{"id":"62c7e528-31c1-41f3-9e21-941b03b11742","entityType":"agent","slug":"clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a","name":"Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具","canonicalUrl":"https://www.xpersona.co/agent/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a","canonicalPath":"/agent/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a","generatedAt":"2026-10-10T00:06:28.953Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-09T16:54:35.017Z","emptyReason":null},"description":"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 Skill: Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具 Owner: 18072937735 Summary: Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 Tags: latest:1.0.16 Version history: v1.0","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.3K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s17f8q65zg3y98t86jdg1177g583whq8:smyx-child-dangerous-behavior-recognition-analysis","sourceUrl":"https://clawhub.ai/18072937735/smyx-child-dangerous-behavior-recognition-analysis","homepage":"https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/18072937735/smyx-child-dangerous-behavior-recognition-analysis","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":40,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety sup"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:54:35.017Z","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":"2026-10-09T16:54:35.017Z","emptyReason":null},"stars":null,"forks":null,"downloads":2266,"packageName":null,"latestVersion":"1.0.16","tractionLabel":"2.3K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T16:54:35.017Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T16:54:35.017Z","lastCrawledAt":"2026-10-09T16:54:35.017Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T16:54:35.017Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.16","createdAt":"2026-09-27T23:47:34.746Z","changelog":"- Updated version number to 1.0.18 in documentation. - Removed the file skill-card.md from the project. - No functional or technical changes described; update is limited to project documentation and file cleanup.","fileCount":31,"zipByteSize":39974},{"version":"1.0.15","createdAt":"2026-09-25T20:19:31.909Z","changelog":"- Updated skill version to 1.0.17. - Revised configuration files in the common scripts directory. - Removed the redundant skill-card.md documentation file. - SKILL.md: Bumped version metadata and updated documentation content to reflect current version information.","fileCount":31,"zipByteSize":39881},{"version":"1.0.14","createdAt":"2026-09-13T09:32:29.445Z","changelog":"Version 1.0.16 - Updated documentation in SKILL.md (version updated, text/content improvements). - Removed redundant file: skill-card.md. - No functional or interface changes; this release focuses on documentation cleanup and maintenance.","fileCount":31,"zipByteSize":40135},{"version":"1.0.13","createdAt":"2026-08-27T15:19:31.025Z","changelog":"Version 1.0.14 - Updated documentation in SKILL.md to reflect latest guidelines and workflow. - Removed outdated skill-card.md for better maintenance. - No changes to API usage or skill capabilities; this update is documentation and structure only.","fileCount":31,"zipByteSize":40233},{"version":"1.0.12","createdAt":"2026-08-20T23:17:29.617Z","changelog":"- Version update to 1.0.13. - Documentation updated in SKILL.md. - Removed the redundant file skill-card.md. - Minor configuration changes in scripts/config.yaml.","fileCount":31,"zipByteSize":40167},{"version":"1.0.11","createdAt":"2026-08-11T17:02:40.422Z","changelog":"- Removed the file: skill-card.md. - SKILL.md updated to increment version to 1.0.11. - No user-facing logic or feature changes; documentation only. - No breaking changes introduced.","fileCount":31,"zipByteSize":40023},{"version":"1.0.10","createdAt":"2026-08-04T23:39:29.009Z","changelog":"- Removed the skill-card.md file. - No functional or behavioral changes to the skill itself.","fileCount":31,"zipByteSize":40179},{"version":"1.0.9","createdAt":"2026-08-01T21:34:28.664Z","changelog":"- Updated version to 1.0.10 and revised documentation in SKILL.md. - Removed the skill-card.md file. - No feature or logic changes to the skill itself; this is a documentation and minor maintenance update.","fileCount":31,"zipByteSize":40156}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17f8q65zg3y98t86jdg1177g583whq8:smyx-child-dangerous-behavior-recognition-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-child-dangerous-behavior-recognition-a/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T00:06:28.950Z"}},"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-child-dangerous-behavior-recognition-a/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-dangerous-behavior-recognition-a/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":"2026-10-09T16:54:35.017Z","emptyReason":null},"readme":"Skill: Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\nOwner: 18072937735\n\nSummary: Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\n\nTags: latest:1.0.16\n\nVersion history:\n\nv1.0.16 | 2026-09-27T23:47:34.746Z | auto\n\n- Updated version number to 1.0.18 in documentation.\n- Removed the file skill-card.md from the project.\n- No functional or technical changes described; update is limited to project documentation and file cleanup.