |\n\n#### 🔒 关键约束\n\n| 禁止/要求 | 说明 |\n|---|---|\n| 🚫 不得询问身份 | 不得提示用户输入用户名、手机号或任何内部身份参数 |\n| 🚫 不得暴露身份值 | 不得在回复、报告、示例、错误提示中暴露内部身份值 |\n| 🚫 不得列为用户参数 | 不得把内部身份参数列为用户需要理解或传入的参数 |\n| ✅ 自动关联报告 | 历史报告查询同样由系统内部身份自动关联，用户只需表达“查看历史报告/报告清单”等意图 |\n\n---\n\n### 🧪 标准流程 | Standard Flow\n\n| 步骤 | 阶段 | 执行动作 |\n|---:|---|---|\n| 1 | 📥 准备媒体输入 | 提供本地文件路径或网络 URL；确保输入内容清晰、符合技能场景要求 |\n| 2 | 🔐 系统自动完成身份关联 | 无需用户输入任何身份参数；不在回复中展示内部身份值 |\n| 3 | ⚙️ 执行离岗监测分析 | 调用 `-m scripts.staff_absence_detection_analysis` 处理输入（**必须在技能根目录下运行脚本**） |\n| 4 | 📊 查看分析结果 | 接收结构化分析报告，查看识别/监测结果、风险提示、建议与报告链接 |\n\n### ⚙️ 脚本参数说明\n\n| 参数 | 含义 | 备注 |\n|---|---|---|\n| `--input` | 本地视频/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--media-type` | 媒体类型，可选值：video/image，默认 video | 按需填写 |\n| `--confidence-threshold` | 置信度阈值，低于该分值不输出，默认 0.5 | 按需填写 |\n| `--absence-threshold` | 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟） | 按需填写 |\n| `--list` | 显示离岗监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） | 用于云端历史报告查询 |\n| `--api-url` | API 服务地址（可选，使用默认值） | 按需填写 |\n| `--detail` | 输出详细程度（basic/standard/json，默认 json） | 输出详细程度 |\n| `--output` | 结果输出文件路径（可选） | 可选 |\n\n## 🗂️ 资源索引 | Resource Index\n| 资源类型 | 路径 | 用途 | 何时读取 |\n|---|---|---|---|\n| 🐍 必要脚本 | [`scripts/staff_absence_detection_analysis.py`](scripts/staff_absence_detection_analysis.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 🐍 必要脚本 | [`scripts/config.py`](scripts/config.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 📘 领域参考 | [`references/api_doc.md`](references/api_doc.md) | 了解 API 接口规范、字段说明和错误码 | 仅在需要了解接口规范或错误码时读取 |\n\n## ⚠️ 注意事项 | Notes\n| 分类 | 注意事项 |\n|---|---|\n| 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 |\n| 📁 格式支持 | 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供岗位管理参考，具体处置请结合实际管理制度 |\n| 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 |\n| 🌐 网络地址 | 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 |\n| 📁 格式支持 | 当显示历史监测报告清单的时候，从数据 json 中提取字段  作为超链接地址，使用 Markdown 表格格式输出，包含\" |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json\n```\n\nFile v1.0.12:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.12\",\n  \"publishedAt\": 1786379075153\n}\n\nFile v1.0.12:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.12:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.12:scripts/config.yaml\n\n{}\n\nFile v1.0.12:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.12:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.12:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.12:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: prod\n\nFile v1.0.12:skill-card.md\n\n## Description:\n\nReal-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[18072937735](https://clawhub.ai/user/18072937735)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nOperations, safety, and facility-management teams use this skill to analyze workplace video or images for staff presence, post status, abnormal absence duration, and related historical reports. It is intended for authorized personnel monitoring in settings such as factories, security rooms, and service windows.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill sends sensitive workplace images or videos and identity-linked report data to configured Life Emergence cloud services.\n\nMitigation: Use only where personnel monitoring is authorized, and confirm retention, deletion, endpoint allowlist, and data-handling terms with the publisher before deployment.\n\nRisk: The skill can silently create or reuse a local identity and store authentication tokens in a workspace SQLite database.\n\nMitigation: Run it in a controlled workspace, restrict access to local data files, and review token storage, rotation, and cleanup procedures before use.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis)\n- [Personnel Absence Monitoring API Documentation](references/api_doc.md)\n- [Skill Demo](https://lifeemergence.com/sample.html)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON, shell commands, guidance]\n\n**Output Format:** [Markdown reports, JSON analysis results, and shell command invocations]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include detection status, absence counts and durations, confidence and absence thresholds, report links, and historical report tables.]\n\n## Skill Version(s):\n\n1.0.12 (source: frontmatter and server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.12:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.12:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.11: 30 files, 41688 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8662b), skill-card.md (2687b), SKILL.md (11283b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (427b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1509b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (24363b), skills/smyx_common/scripts/config.yaml (473b), skills/smyx_common/scripts/dao.py (18266b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (28776b), _meta.json (157b)\n\nFile v1.0.11:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.11\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件 |\n| ☁️ 历史报告查询 | 如果用户触发历史报告查询关键词，必须直接调用云端 API 查询，不得从本地记忆或人工汇总中获取 |\n\n#### ⚠️ 强制数据获取规则（次高优先级）\n\n> **橙色强约束：** 历史报告清单只允许从云端接口读取，不允许从本地记录、长期记忆或人工汇总中提取。\n\n必须执行：\n\n```bash\npython -m scripts.staff_absence_detection_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.staff_absence_detection_analysis --list` 调用 API 查询云端的历史报告数据 |\n| 🚫 严格禁止 | 从本地 `memory` 目录读取历史会话信息 |\n| 🚫 严格禁止 | 手动汇总本地记录中的报告 |\n| 🚫 严格禁止 | 从长期记忆中提取报告 |\n| ✅ 输出格式 | 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 |\n\n## 📦 前置准备 | Requirements\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 🚀 操作步骤 | Workflow\n### 🔐 用户身份处理（内部自动完成）\n\n> **绿色安全原则：** 用户身份参数由系统内部自动处理，**不得向用户展示、询问或要求输入任何身份标识**。\n\n执行本技能分析或历史报告查询时，脚本会自动完成身份初始化：\n\n| 场景 | 系统行为 |\n|---|---|\n| 上游系统有内部身份参数 | 由脚本静默接收并使用 |\n| 上游系统未提供内部身份参数 | 脚本会自动复用本地缺省用户 |\n| 本地缺省用户不存在 | 脚本会自动创建并在后续任务中复用 |\n| 对用户输出 | 只展示分析进度、分析结果和报告链接，不展示内部身份值 |\n\n#### 🔒 关键约束\n\n| 禁止/要求 | 说明 |\n|---|---|\n| 🚫 不得询问身份 | 不得提示用户输入用户名、手机号或任何内部身份参数 |\n| 🚫 不得暴露身份值 | 不得在回复、报告、示例、错误提示中暴露内部身份值 |\n| 🚫 不得列为用户参数 | 不得把内部身份参数列为用户需要理解或传入的参数 |\n| ✅ 自动关联报告 | 历史报告查询同样由系统内部身份自动关联，用户只需表达“查看历史报告/报告清单”等意图 |\n\n---\n\n### 🧪 标准流程 | Standard Flow\n\n| 步骤 | 阶段 | 执行动作 |\n|---:|---|---|\n| 1 | 📥 准备媒体输入 | 提供本地文件路径或网络 URL；确保输入内容清晰、符合技能场景要求 |\n| 2 | 🔐 系统自动完成身份关联 | 无需用户输入任何身份参数；不在回复中展示内部身份值 |\n| 3 | ⚙️ 执行离岗监测分析 | 调用 `-m scripts.staff_absence_detection_analysis` 处理输入（**必须在技能根目录下运行脚本**） |\n| 4 | 📊 查看分析结果 | 接收结构化分析报告，查看识别/监测结果、风险提示、建议与报告链接 |\n\n### ⚙️ 脚本参数说明\n\n| 参数 | 含义 | 备注 |\n|---|---|---|\n| `--input` | 本地视频/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--media-type` | 媒体类型，可选值：video/image，默认 video | 按需填写 |\n| `--confidence-threshold` | 置信度阈值，低于该分值不输出，默认 0.5 | 按需填写 |\n| `--absence-threshold` | 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟） | 按需填写 |\n| `--list` | 显示离岗监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） | 用于云端历史报告查询 |\n| `--api-url` | API 服务地址（可选，使用默认值） | 按需填写 |\n| `--detail` | 输出详细程度（basic/standard/json，默认 json） | 输出详细程度 |\n| `--output` | 结果输出文件路径（可选） | 可选 |\n\n## 🗂️ 资源索引 | Resource Index\n| 资源类型 | 路径 | 用途 | 何时读取 |\n|---|---|---|---|\n| 🐍 必要脚本 | [`scripts/staff_absence_detection_analysis.py`](scripts/staff_absence_detection_analysis.