\n\nv1.0.15 | 2026-09-25T20:19:31.909Z | auto\n\n- Updated skill version to 1.0.17.\n- Revised configuration files in the common scripts directory.\n- Removed the redundant skill-card.md documentation file.\n- SKILL.md: Bumped version metadata and updated documentation content to reflect current version information.\n\nv1.0.14 | 2026-09-13T09:32:29.445Z | auto\n\nVersion 1.0.16\n\n- Updated documentation in SKILL.md (version updated, text/content improvements).\n- Removed redundant file: skill-card.md.\n- No functional or interface changes; this release focuses on documentation cleanup and maintenance.\n\nv1.0.13 | 2026-08-27T15:19:31.025Z | auto\n\nVersion 1.0.14\n\n- Updated documentation in SKILL.md to reflect latest guidelines and workflow.\n- Removed outdated skill-card.md for better maintenance.\n- No changes to API usage or skill capabilities; this update is documentation and structure only.\n\nv1.0.12 | 2026-08-20T23:17:29.617Z | auto\n\n- Version update to 1.0.13.\n- Documentation updated in SKILL.md.\n- Removed the redundant file skill-card.md.\n- Minor configuration changes in scripts/config.yaml.\n\nv1.0.11 | 2026-08-11T17:02:40.422Z | auto\n\n- Removed the file: skill-card.md.\n- SKILL.md updated to increment version to 1.0.11.\n- No user-facing logic or feature changes; documentation only.\n- No breaking changes introduced.\n\nv1.0.10 | 2026-08-04T23:39:29.009Z | auto\n\n- Removed the skill-card.md file.\n- No functional or behavioral changes to the skill itself.\n\nv1.0.9 | 2026-08-01T21:34:28.664Z | auto\n\n- Updated version to 1.0.10 and revised documentation in SKILL.md.\n- Removed the skill-card.md file.\n- No feature or logic changes to the skill itself; this is a documentation and minor maintenance update.\n\nv1.0.8 | 2026-07-18T04:19:27.816Z | auto\n\n- Updated version from 1.0.6 to 1.0.7 in documentation.\n- Removed the file `skill-card.md`.\n- Made small updates to documentation in SKILL.md; no feature or logic changes noted.\n- No changes to functional code or features.\n\nv1.0.7 | 2026-07-06T05:30:05.359Z | auto\n\n- Removed the file skill-card.md from the project.\n- No changes were made to the SKILL.md content or functionality.\n\nv1.0.6 | 2026-07-05T13:04:27.509Z | auto\n\n- Updated to version 1.0.6.\n- Internal scripts improved: changes applied to config, DAO, and utility logic for more robust operation.\n- Documentation updates in SKILL.md for clearer workflow and constraints.\n- Removed redundant skill-card.md file for cleaner project structure.\n\nv1.0.5 | 2026-06-27T18:48:25.967Z | auto\n\n**Version 1.0.5 Changelog**\n\n- Major update to documentation: SKILL.md completely restructured with clearer usage flow, table overviews, and a strong focus on automatic/hidden identity management.\n- Internal user identity acquisition and usage are now fully automatic; users are never asked for identity values or to provide open-id.\n- All instructions and examples now hide identity parameters from users, ensuring privacy and simplicity.\n- History report queries are strictly cloud-based; all local/memory/manual fallback references removed for clarity.\n- Redundant files removed and resources/index updated for easier navigation and compliance.\n\nv1.0.4 | 2026-06-21T14:37:28.688Z | auto\n\nVersion 1.0.4 introduces structural and configuration updates for improved code organization and clarity.\n\n- Refactored skill structure: added new `skills/smyx_analysis` module, removed `skills/face_analysis` and related files.\n- Updated and simplified configuration file paths and loading logic.\n- Clarified open-id acquisition steps and file locations in documentation.\n- Adjusted video file size limit from 100MB to 10MB.\n- Updated license and included it in metadata.\n- Improved separation of common and analysis-specific code for easier maintenance.\n\nv1.0.3 | 2026-05-15T10:42:41.380Z | auto\n\n- Improved code structure across common scripts for better maintainability.\n- Updated initialization processes in skills/smyx_common/scripts/__init__.py.\n- Enhanced configuration handling in skills/smyx_common/scripts/config.py.\n- Refined utility functions in skills/smyx_common/scripts/util.py.\n\nv1.0.2 | 2026-05-09T11:44:39.749Z | auto\n\n## v1.0.2 Changelog\n\n- Internal updates to scripts in face_analysis and smyx_common modules\n- No user-facing feature or documentation changes\n- SKILL.md remains unchanged (version and description not updated)\n- Infrastructure or dependency preparations may have been improved\n\nv1.0.1 | 2026-05-02T03:27:38.055Z | auto\n\n- Improved configuration loading and management for API keys and parameters.\n- Updated config files (dev, test, and production) for clearer API and authentication settings.\n- Enhanced error handling and safeguards around open-id retrieval and usage.\n- Refactored utility and script logic for more robust, predictable behavior.\n- SKILL.md and documentation updated for version clarity and stricter usage/calling rules.\n\nv1.0.0 | 2026-04-14T08:55:25.020Z | auto\n\nInitial release: AI-powered tool for real-time child dangerous behavior recognition and alerting.\n\n- Detects climbing, playing with fire, touching power sources, and dangerous actions near windows from video streams.\n- Provides instant alerts and generates structured safety reports for homes, kindergartens, and nurseries.\n- Strict open-id acquisition and data access controls enforced for security and privacy.\n- All report queries fetch data from the cloud API; local memory access is strictly prohibited.\n- Outputs historical safety reports in clear Markdown tables with direct report links.\n\nArchive index:\n\nArchive v1.0.16: 31 files, 39974 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (2161b), SKILL.md (9663b), 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 (170b)\n\nFile v1.0.16:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.18\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.16:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.16\",\n  \"publishedAt\": 1790552854746\n}\n\nFile v1.0.16:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\n\nFile v1.0.16: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 v1.0.16:scripts/config.yaml\n\n{}\n\nFile v1.0.16:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.16: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 v1.0.16: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 v1.0.16: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 v1.0.16:skill-card.md\n\n## Description:\n\nAnalyzes videos for hazardous child behaviors such as climbing, playing with fire, touching electrical sources, and risky actions near windows, and provides alerts and structured reports.\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\nCaregivers and staff in homes, nurseries, and classrooms can analyze monitoring videos for potentially hazardous child behavior and review alerts or historical reports. Alerts should be checked by a person rather than treated as a substitute for supervision.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Children's videos or video URLs may be sent to external analysis services.\n\nMitigation: Obtain appropriate consent and review the external data flow before submitting footage from homes, nurseries, or classrooms.\n\nRisk: The skill may silently associate analysis with an identity and store account tokens locally.\n\nMitigation: Review identity and local token storage practices before installation; restrict access to the workspace and stored credentials.\n\nRisk: Historical cloud reports may be retrieved automatically.\n\nMitigation: Limit use to authorized operators and review who can access historical reports.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis)\n- [Skill demo](https://lifeemergence.com/sample.html)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, JSON]\n\n**Output Format:** [Structured analysis report or Markdown report list with links; optional JSON output file]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes risk alerts, suggested actions, and report links when available.]\n\n## Skill Version(s):\n\n1.0.16 (source: ClawHub release)\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 v1.0.16:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.16:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.15: 31 files, 39881 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (1995b), SKILL.md (9663b), 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 (170b)\n\nFile v1.0.15:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.17\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.15:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.15\",\n  \"publishedAt\": 1790367571909\n}\n\nFile v1.0.15:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\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 child-monitoring videos for hazardous behaviors and provides risk alerts and structured reports.\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\nCaregivers and childcare staff can analyze video files or URLs for hazardous child behaviors, review risk reports, and request historical reports. Confirm consent and cloud-processing arrangements before using it with children’s footage.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Child-monitoring videos or URLs are sent to lifeemergence.com cloud services; consent, retention, and report access controls are unclear.\n\nMitigation: Review cloud-processing terms and independently establish consent, retention, and report-access controls before using real footage.\n\nRisk: The skill silently creates or reuses local identity records and stored tokens.\n\nMitigation: Inspect local credential handling and define token access and cleanup procedures before installation.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis)\n- [Analysis API documentation](skills/smyx_analysis/references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Markdown, JSON]\n\n**Output Format:** [Structured report or Markdown table for historical reports; optional JSON output file]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Includes risk findings, recommendations, and report links when available]\n\n## Skill Version(s):\n\n1.0.15 (source: server-resolved release; bundled frontmatter says 1.0.17)\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: 31 files, 40135 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (2616b), SKILL.md (9663b), 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 (170b)\n\nFile v1.0.14:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.16\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.14:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.14\",\n  \"publishedAt\": 1789291949445\n}\n\nFile v1.0.14:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\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\nDetects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts for child safety supervision in homes, kindergartens, and nurseries.