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 🐍 必要脚本 | [`scripts/config.py`](scripts/config.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 📘 领域参考 | [`references/api_doc.md`](references/api_doc.md) | 了解 API 接口规范、字段说明和错误码 | 仅在需要了解接口规范或错误码时读取 |\n\n## ⚠️ 注意事项 | Notes\n| 分类 | 注意事项 |\n|---|---|\n| 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 |\n| 📁 格式支持 | 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供岗位管理参考，具体处置请结合实际管理制度 |\n| 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 |\n| 🌐 网络地址 | 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 |\n| 📁 格式支持 | 当显示历史监测报告清单的时候，从数据 json 中提取字段  作为超链接地址，使用 Markdown 表格格式输出，包含\" |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json\n```\n\nFile v1.0.11:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.11\",\n  \"publishedAt\": 1786259851520\n}\n\nFile v1.0.11:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.11:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.11:scripts/config.yaml\n\n{}\n\nFile v1.0.11:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.11:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.11:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.11:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: prod\n\nFile v1.0.11:skill-card.md\n\n## Description:\n\nMonitors employee on-duty status in designated areas from images or video using computer vision and human pose estimation, detects leave-post or absence conditions, supports configurable thresholds, and returns structured monitoring results and alerts.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[18072937735](https://clawhub.ai/user/18072937735)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nOperations, security, and workplace management teams use this skill to analyze workplace images or surveillance video for leave-post and absence events in monitored areas. Agents can run the bundled command-line workflow to submit media, retrieve structured results, and list cloud-hosted historical reports.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Sensitive workplace images or video and identity-linked request data may be sent to external cloud services.\n\nMitigation: Deploy only after confirming employee-consent, data-transfer, retention, and vendor-processing requirements for the monitored workplace.\n\nRisk: The skill can automatically create or reuse local user records and associate reports with an internal identity.\n\nMitigation: Review identity handling before installation, restrict workspace access, and confirm that generated or reused identities align with internal access-control and audit policies.\n\nRisk: Service tokens may be persisted in the workspace.\n\nMitigation: Use a secured runtime location, limit filesystem permissions, rotate tokens regularly, and remove persisted credentials when the skill is no longer needed.\n\n## Reference(s):\n\n- [Personnel Absence Monitoring API Documentation](references/api_doc.md)\n- [Shared Analysis API Documentation](skills/smyx_analysis/references/api_doc.md)\n- [Skill Demo](https://lifeemergence.com/sample.html)\n- [ClawHub Skill Page](https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON, shell commands]\n\n**Output Format:** [Markdown summaries and structured JSON returned from command-line/API workflows]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include report links, monitoring status, absence counts, duration statistics, recommendations, and optional saved output files.]\n\n## Skill Version(s):\n\n1.0.11 (source: frontmatter and server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.11:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.11:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.10: 30 files, 41484 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8662b), skill-card.md (2294b), SKILL.md (11283b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (427b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1509b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (24363b), skills/smyx_common/scripts/config.yaml (473b), skills/smyx_common/scripts/dao.py (18266b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (28776b), _meta.json (157b)\n\nFile v1.0.10:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.10\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件 |\n| ☁️ 历史报告查询 | 如果用户触发历史报告查询关键词，必须直接调用云端 API 查询，不得从本地记忆或人工汇总中获取 |\n\n#### ⚠️ 强制数据获取规则（次高优先级）\n\n> **橙色强约束：** 历史报告清单只允许从云端接口读取，不允许从本地记录、长期记忆或人工汇总中提取。\n\n必须执行：\n\n```bash\npython -m scripts.staff_absence_detection_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.staff_absence_detection_analysis --list` 调用 API 查询云端的历史报告数据 |\n| 🚫 严格禁止 | 从本地 `memory` 目录读取历史会话信息 |\n| 🚫 严格禁止 | 手动汇总本地记录中的报告 |\n| 🚫 严格禁止 | 从长期记忆中提取报告 |\n| ✅ 输出格式 | 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 |\n\n## 📦 前置准备 | Requirements\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 🚀 操作步骤 | Workflow\n### 🔐 用户身份处理（内部自动完成）\n\n> **绿色安全原则：** 用户身份参数由系统内部自动处理，**不得向用户展示、询问或要求输入任何身份标识**。\n\n执行本技能分析或历史报告查询时，脚本会自动完成身份初始化：\n\n| 场景 | 系统行为 |\n|---|---|\n| 上游系统有内部身份参数 | 由脚本静默接收并使用 |\n| 上游系统未提供内部身份参数 | 脚本会自动复用本地缺省用户 |\n| 本地缺省用户不存在 | 脚本会自动创建并在后续任务中复用 |\n| 对用户输出 | 只展示分析进度、分析结果和报告链接，不展示内部身份值 |\n\n#### 🔒 关键约束\n\n| 禁止/要求 | 说明 |\n|---|---|\n| 🚫 不得询问身份 | 不得提示用户输入用户名、手机号或任何内部身份参数 |\n| 🚫 不得暴露身份值 | 不得在回复、报告、示例、错误提示中暴露内部身份值 |\n| 🚫 不得列为用户参数 | 不得把内部身份参数列为用户需要理解或传入的参数 |\n| ✅ 自动关联报告 | 历史报告查询同样由系统内部身份自动关联，用户只需表达“查看历史报告/报告清单”等意图 |\n\n---\n\n### 🧪 标准流程 | Standard Flow\n\n| 步骤 | 阶段 | 执行动作 |\n|---:|---|---|\n| 1 | 📥 准备媒体输入 | 提供本地文件路径或网络 URL；确保输入内容清晰、符合技能场景要求 |\n| 2 | 🔐 系统自动完成身份关联 | 无需用户输入任何身份参数；不在回复中展示内部身份值 |\n| 3 | ⚙️ 执行离岗监测分析 | 调用 `-m scripts.staff_absence_detection_analysis` 处理输入（**必须在技能根目录下运行脚本**） |\n| 4 | 📊 查看分析结果 | 接收结构化分析报告，查看识别/监测结果、风险提示、建议与报告链接 |\n\n### ⚙️ 脚本参数说明\n\n| 参数 | 含义 | 备注 |\n|---|---|---|\n| `--input` | 本地视频/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--media-type` | 媒体类型，可选值：video/image，默认 video | 按需填写 |\n| `--confidence-threshold` | 置信度阈值，低于该分值不输出，默认 0.5 | 按需填写 |\n| `--absence-threshold` | 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟） | 按需填写 |\n| `--list` | 显示离岗监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） | 用于云端历史报告查询 |\n| `--api-url` | API 服务地址（可选，使用默认值） | 按需填写 |\n| `--detail` | 输出详细程度（basic/standard/json，默认 json） | 输出详细程度 |\n| `--output` | 结果输出文件路径（可选） | 可选 |\n\n## 🗂️ 资源索引 | Resource Index\n| 资源类型 | 路径 | 用途 | 何时读取 |\n|---|---|---|---|\n| 🐍 必要脚本 | [`scripts/staff_absence_detection_analysis.py`](scripts/staff_absence_detection_analysis.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 🐍 必要脚本 | [`scripts/config.py`](scripts/config.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 📘 领域参考 | [`references/api_doc.md`](references/api_doc.md) | 了解 API 接口规范、字段说明和错误码 | 仅在需要了解接口规范或错误码时读取 |\n\n## ⚠️ 注意事项 | Notes\n| 分类 | 注意事项 |\n|---|---|\n| 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 |\n| 📁 格式支持 | 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供岗位管理参考，具体处置请结合实际管理制度 |\n| 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 |\n| 🌐 网络地址 | 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 |\n| 📁 格式支持 | 当显示历史监测报告清单的时候，从数据 json 中提取字段  作为超链接地址，使用 Markdown 表格格式输出，包含\" |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json\n```\n\nFile v1.0.10:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.10\",\n  \"publishedAt\": 1785436374538\n}\n\nFile v1.0.10:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.10:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.10:scripts/config.yaml\n\n{}\n\nFile v1.0.10:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.10:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.10:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.10:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: prod\n\nFile v1.0.10:skill-card.md\n\n## Description: <br>\nMonitors workplace images or video through a remote computer-vision service to identify personnel presence, on-duty status, leave-post events, and absence duration. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[18072937735](https://clawhub.ai/user/18072937735) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nOperations, security, and workplace management teams use this skill to analyze monitoring images or videos for employee absence and leave-post events. It can also query prior absence-monitoring reports associated with the configured local identity. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Workplace surveillance media or URLs are processed by a configured remote service. <br>\nMitigation: Deploy only with explicit consent, retention, access-control, and deletion guidance for real employee footage. <br>\nRisk: Report history is tied to a local identity and tokens that may be created or reused automatically. <br>\nMitigation: Restrict access to the runtime environment and define identity, token, and report-history handling procedures before workplace use. <br>\n\n\n## Reference(s): <br>\n- [Personnel absence monitoring API documentation](references/api_doc.md) <br>\n- [Skill demo](https://lifeemergence.com/sample.html) <br>\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, json, shell commands, configuration, guidance] <br>\n**Output Format:** [Markdown or JSON analysis report with status counts, absence duration, report links, and optional saved output files.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Accepts local image or video files, media URLs, confidence and absence thresholds, and a history-list mode.] <br>\n\n## Skill Version(s): <br>\n1.0.10 (source: server evidence and SKILL.md frontmatter) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nFile v1.0.10:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.10:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.9: 30 files, 41696 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8662b), skill-card.md (2817b), SKILL.md (11282b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (427b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1509b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (24363b), skills/smyx_common/scripts/config.yaml (473b), skills/smyx_common/scripts/dao.py (18266b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (28776b), _meta.json (156b)\n\nFile v1.0.9:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.7\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件 |\n| ☁️ 历史报告查询 | 如果用户触发历史报告查询关键词，必须直接调用云端 API 查询，不得从本地记忆或人工汇总中获取 |\n\n#### ⚠️ 强制数据获取规则（次高优先级）\n\n> **橙色强约束：** 历史报告清单只允许从云端接口读取，不允许从本地记录、长期记忆或人工汇总中提取。\n\n必须执行：\n\n```bash\npython -m scripts.staff_absence_detection_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.staff_absence_detection_analysis --list` 调用 API 查询云端的历史报告数据 |\n| 🚫 严格禁止 | 从本地 `memory` 目录读取历史会话信息 |\n| 🚫 严格禁止 | 手动汇总本地记录中的报告 |\n| 🚫 严格禁止 | 从长期记忆中提取报告 |\n| ✅ 输出格式 | 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 |\n\n## 📦 前置准备 | Requirements\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 🚀 操作步骤 | Workflow\n### 🔐 用户身份处理（内部自动完成）\n\n> **绿色安全原则：** 用户身份参数由系统内部自动处理，**不得向用户展示、询问或要求输入任何身份标识**。\n\n执行本技能分析或历史报告查询时，脚本会自动完成身份初始化：\n\n| 场景 | 系统行为 |\n|---|---|\n| 上游系统有内部身份参数 | 由脚本静默接收并使用 |\n| 上游系统未提供内部身份参数 | 脚本会自动复用本地缺省用户 |\n| 本地缺省用户不存在 | 脚本会自动创建并在后续任务中复用 |\n| 对用户输出 | 只展示分析进度、分析结果和报告链接，不展示内部身份值 |\n\n#### 🔒 关键约束\n\n| 禁止/要求 | 说明 |\n|---|---|\n| 🚫 不得询问身份 | 不得提示用户输入用户名、手机号或任何内部身份参数 |\n| 🚫 不得暴露身份值 | 不得在回复、报告、示例、错误提示中暴露内部身份值 |\n| 🚫 不得列为用户参数 | 不得把内部身份参数列为用户需要理解或传入的参数 |\n| ✅ 自动关联报告 | 历史报告查询同样由系统内部身份自动关联，用户只需表达“查看历史报告/报告清单”等意图 |\n\n---\n\n### 🧪 标准流程 | Standard Flow\n\n| 步骤 | 阶段 | 执行动作 |\n|---:|---|---|\n| 1 | 📥 准备媒体输入 | 提供本地文件路径或网络 URL；确保输入内容清晰、符合技能场景要求 |\n| 2 | 🔐 系统自动完成身份关联 | 无需用户输入任何身份参数；不在回复中展示内部身份值 |\n| 3 | ⚙️ 执行离岗监测分析 | 调用 `-m scripts.staff_absence_detection_analysis` 处理输入（**必须在技能根目录下运行脚本**） |\n| 4 | 📊 查看分析结果 | 接收结构化分析报告，查看识别/监测结果、风险提示、建议与报告链接 |\n\n### ⚙️ 脚本参数说明\n\n| 参数 | 含义 | 备注 |\n|---|---|---|\n| `--input` | 本地视频/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--media-type` | 媒体类型，可选值：video/image，默认 video | 按需填写 |\n| `--confidence-threshold` | 置信度阈值，低于该分值不输出，默认 0.5 | 按需填写 |\n| `--absence-threshold` | 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟） | 按需填写 |\n| `--list` | 显示离岗监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） | 用于云端历史报告查询 |\n| `--api-url` | API 服务地址（可选，使用默认值） | 按需填写 |\n| `--detail` | 输出详细程度（basic/standard/json，默认 json） | 输出详细程度 |\n| `--output` | 结果输出文件路径（可选） | 可选 |\n\n## 🗂️ 资源索引 | Resource Index\n| 资源类型 | 路径 | 用途 | 何时读取 |\n|---|---|---|---|\n| 🐍 必要脚本 | [`scripts/staff_absence_detection_analysis.py`](scripts/staff_absence_detection_analysis.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 🐍 必要脚本 | [`scripts/config.py`](scripts/config.