\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\nCaregivers, child-safety operators, and agents supporting child supervision workflows use this skill to analyze monitoring videos or image inputs for hazardous child behaviors and produce structured alerts, reports, recommendations, and report links. Agents can also retrieve historical child-dangerous-behavior analysis reports when requested.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill handles sensitive child-monitoring videos and historical reports.\n\nMitigation: Use only with explicit consent and documented controls for media upload destinations, retention, access, and report handling.\n\nRisk: The security evidence reports development HTTP endpoints and limited disclosure around stored tokens.\n\nMitigation: Require a production configuration using HTTPS endpoints and protect or avoid persisted tokens before real child-safety monitoring use.\n\nRisk: The skill silently creates or reuses identities for analysis and historical report access.\n\nMitigation: Confirm account identity handling, consent, and audit expectations with the publisher before deployment.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis)\n- [Skill Demo](https://lifeemergence.com/sample.html)\n- [API Documentation](references/api_doc.md)\n- [Analysis API Documentation](skills/smyx_analysis/references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, json, shell commands, guidance]\n\n**Output Format:** [Markdown and JSON structured analysis reports with risk findings, recommendations, historical report tables, and report links.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May process local or URL-based media inputs and may retrieve historical reports associated with an internal identity.]\n\n## Skill Version(s):\n\n1.0.14 (source: server release metadata; artifact frontmatter and changelog reference 1.0.16)\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: 31 files, 40233 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (2747b), SKILL.md (9663b), 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 (170b)\n\nFile v1.0.13:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.14\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.13:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.13\",\n  \"publishedAt\": 1787843971025\n}\n\nFile v1.0.13:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\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\nDetects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts for child safety supervision in homes, kindergartens, and nurseries.\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\nDevelopers and operators use this skill to submit child-monitoring media for hazardous-behavior recognition, alerts, structured reports, and report history lookup in home, kindergarten, or nursery settings.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Real child, home, school, or nursery footage may be uploaded or referenced by URL for backend analysis.\n\nMitigation: Use only approved media with appropriate consent, and install the skill only after trusting the publisher and backend data flow.\n\nRisk: The skill can silently create or reuse an internal identity and store service tokens in the local workspace database.\n\nMitigation: Run it in an isolated workspace, restrict local file access, and clear local identity or token state when the analysis session is complete.\n\nRisk: Cloud report history queries can expose sensitive child-monitoring reports.\n\nMitigation: Limit history access to authorized users and review report history behavior before enabling the skill in shared environments.\n\nRisk: Automated alerts are an auxiliary child-safety aid and may miss or misclassify dangerous behavior.\n\nMitigation: Require human confirmation of alerts and do not use the skill as the sole supervision or emergency-response mechanism.\n\n## Reference(s):\n\n- [ClawHub Skill Page](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis)\n- [Skill Demo](https://lifeemergence.com/sample.html)\n- [API Documentation](references/api_doc.md)\n- [Common Analysis API Documentation](skills/smyx_analysis/references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON, files, shell commands, guidance]\n\n**Output Format:** [Markdown or JSON structured analysis report with optional saved output file]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Reports can include detected behavior details, alert status, recommendations, report links, and cloud report history results.]\n\n## Skill Version(s):\n\n1.0.13 (source: server release metadata; artifact frontmatter and auto changelog mention 1.0.14)\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: 31 files, 40167 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (2609b), SKILL.md (9663b), 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 (170b)\n\nFile v1.0.12:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.13\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.12:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.12\",\n  \"publishedAt\": 1787267849617\n}\n\nFile v1.0.12:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\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: dev\n\nFile v1.0.12:skill-card.md\n\n## Description:\n\nDetects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts for child safety supervision in homes, kindergartens, and nurseries.