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 📘 领域参考 | [`references/api_doc.md`](references/api_doc.md) | 了解 API 接口规范、字段说明和错误码 | 仅在需要了解接口规范或错误码时读取 |\n\n## ⚠️ 注意事项 | Notes\n| 分类 | 注意事项 |\n|---|---|\n| 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 |\n| 📁 格式支持 | 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供岗位管理参考，具体处置请结合实际管理制度 |\n| 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 |\n| 🌐 网络地址 | 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 |\n| 📁 格式支持 | 当显示历史监测报告清单的时候，从数据 json 中提取字段  作为超链接地址，使用 Markdown 表格格式输出，包含\" |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json\n```\n\nFile v1.0.9:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.9\",\n  \"publishedAt\": 1784204430171\n}\n\nFile v1.0.9:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.9:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.9:scripts/config.yaml\n\n{}\n\nFile v1.0.9:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.9:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.9:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.9:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: prod\n\nFile v1.0.9:skill-card.md\n\n## Description: <br>\nReal-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[18072937735](https://clawhub.ai/user/18072937735) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nOperations, safety, and facilities teams use this skill to analyze workplace images or video for staff absence, post-leaving, and on-duty status signals in monitored areas such as factory stations, security rooms, and service windows. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill sends workplace surveillance images or videos and report history to a configured cloud service. <br>\nMitigation: Use only with approved workplace monitoring data, confirm organizational authorization for cloud processing, and review retention and deletion practices before deployment. <br>\nRisk: The skill can silently create or reuse an account-linked identity with persisted tokens. <br>\nMitigation: Review how default identities and stored tokens are managed, restrict who can query historical reports, and rotate or remove credentials when access changes. <br>\nRisk: Security evidence marks the release suspicious because of sensitive media transfer and account-linked report access. <br>\nMitigation: Perform a deployment security review and install only when those data-sharing and access-control behaviors are acceptable. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis) <br>\n- [Personnel absence monitoring API documentation](references/api_doc.md) <br>\n- [Skill demo](https://lifeemergence.com/sample.html) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, JSON, shell commands, guidance] <br>\n**Output Format:** [Markdown reports, JSON analysis responses, report links, and command-line guidance] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Outputs may include status classifications, absence counts, accumulated absence duration, threshold settings, report history tables, and links to cloud-hosted reports.] <br>\n\n## Skill Version(s): <br>\n1.0.9 (source: ClawHub release evidence; artifact frontmatter says 1.0.7) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nFile v1.0.9:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.9:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.8: 30 files, 41757 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8662b), skill-card.md (2968b), SKILL.md (11282b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (427b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1509b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (24363b), skills/smyx_common/scripts/config.yaml (473b), skills/smyx_common/scripts/dao.py (18266b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (28776b), _meta.json (156b)\n\nFile v1.0.8:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.7\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件 |\n| ☁️ 历史报告查询 | 如果用户触发历史报告查询关键词，必须直接调用云端 API 查询，不得从本地记忆或人工汇总中获取 |\n\n#### ⚠️ 强制数据获取规则（次高优先级）\n\n> **橙色强约束：** 历史报告清单只允许从云端接口读取，不允许从本地记录、长期记忆或人工汇总中提取。\n\n必须执行：\n\n```bash\npython -m scripts.staff_absence_detection_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.staff_absence_detection_analysis --list` 调用 API 查询云端的历史报告数据 |\n| 🚫 严格禁止 | 从本地 `memory` 目录读取历史会话信息 |\n| 🚫 严格禁止 | 手动汇总本地记录中的报告 |\n| 🚫 严格禁止 | 从长期记忆中提取报告 |\n| ✅ 输出格式 | 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 |\n\n## 📦 前置准备 | Requirements\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 🚀 操作步骤 | Workflow\n### 🔐 用户身份处理（内部自动完成）\n\n> **绿色安全原则：** 用户身份参数由系统内部自动处理，**不得向用户展示、询问或要求输入任何身份标识**。\n\n执行本技能分析或历史报告查询时，脚本会自动完成身份初始化：\n\n| 场景 | 系统行为 |\n|---|---|\n| 上游系统有内部身份参数 | 由脚本静默接收并使用 |\n| 上游系统未提供内部身份参数 | 脚本会自动复用本地缺省用户 |\n| 本地缺省用户不存在 | 脚本会自动创建并在后续任务中复用 |\n| 对用户输出 | 只展示分析进度、分析结果和报告链接，不展示内部身份值 |\n\n#### 🔒 关键约束\n\n| 禁止/要求 | 说明 |\n|---|---|\n| 🚫 不得询问身份 | 不得提示用户输入用户名、手机号或任何内部身份参数 |\n| 🚫 不得暴露身份值 | 不得在回复、报告、示例、错误提示中暴露内部身份值 |\n| 🚫 不得列为用户参数 | 不得把内部身份参数列为用户需要理解或传入的参数 |\n| ✅ 自动关联报告 | 历史报告查询同样由系统内部身份自动关联，用户只需表达“查看历史报告/报告清单”等意图 |\n\n---\n\n### 🧪 标准流程 | Standard Flow\n\n| 步骤 | 阶段 | 执行动作 |\n|---:|---|---|\n| 1 | 📥 准备媒体输入 | 提供本地文件路径或网络 URL；确保输入内容清晰、符合技能场景要求 |\n| 2 | 🔐 系统自动完成身份关联 | 无需用户输入任何身份参数；不在回复中展示内部身份值 |\n| 3 | ⚙️ 执行离岗监测分析 | 调用 `-m scripts.staff_absence_detection_analysis` 处理输入（**必须在技能根目录下运行脚本**） |\n| 4 | 📊 查看分析结果 | 接收结构化分析报告，查看识别/监测结果、风险提示、建议与报告链接 |\n\n### ⚙️ 脚本参数说明\n\n| 参数 | 含义 | 备注 |\n|---|---|---|\n| `--input` | 本地视频/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--media-type` | 媒体类型，可选值：video/image，默认 video | 按需填写 |\n| `--confidence-threshold` | 置信度阈值，低于该分值不输出，默认 0.5 | 按需填写 |\n| `--absence-threshold` | 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟） | 按需填写 |\n| `--list` | 显示离岗监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） | 用于云端历史报告查询 |\n| `--api-url` | API 服务地址（可选，使用默认值） | 按需填写 |\n| `--detail` | 输出详细程度（basic/standard/json，默认 json） | 输出详细程度 |\n| `--output` | 结果输出文件路径（可选） | 可选 |\n\n## 🗂️ 资源索引 | Resource Index\n| 资源类型 | 路径 | 用途 | 何时读取 |\n|---|---|---|---|\n| 🐍 必要脚本 | [`scripts/staff_absence_detection_analysis.py`](scripts/staff_absence_detection_analysis.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 🐍 必要脚本 | [`scripts/config.py`](scripts/config.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 📘 领域参考 | [`references/api_doc.md`](references/api_doc.md) | 了解 API 接口规范、字段说明和错误码 | 仅在需要了解接口规范或错误码时读取 |\n\n## ⚠️ 注意事项 | Notes\n| 分类 | 注意事项 |\n|---|---|\n| 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 |\n| 📁 格式支持 | 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供岗位管理参考，具体处置请结合实际管理制度 |\n| 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 |\n| 🌐 网络地址 | 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 |\n| 📁 格式支持 | 当显示历史监测报告清单的时候，从数据 json 中提取字段  作为超链接地址，使用 Markdown 表格格式输出，包含\" |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json\n```\n\nFile v1.0.8:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.8\",\n  \"publishedAt\": 1783806446291\n}\n\nFile v1.0.8:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.8:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.8:scripts/config.yaml\n\n{}\n\nFile v1.0.8:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.8:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.8:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.8:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: prod\n\nFile v1.0.8:skill-card.md\n\n## Description: <br>\nReal-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[18072937735](https://clawhub.ai/user/18072937735) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nOperations, safety, and facilities teams can use this skill to analyze workplace video, images, local files, or media URLs for on-duty presence, leave-post events, absence duration, and historical absence-monitoring reports. It is suited to managed areas such as factory floors, security rooms, and service counters where monitoring policies and consent requirements are already established. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Workplace monitoring media and report queries are sent to the publisher's cloud service. <br>\nMitigation: Use only with approved workplace monitoring policies, explicit consent where required, and confirmed retention and data-processing terms. <br>\nRisk: Analyses can be linked to a local or auto-created identity for historical report retrieval. <br>\nMitigation: Review identity persistence before deployment and avoid sensitive employee footage unless account-linking behavior is acceptable. <br>\nRisk: The authoritative security verdict is suspicious because the behavior includes remote media processing and identity-linked activity. <br>\nMitigation: Administrators should review configured endpoints, token handling, and expected cloud interactions before enabling the skill. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis) <br>\n- [Skill demo](https://lifeemergence.com/sample.html) <br>\n- [Personnel absence monitoring API documentation](references/api_doc.md) <br>\n- [Shared analysis API documentation](skills/smyx_analysis/references/api_doc.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, JSON, Shell commands, Configuration] <br>\n**Output Format:** [Markdown and JSON-formatted analysis reports with status counts, absence durations, report links, and optional file output] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Can output historical report lists as structured Markdown or JSON and can save analysis output to a user-specified file.] <br>\n\n## Skill Version(s): <br>\n1.0.8 (source: server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nFile v1.0.8:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.8:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.7: 30 files, 41375 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8662b), skill-card.md (2792b), SKILL.md (11282b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (427b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1509b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (22801b), skills/smyx_common/scripts/config.yaml (473b), skills/smyx_common/scripts/dao.py (18266b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (28605b), _meta.json (156b)\n\nFile v1.0.7:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.5\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件 |\n| ☁️ 历史报告查询 | 如果用户触发历史报告查询关键词，必须直接调用云端 API 查询，不得从本地记忆或人工汇总中获取 |\n\n#### ⚠️ 强制数据获取规则（次高优先级）\n\n> **橙色强约束：** 历史报告清单只允许从云端接口读取，不允许从本地记录、长期记忆或人工汇总中提取。\n\n必须执行：\n\n```bash\npython -m scripts.staff_absence_detection_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.staff_absence_detection_analysis --list` 调用 API 查询云端的历史报告数据 |\n| 🚫 严格禁止 | 从本地 `memory` 目录读取历史会话信息 |\n| 🚫 严格禁止 | 手动汇总本地记录中的报告 |\n| 🚫 严格禁止 | 从长期记忆中提取报告 |\n| ✅ 输出格式 | 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 |\n\n## 📦 前置准备 | Requirements\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 🚀 操作步骤 | Workflow\n### 🔐 用户身份处理（内部自动完成）\n\n> **绿色安全原则：** 用户身份参数由系统内部自动处理，**不得向用户展示、询问或要求输入任何身份标识**。\n\n执行本技能分析或历史报告查询时，脚本会自动完成身份初始化：\n\n| 场景 | 系统行为 |\n|---|---|\n| 上游系统有内部身份参数 | 由脚本静默接收并使用 |\n| 上游系统未提供内部身份参数 | 脚本会自动复用本地缺省用户 |\n| 本地缺省用户不存在 | 脚本会自动创建并在后续任务中复用 |\n| 对用户输出 | 只展示分析进度、分析结果和报告链接，不展示内部身份值 |\n\n#### 🔒 关键约束\n\n| 禁止/要求 | 说明 |\n|---|---|\n| 🚫 不得询问身份 | 不得提示用户输入用户名、手机号或任何内部身份参数 |\n| 🚫 不得暴露身份值 | 不得在回复、报告、示例、错误提示中暴露内部身份值 |\n| 🚫 不得列为用户参数 | 不得把内部身份参数列为用户需要理解或传入的参数 |\n| ✅ 自动关联报告 | 历史报告查询同样由系统内部身份自动关联，用户只需表达“查看历史报告/报告清单”等意图 |\n\n---\n\n### 🧪 标准流程 | Standard Flow\n\n| 步骤 | 阶段 | 执行动作 |\n|---:|---|---|\n| 1 | 📥 准备媒体输入 | 提供本地文件路径或网络 URL；确保输入内容清晰、符合技能场景要求 |\n| 2 | 🔐 系统自动完成身份关联 | 无需用户输入任何身份参数；不在回复中展示内部身份值 |\n| 3 | ⚙️ 执行离岗监测分析 | 调用 `-m scripts.staff_absence_detection_analysis` 处理输入（**必须在技能根目录下运行脚本**） |\n| 4 | 📊 查看分析结果 | 接收结构化分析报告，查看识别/监测结果、风险提示、建议与报告链接 |\n\n### ⚙️ 脚本参数说明\n\n| 参数 | 含义 | 备注 |\n|---|---|---|\n| `--input` | 本地视频/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--media-type` | 媒体类型，可选值：video/image，默认 video | 按需填写 |\n| `--confidence-threshold` | 置信度阈值，低于该分值不输出，默认 0.5 | 按需填写 |\n| `--absence-threshold` | 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟） | 按需填写 |\n| `--list` | 显示离岗监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） | 用于云端历史报告查询 |\n| `--api-url` | API 服务地址（可选，使用默认值） | 按需填写 |\n| `--detail` | 输出详细程度（basic/standard/json，默认 json） | 输出详细程度 |\n| `--output` | 结果输出文件路径（可选） | 可选 |\n\n## 🗂️ 资源索引 | Resource Index\n| 资源类型 | 路径 | 用途 | 何时读取 |\n|---|---|---|---|\n| 🐍 必要脚本 | [`scripts/staff_absence_detection_analysis.py`](scripts/staff_absence_detection_analysis.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 🐍 必要脚本 | [`scripts/config.py`](scripts/config.py) | 调用 API、执行分析或查询历史报告 | 执行分析或查询时使用 |\n| 📘 领域参考 | [`references/api_doc.md`](references/api_doc.md) | 了解 API 接口规范、字段说明和错误码 | 仅在需要了解接口规范或错误码时读取 |\n\n## ⚠️ 注意事项 | Notes\n| 分类 | 注意事项 |\n|---|---|\n| 📚 文档读取 | 仅在需要时读取参考文档，保持上下文简洁 |\n| 📁 格式支持 | 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供岗位管理参考，具体处置请结合实际管理制度 |\n| 🚫 脚本限制 | 禁止临时生成脚本，只能用技能本身的脚本 |\n| 🌐 网络地址 | 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 |\n| 📁 格式支持 | 当显示历史监测报告清单的时候，从数据 json 中提取字段  作为超链接地址，使用 Markdown 表格格式输出，包含\" |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json\n```\n\nFile v1.0.7:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.7\",\n  \"publishedAt\": 1782946409506\n}\n\nFile v1.0.7:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.7:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.7:scripts/config.yaml\n\n{}\n\nFile v1.0.7:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.7:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.7:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.7:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: prod\n\nFile v1.0.7:skill-card.md\n\n## Description: <br>\nReal-time monitoring of personnel on-duty status in specific areas using computer vision and human pose estimation to detect leaving-post and absence events, support configurable thresholds, and return structured monitoring reports. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[18072937735](https://clawhub.ai/user/18072937735) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nOperations, safety, and facilities teams use this skill to analyze workplace camera images, videos, or media URLs for personnel absence and leaving-post events. It can also retrieve cloud-hosted historical reports associated with the automatically managed user identity. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill sends workplace images, videos, or media URLs to the vendor's cloud service for analysis. <br>\nMitigation: Use only with media that the organization is authorized to process, and confirm employee notice, consent, retention, and vendor-processing requirements before deployment. <br>\nRisk: Reports are tied to an automatically managed identity, and the skill can silently create or reuse that identity. <br>\nMitigation: Review whether silent identity creation and cloud history retrieval meet internal privacy and account-governance policies before enabling historical report queries. <br>\nRisk: The security evidence says credentials or tokens may be stored and reused for cloud requests with limited user control. <br>\nMitigation: Run in an isolated agent workspace, restrict access to local skill data files, and rotate or revoke service credentials according to the vendor's process if the workspace is shared or decommissioned. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/18072937735/skills/smyx-staff-absence-detection-analysis) <br>\n- [API documentation](artifact/references/api_doc.md) <br>\n- [Skill demo](https://lifeemergence.com/sample.html) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, JSON, Shell commands, Guidance] <br>\n**Output Format:** [Markdown report text or structured JSON, with optional saved output files] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Reports may include detection status, absence counts, duration statistics, recommendations, cloud report links, and historical report lists.] <br>\n\n## Skill Version(s): <br>\n1.0.7 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nFile v1.0.7:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.7:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.6: 30 files, 39302 bytes\n\nFiles: references/api_doc.md (2290b), scripts/config.py (779b), scripts/config.yaml (3b), scripts/skill.py (579b), scripts/staff_absence_detection_analysis.py (8646b), skill-card.md (2532b), SKILL.md (11375b), skills/smyx_analysis/__init__.py (0b), skills/smyx_analysis/references/api_doc.md (2094b), skills/smyx_analysis/requirements.txt (45b), skills/smyx_analysis/scripts/__init__.py (0b), skills/smyx_analysis/scripts/api_service.py (1857b), skills/smyx_analysis/scripts/config.py (1003b), skills/smyx_analysis/scripts/config.yaml (3b), skills/smyx_analysis/scripts/skill.py (6529b), skills/smyx_analysis/scripts/smyx_analysis.py (3833b), skills/smyx_common/__init__.py (0b), skills/smyx_common/requirements.txt (47b), skills/smyx_common/scripts/__init__.py (177b), skills/smyx_common/scripts/api_service.py (2645b), skills/smyx_common/scripts/base.py (469b), skills/smyx_common/scripts/config-dev.yaml (214b), skills/smyx_common/scripts/config-prod.yaml (0b), skills/smyx_common/scripts/config-test.yaml (256b), skills/smyx_common/scripts/config.py (22801b), skills/smyx_common/scripts/config.yaml (473b), skills/smyx_common/scripts/dao.py (13468b), skills/smyx_common/scripts/skill.py (2473b), skills/smyx_common/scripts/util.py (24106b), _meta.json (156b)\n\nFile v1.0.6:SKILL.md\n\n---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.4\"\nlicense: \"MIT-0\"\n---\n\n# Staff Absence Detection Skill | 人员离岗实时监测技能\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## ⚠️ 强制记忆规则（最高优先级）\n\n**本技能明确约定：**\n\n- **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\n- **绝对禁止从 LanceDB 长期记忆中检索信息**\n- **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\n- 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\n\n## 任务目标\n\n- 本 Skill 用于：通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n- 能力包含：人员存在检测、在岗定位识别、离岗状态判定、异常时长统计\n- 支持场景：工厂车间、监控室、服务窗口、安保岗亭、收费站、营业厅等需要固定人员在岗的场景\n- 触发条件:\n    1. **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能\n    2. 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片\n    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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告\n- 自动行为：\n    1. 如果用户上传了附件或者视频/图片文件，则自动保存为本地文件\n    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\"、\"\n       显示所有离岗监测报告\"、\"查看历史报告\"等），**必须**：\n        - 直接使用 `python -m scripts.staff_absence_detection_analysis --list --open-id` 参数调用 API 查询云端的历史报告数据\n        - **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\n        - **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\n\n## 前置准备\n\n- 依赖说明:scripts 脚本所需的依赖包及版本\n  ```\n  requests>=2.28.0\n  ```\n\n## 操作步骤\n\n### 🔒 open-id 获取流程控制（强制执行，防止遗漏）\n\n**在执行人员离岗监测前，必须按以下优先级顺序获取 open-id：**\n\n```\n第 1 步：【最高优先级】检查技能所在目录的配置文件（优先）\n        路径：scripts/config.yaml（相对于技能根目录）\n        完整路径示例：${OPENCLAW_WORKSPACE}/skills/{当前技能目录}/scripts/config.yaml\n        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id\n        ↓ (未找到/未配置/api-key 为空)\n第 2 步：检查 workspace 公共目录的配置文件\n        路径：${OPENCLAW_WORKSPACE}/skills/smyx_common/scripts/config.yaml\n        → 如果文件存在且配置了 api-key 字段，则读取 api-key 作为 open-id\n        ↓ (未找到/未配置)\n第 3 步：检查用户是否在消息中明确提供了 open-id\n        ↓ (未提供)\n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\n```\n\n**⚠️ 关键约束：**\n\n- **禁止**自行假设,自行推导,自行生成 open-id 值（如 openclaw-control-ui、default、staff123 等）\n- **禁止**跳过 open-id 验证直接调用 API\n- **必须**在获取到有效 open-id 后才能继续执行分析\n- 如果用户拒绝提供 open-id，说明用途（用于保存和查询离岗监测报告记录），并询问是否继续\n\n---\n\n- 标准流程:\n    1. **准备媒体输入**\n        - 提供监控视频文件路径、网络视频 URL 或现场图片\n        - 确保监控画面完整覆盖监测区域，画面稳定\n    2. **获取 open-id（强制执行）**\n        - 按上述流程控制获取 open-id\n        - 如无法获取，必须提示用户提供用户名或手机号\n    3. **执行离岗监测分析**\n        - 调用 `-m scripts.staff_absence_detection_analysis` 处理素材（**必须在技能根目录下运行脚本**）\n        - 参数说明:\n            - `--input`: 本地视频/图片文件路径\n            - `--url`: 网络视频/图片 URL 地址（API 服务自动下载）\n            - `--media-type`: 媒体类型，可选值：video/image，默认 video\n            - `--confidence-threshold`: 置信度阈值，低于该分值不输出，默认 0.5\n            - `--absence-threshold`: 离岗判定阈值（秒），超过该时长判定为异常离岗，默认 300 秒（5分钟）\n            - `--open-id`: 当前用户的 open-id（必填，按上述流程获取）\n            - `--list`: 显示离岗监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）\n            - `--api-key`: API 访问密钥（可选）\n            - `--api-url`: API 服务地址（可选，使用默认值）\n            - `--detail`: 输出详细程度（basic/standard/json，默认 json）\n            - `--output`: 结果输出文件路径（可选）\n    4. **查看分析结果**\n        - 接收结构化的人员离岗监测报告\n        - 包含：检测基本信息、在岗状态、异常离岗判定、离岗时长统计\n\n## 资源索引\n\n- 必要脚本：见 [scripts/staff_absence_detection_analysis.py](scripts/staff_absence_detection_analysis.py)(用途：调用 API\n  进行人员离岗监测，本地文件上传，网络 URL 由 API 服务自动下载)\n- 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)\n- 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)\n\n## 注意事项\n\n- 仅在需要时读取参考文档，保持上下文简洁\n- 支持格式：视频支持 mp4/avi/mov 格式，图片支持 jpg/png/jpeg 格式，最大 10MB\n- 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\n- 分析结果仅供岗位管理参考，具体处置请结合实际管理制度\n- 禁止临时生成脚本，只能用技能本身的脚本\n- 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\n- 当显示历史监测报告清单的时候，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\"\n  报告名称\"、\"检测时间\"、\"异常离岗次数\"、\"点击查看\"四列，其中\"报告名称\"列使用`人员离岗监测分析报告-{记录id}`形式拼接, \"\n  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。\n- 表格输出示例：\n  | 报告名称 | 检测时间 | 异常离岗次数 | 点击查看 |\n  |----------|----------|--------------|----------|\n  | 人员离岗监测分析报告-20260415103000001 | 2026-04-15 10:30:00 | 2 | [🔗 查看报告](https://example.com/report?id=xxx) |\n\n## 使用示例\n\n```bash\n# 监测本地监控视频（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 --open-id openclaw-control-ui\n\n# 监测现场图片（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 --open-id openclaw-control-ui\n\n# 监测网络监控视频（以下只是示例，禁止直接使用openclaw-control-ui 作为 open-id）\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 --open-id openclaw-control-ui\n\n# 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list --open-id openclaw-control-ui\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --open-id your-open-id --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --open-id your-open-id --output result.json\n```\n\nFile v1.0.6:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.6\",\n  \"publishedAt\": 1782163348658\n}\n\nFile v1.0.6:references/api_doc.md\n\n# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒\n\nFile v1.0.6:skills/smyx_analysis/references/api_doc.md\n\n# API接口文档\n\n## 接口地址\n\n`POST https://your-api-server.com/api/v1/common-analysis`\n\n## 请求头\n\n| 字段           | 必选 | 说明                            |\n|--------------|----|-------------------------------|\n| X-API-Key    | 是  | API访问密钥                       |\n| Content-Type | 是  | 文件上传或 application/json（URL模式） |\n\n## 请求参数\n\n### 1. 文件上传模式\n\n| 字段           | 类型     | 必选 | 说明                                    |\n|--------------|--------|----|---------------------------------------|\n| video        | file   | 是  | MP4视频文件                               |\n| detail_level | string | 否  | 输出详细程度：basic/standard/full，默认standard |\n\n### 2. URL模式\n\n| 字段           | 类型     | 必选 | 说明                                    |\n|--------------|--------|----|---------------------------------------|\n| video_url    | string | 是  | 可公开访问的视频URL                           |\n| detail_level | string | 否  | 输出详细程度：basic/standard/full，默认standard |\n\n## 响应格式\n\n```json\n{\n  \"code\": 200,\n  \"message\": \"success\",\n  \"data\": {\n    \"analysis_time\": \"2026-03-10 15:30:00\",\n    \"face_detection\": {\n      \"status\": \"success\",\n      \"face_count\": 1,\n      \"quality_score\": 95\n    },\n    \"diagnosis\": {\n      \"overall_constitution\": \"平和质\",\n      \"organ_condition\": {\n        \"liver\": \"正常\",\n        \"heart\": \"轻微火旺\",\n        \"spleen\": \"略虚\",\n        \"lung\": \"正常\",\n        \"kidney\": \"正常\"\n      },\n      \"color_analysis\": {\n        \"complexion\": \"微黄\",\n        \"correspondence\": \"脾胃功能略弱\"\n      }\n    },\n    \"health_warnings\": [\n      \"注意休息，避免熬夜\"\n    ],\n    \"suggestions\": [\n      \"饮食清淡，减少辛辣食物摄入\"\n    ]\n  }\n}\n```\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |\n\nFile v1.0.6:scripts/config.yaml\n\n{}\n\nFile v1.0.6:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.6:skills/smyx_common/scripts/config-dev.yaml\n\nApiEnum:\n  base-url-open-api: \"http://192.168.1.234:9601/smyx-open-api\"\n  base-url-open-h5: \"http://192.168.1.234:4100\"\n  base-url-health: \"http://192.168.1.234:7070/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.6:skills/smyx_common/scripts/config-test.yaml\n\nApiEnum:\n  base-url-open-api: \"https://livemonitortest.lifeemergence.com/smyx-open-api\"\n  base-url-open-h5: \"http://livemonitortest.lifeemergence.com\"\n  base-url-health: \"https://healthtest.lifeemergence.com/jeecg-boot-xzgz\"\n\nConstantEnum:\n  is-debug: true\n\nFile v1.0.6:skills/smyx_common/scripts/config.yaml\n\nApiEnum:\n  api-key: null\n  api-secret-key: null\n  base-url-health: https://lifeemergence.com/jeecg-boot-xzgz\n  base-url-open-api: https://open.lifeemergence.com/smyx-open-api\n  base-url-open-h5: http://livemonitor.lifeemergence.com\n  database-url: null\nConstantEnum:\n  app--id: x1a3s4nwy1s2r4se\n  current--tentant-code: XIAN_ZHAO_GAN_ZHI\n  default--skill-platform-name: ARK_CLAW\n  feishu-app--id: cli_a93d769369badcb1\n  feishu-app--secret: null\n  is-debug: false\nenv: prod\n\nFile v1.0.6:skill-card.md\n\n## Description: <br>\nMonitors whether personnel remain on duty in specified workplace areas by submitting video or images to a cloud computer-vision service and returning absence status, duration, and history reports. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[18072937735](https://clawhub.ai/user/18072937735) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nOperations, safety, and facilities teams use this skill to analyze workplace camera video or images for leave-post and absence events in fixed-duty areas such as production lines, monitoring rooms, service windows, guard posts, toll stations, and business halls. The skill can also retrieve cloud-stored historical absence reports for a supplied user identifier. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill sends workplace images or video, user identifiers, and generated absence reports to the configured LifeEmergence cloud service. <br>\nMitigation: Use only with approved media and identifiers, review configured API endpoints before deployment, and apply applicable employee notice, consent, and data-retention controls. <br>\nRisk: A development private-IP configuration is present in the artifact and could be inappropriate for production use. <br>\nMitigation: Confirm production deployments use the intended public service configuration and do not rely on development endpoints. <br>\n\n\n## Reference(s): <br>\n- [Personnel Absence Monitoring API Documentation](references/api_doc.md) <br>\n- [ClawHub Release Page](https://clawhub.ai/18072937735/smyx-staff-absence-detection-analysis) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, JSON, shell commands, configuration] <br>\n**Output Format:** [Markdown or JSON analysis reports with optional saved text output] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Accepts local media paths or media URLs, an open-id user identifier, media type, confidence threshold, and absence threshold; can return current analysis results or historical report listings.] <br>\n\n## Skill Version(s): <br>\n1.0.6 (source: server release metadata; skill frontmatter reports 1.0.4) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nFile v1.0.6:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.6:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3","readmeExcerpt":"Skill: Real-time Employee Absence Monitoring Skill | 人员离岗实时监测技能 Owner: 18072937735 Summary: Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"python -m scripts.staff_absence_detection_analysis --list"},{"language":"text","snippet":"requests>=2.28.0"},{"language":"bash","snippet":"# 