\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\nDevelopers and operators use this skill to analyze child-monitoring videos or URLs for hazardous behavior, generate structured risk reports, and query cloud-stored historical reports.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Child-safety videos or URLs may be processed through the provider's cloud services.\n\nMitigation: Use the skill only when the operator accepts the provider's media processing, retention, and deletion practices for sensitive child-safety footage.\n\nRisk: The skill can create or reuse a local identity tied to cloud-stored reports.\n\nMitigation: Review identity handling and cloud report association before deployment, and avoid exposing internal identity values in user-facing outputs.\n\nRisk: Bundled common configuration may select development or private-network endpoints.\n\nMitigation: Review and update configuration endpoints before use in production or customer-facing environments.\n\nRisk: Account tokens may be persisted with incomplete disclosure.\n\nMitigation: Confirm token storage, rotation, and deletion practices before installing or running the skill.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis)\n- [Skill demo](https://lifeemergence.com/sample.html)\n- [API documentation](references/api_doc.md)\n- [Analysis API documentation](skills/smyx_analysis/references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, API Calls, Markdown, JSON, Files, Shell commands, Guidance]\n\n**Output Format:** [Markdown summaries, JSON analysis results, report links, and optional output files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Supports local video files or video URLs, configurable alert threshold, basic/standard/json detail levels, and historical report listing.]\n\n## Skill Version(s):\n\n1.0.12 (source: server release metadata; artifact frontmatter reports 1.0.13)\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: 31 files, 40023 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (2254b), SKILL.md (9663b), 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 (170b)\n\nFile v1.0.11:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.11\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.11:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.11\",\n  \"publishedAt\": 1786467760422\n}\n\nFile v1.0.11:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\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\nDetects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time 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\nExternal users and safety supervisors use this skill to analyze child monitoring videos or video URLs for hazardous behaviors and produce structured safety reports, alerts, recommendations, and report links. It is intended as an aid for homes, kindergartens, and nurseries, not as a replacement for human supervision.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Sensitive child video files or video URLs are sent to the configured cloud service.\n\nMitigation: Use only with appropriate consent, retention rules, access controls, and legal authority; prefer explicit confirmation before uploads.\n\nRisk: Report history is fetched from the cloud and local identity or token state may be created or reused in the workspace.\n\nMitigation: Review workspace identity state and confirm authorization before history lookups, especially in homes, schools, kindergartens, or nurseries.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis)\n- [Skill demo](https://lifeemergence.com/sample.html)\n- [API interface documentation](references/api_doc.md)\n- [Common analysis API documentation](skills/smyx_analysis/references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [Analysis, Markdown, JSON, Shell commands, Configuration]\n\n**Output Format:** [Markdown or JSON structured analysis reports with optional report links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Can output basic, standard, or JSON detail levels and can save results to a local output file.]\n\n## Skill Version(s):\n\n1.0.11 (source: frontmatter and server 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 v1.0.11: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: 31 files, 40179 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (2636b), SKILL.md (9663b), 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 (170b)\n\nFile v1.0.10:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.10\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.10:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.10\",\n  \"publishedAt\": 1785886769009\n}\n\nFile v1.0.10:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\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:\n\nDetects hazardous child behaviors such as climbing, playing with fire, touching power sources, and risky window activity in monitoring media, then returns alerts and structured reports.\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\nExternal users and developers use this skill to analyze child-monitoring video or image inputs for hazardous behavior indicators and to retrieve structured child-safety reports. It supports supervision workflows for homes, kindergartens, nurseries, and similar monitored spaces.