监测本地监控视频\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.mp4 --media-type video --absence-threshold 300 监测现场图片\npython -m scripts.staff_absence_detection_analysis --input /path/to/monitor.jpg --media-type image --confidence-threshold 0.6 监测网络监控视频\npython -m scripts.staff_absence_detection_analysis --url https://example.com/monitor.mp4 --media-type video --absence-threshold 180 显示历史监测报告/显示监测报告清单列表/显示历史离岗监测报告（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）\npython -m scripts.staff_absence_detection_analysis --list\n\n# 输出精简报告\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --detail basic\n\n# 保存结果到文件\npython -m scripts.staff_absence_detection_analysis --input video.mp4 --media-type video --output result.json"},{"language":"json","snippet":"{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}"},{"language":"bash","snippet":"python -m scripts.staff_absence_detection_analysis --list"},{"language":"text","snippet":"requests>=2.28.0"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: \"staff-absence-detection-analysis\"\ndescription: \"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景\"\nversion: \"1.0.19\"\nlicense: \"MIT-0\"\n---\n\n# 👤 Staff Absence Detection Skill | 人员离岗实时监测技能\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **人员离岗实时监测技能** |\n| 🎯 核心目标 | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `PERSONNEL_LEAVE_POST_MONITORING` |\n\nTailored specifically for post management supervision scenarios in industrial production, security monitoring, service\nwindows and other work scenarios, this skill is equipped with a high-precision computer vision algorithm combined with\nhuman pose estimation technology, which can accurately identify the presence, location and behavior characteristics of\npersonnel in the monitoring area, automatically distinguish between temporary departure and long-term absence based on\ntime-series behavior analysis, and supports user-defined judgment thresholds such as departure duration and area range.\n\nThe system has strong adaptability to complex environments such as different lighting conditions and camera angles, can\nachieve millisecond-level response, and immediately trigger the early warning mechanism when an abnormality is detected,\nnotifies managers through APP push, on-site voice reminders and other methods, and automatically records the departure\ntime, duration and on-site pictures, providing efficient and accurate real-time supervision services for scenarios that\nrequire personnel on duty, helping to improve post management efficiency and safety assurance level.\n\n本技能专为工厂车间、安保监控室、服务窗口等岗位管理监管场景量身打造，搭载高精度计算机视觉算法结合人体姿态估计技术，能够精准识别监测区域内人员的存在、定位及行为特征，基于时序行为分析自动区分短暂离开与长时间离岗，支持用户自定义离岗时长、区域范围等判定阈值。\n\n系统对不同光照条件、摄像机角度等复杂环境具备强大的适应能力，可实现毫秒级响应，异常发生时立即触发预警机制，通过APP推送、现场语音提醒等方式通知管理人员，并自动记录离岗时间、时长及现场画面，为需要人员在岗的场景提供高效、精准的实时监管服务，助力提升岗位管理效率与安全保障水平。\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频/现场图片对目标监测区域进行人员在岗状态分析，识别人员离岗、缺岗等异常状态，输出结构化的离岗监测分析报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 人员存在检测 |\n| 2 | 在岗定位识别 |\n| 3 | 离岗状态判定 |\n| 4 | 异常时长统计 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片 URL 或文件需要进行人员离岗监测时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行人员离岗监测，提及人员离岗、缺岗监测、在岗检测、岗位监控等关键词，并且上传了视频或图片 |\n| 📚 历史报告查询 | 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、离岗监测报告清单、检测报告列表、查询历史报告、显示所有监测报告、离岗监测历史记录，查询离岗分析报告 |\n\n### 4. 🤖 自动行为\n\n| 自动行为 | 执行要求 |\n|---|---|\n| 📎 附件处理 | 如果用户上传了附件或"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-staff-absence-detection-analysis\",\n  \"version\": \"1.0.15\",\n  \"publishedAt\": 1791014765477\n}"},{"path":"references/api_doc.md","content":"# 人员离岗实时监测 API 接口文档\n\n## 接口概览\n\n人员离岗实时监测功能依赖云端 API 服务进行计算机视觉分析，以下是 API 接口规范说明。\n\n## 认证方式\n\n- API Key 通过请求头 `Authorization: Bearer {api_key}` 传递\n- 未配置 API Key 时使用默认共享配额\n\n## 主要接口\n\n### 1. 离岗监测分析接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/personnel-leave-post-detection`\n\n**Method**: `POST`\n\n**请求参数**:\n\n- `input_type`: `file` 或 `url`\n- `media_type`: `video` 或 `image`\n- `confidence_threshold`: 置信度阈值，默认 0.5\n- `absence_threshold`: 离岗判定阈值（秒），默认 300\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`（固定值）\n- `open_id`: 用户标识\n\n**响应格式**: JSON\n\n```json\n{\n  \"code\": 0,\n  \"message\": \"success\",\n  \"data\": {\n    \"id\": \"request-id\",\n    \"detection_time\": \"2026-04-15 10:30:00\",\n    \"detection\": {\n      \"post_status\": \"leave_post\",\n      \"abnormal_absence_count\": 2,\n      \"total_absence_duration\": 650,\n      \"status_stats\": [\n        {\n          \"status\": \"on_duty\",\n          \"count\": 1,\n          \"total_duration\": 1200\n        },\n        {\n          \"status\": \"leave_post\",\n          \"count\": 2,\n          \"total_duration\": 650\n        },\n        {\n          \"status\": \"temporary_leave\",\n          \"count\": 1,\n          \"total_duration\": 80\n        }\n      ]\n    }\n  }\n}\n```\n\n### 2. 查询历史报告列表接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/list`\n\n**Method**: `GET`\n\n**请求参数**:\n\n- `scene_code`: `PERSONNEL_LEAVE_POST_MONITORING`\n- `open_id`: 用户标识\n- `start_time`: 起始时间（可选）\n- `end_time`: 结束时间（可选）\n\n### 3. 获取报告详情接口\n\n**URL**: `{base_url}/api/v1/ai-analysis/detail/{request_id}`\n\n**Method**: `GET`\n\n## 错误码说明\n\n| 错误码  | 说明      |\n|------|---------|\n| 0    | 成功      |\n| 1001 | 参数错误    |\n| 1002 | 文件格式不支持 |\n| 1003 | 文件过大    |\n| 2001 | 认证失败    |\n| 2002 | 配额不足    |\n| 3001 | 分析失败    |\n| 4001 | 记录不存在   |\n\n## 注意事项\n\n1. 最大支持文件大小：10MB\n2. 支持视频格式：mp4、avi、mov\n3. 支持图片格式：jpg、png、jpeg\n4. 分析时间根据文件大小不同，通常在 3-30 秒"},{"path":"skills/smyx_analysis/references/api_doc.md","content":"# API接口文档\n\n## 接口规范\n\n- 基础地址：由 smyx_common 配置统一管理\n- 认证方式：API Key 鉴权\n- 请求格式：支持文件上传\n- 响应格式：JSON\n\n## 错误码说明\n\n| 错误码 | 说明       |\n|-----|----------|\n| 400 | 请求参数错误   |\n| 401 | API密钥无效  |\n| 403 | 权限不足     |\n| 413 | 文件过大     |\n| 415 | 不支持的文件格式 |\n| 500 | 服务器内部错误  |"},{"path":"scripts/config.yaml","content":"{}"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉与人体姿态估计算法，实时监测特定区域内人员的在岗状态，自动判断离岗、缺岗等异常状态，支持自定义判定阈值，异常发生立即触发预警，适用于工厂车间、监控室、服务窗口等岗位监管场景 Skill: Real-time Employee Absence Monitoring Skill | 人员离岗实时监测技能 Owner: 18072937735 Summary: Real-time monitoring of personnel on-duty status in specific areas based on computer vision and human pose estimation, automatically detects abnormal statuses such as leaving posts and absent from work, supports custom threshold settings, and triggers early warning immediately when abnormality is detected. | 人员离岗实时监测技能，基于计算机视觉","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1025,"uniquenessScore":48,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:04:43.010Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-09T17:04:43.010Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T02:30:11.777Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}