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Sensitive child-monitoring videos or URLs are sent to a remote service for analysis.\n\nMitigation: Use only with appropriate consent and authorization, avoid uploading unnecessary sensitive content, and confirm remote processing is acceptable for the deployment context.\n\nRisk: The skill may create or reuse an account identity, persist tokens locally, and retrieve cloud report history automatically.\n\nMitigation: Review account-linking behavior before deployment, restrict host access to local credentials, and clear or rotate stored credentials when no longer needed.\n\nRisk: Cloud report history can be retrieved automatically with limited user-facing control.\n\nMitigation: Run the skill in a controlled environment, verify report-history access expectations with users or administrators, and monitor outbound service access.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis)\n- [Skill demo](https://lifeemergence.com/sample.html)\n- [API documentation](artifact/references/api_doc.md)\n- [Analysis API documentation](artifact/skills/smyx_analysis/references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown and JSON analysis reports with optional report links and history tables]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include hazard detections, risk summaries, recommendations, alert-threshold context, and cloud report links.]\n\n## Skill Version(s):\n\n1.0.10 (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 v1.0.10: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: 31 files, 40156 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (2702b), SKILL.md (9663b), 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 (169b)\n\nFile v1.0.9:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.10\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.9:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.9\",\n  \"publishedAt\": 1785620068664\n}\n\nFile v1.0.9:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\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>\nDetects child hazardous behaviors such as climbing, playing with fire, touching power sources, and dangerous actions near windows, then returns alerts and structured safety analysis 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>\nExternal users, caregivers, and operators use this skill to analyze child-monitoring video files or URLs for hazardous behaviors and to retrieve structured reports and report history. It is intended as an auxiliary child-safety monitoring tool, not as a substitute for human confirmation and intervention. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Sensitive child-monitoring videos or video URLs may be sent to the configured cloud service for analysis. <br>\nMitigation: Use the skill only with explicit consent, test with non-sensitive media first, and confirm the publisher's retention and deletion terms before using real monitoring footage. <br>\nRisk: Report history is tied to an automatically resolved account and can expose prior child-safety analysis reports. <br>\nMitigation: Use a dedicated account for testing and restrict report-history access to authorized operators. <br>\nRisk: Service tokens may be stored in a local workspace database. <br>\nMitigation: Run the skill in a controlled workspace, protect local storage, and rotate or remove credentials after evaluation. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill release page](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis) <br>\n- [Skill demo](https://lifeemergence.com/sample.html) <br>\n- [API documentation](artifact/references/api_doc.md) <br>\n- [Shared analysis API documentation](artifact/skills/smyx_analysis/references/api_doc.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, json, files] <br>\n**Output Format:** [Markdown or JSON analysis reports, optional saved output files, and report links] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Supports basic, standard, and JSON detail levels; local video files are limited to mp4, avi, and mov formats up to 10 MB.] <br>\n\n## Skill Version(s): <br>\n1.0.9 (source: server release metadata; artifact frontmatter reports 1.0.10) <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: 31 files, 40170 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (2704b), SKILL.md (9662b), 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 (169b)\n\nFile v1.0.8:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.7\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.8:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.8\",\n  \"publishedAt\": 1784348367816\n}\n\nFile v1.0.8:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\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>\nDetects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts for child safety supervision in homes, kindergartens, and nurseries. <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>\nExternal users and developers use this skill to analyze child monitoring videos or video URLs for hazardous behaviors, receive structured safety reports, and query historical analysis reports. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Sensitive child media may be uploaded or provided by URL to external cloud services for analysis. <br>\nMitigation: Use only footage approved for that service, confirm consent and retention requirements, and avoid sending media that violates local privacy rules. <br>\nRisk: The skill can create or reuse persistent identity and token data while associating analysis reports with that identity. <br>\nMitigation: Run it only in governed workspaces where local token storage, identity creation, and report association are acceptable and periodically review stored credentials. <br>\nRisk: Historical report queries can retrieve prior child-safety analysis reports from the cloud service. <br>\nMitigation: Limit access to trusted operators and verify that report visibility and retention align with the deployment's privacy requirements. <br>\n\n\n## Reference(s): <br>\n- [ClawHub Skill Page](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis) <br>\n- [Skill Demo](https://lifeemergence.com/sample.html) <br>\n- [API Documentation](artifact/references/api_doc.md) <br>\n- [Shared Analysis API Documentation](artifact/skills/smyx_analysis/references/api_doc.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [analysis, markdown, json, shell commands, files] <br>\n**Output Format:** [Markdown report text with optional JSON detail, historical report listings, and report export links] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May write an output file when --output is supplied; supports mp4, avi, and mov files up to 10 MB or video URLs.] <br>\n\n## Skill Version(s): <br>\n1.0.8 (source: server release metadata; 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 v1.0.8: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: 31 files, 40079 bytes\n\nFiles: references/api_doc.md (666b), scripts/__init__.py (31b), scripts/child_dangerous_behavior_recognition_analysis.py (7693b), scripts/config.py (679b), scripts/config.yaml (3b), scripts/skill.py (579b), skill-card.md (2696b), SKILL.md (9662b), 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 (28605b), _meta.json (169b)\n\nFile v1.0.7:SKILL.md\n\n---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.6\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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 | 📥 准备视频输入 | 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 | ⚙️ 执行儿童危险行为识别 | 调用 `-m scripts.child_dangerous_behavior_recognition_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` | 本地视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--alert-threshold` | 危险行为预警阈值，高于该分值发出预警，默认 0.6 | 按需填写 |\n| `--list` | 显示儿童危险行为识别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/child_dangerous_behavior_recognition_analysis.py`](scripts/child_dangerous_behavior_recognition_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 | 视频要求：支持 mp4/avi/mov 格式，最大 10MB |\n| 🔎 使用提醒 | 本技能仅作儿童安全监护辅助，发现危险预警请立即确认 |\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 | 当显示历史识别报告清单的时候，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# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json\n```\n\nFile v1.0.7:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.7\",\n  \"publishedAt\": 1783315805359\n}\n\nFile v1.0.7:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析\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>\nDetects child hazardous behaviors such as climbing, playing with fire, touching power sources, and dangerous actions near windows, then returns alerts and structured reports for child safety supervision. <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>\nExternal users and developers use this skill to submit child-monitoring video or URL inputs to a cloud analysis service, detect hazardous behaviors, and retrieve current or historical structured reports for supervision workflows. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Sensitive child-monitoring images or videos, report history, and identity-linked metadata are sent to a Life Emergence/SMYX cloud service. <br>\nMitigation: Use the skill only with appropriate consent and after confirming the provider's retention, deletion, access-control, and stored-report access practices. <br>\nRisk: The skill can create or reuse a local identity and persist local token or identity data. <br>\nMitigation: Run it in a protected workspace, restrict access to local data files, and remove or rotate local credentials when the skill is no longer needed. <br>\nRisk: Hazard alerts and reports may be incomplete or incorrect for real-world child safety decisions. <br>\nMitigation: Treat outputs as supervision aids and require a responsible human to immediately confirm any warning or missing warning against the actual scene. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-dangerous-behavior-recognition-analysis) <br>\n- [Skill demo](https://lifeemergence.com/sample.html) <br>\n- [API interface reference](references/api_doc.md) <br>\n- [SMYX analysis API reference](skills/smyx_analysis/references/api_doc.md) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Markdown, JSON, Files, Guidance] <br>\n**Output Format:** [Markdown and JSON text with report links; optional local output file] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include child hazardous-behavior counts, risk alerts, report-export links, and historical report lists.] <br>\n\n## Skill Version(s): <br>\n1.0.7 (source: server release metadata; SKILL.md frontmatter is 1.0.6) <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","readmeExcerpt":"Skill: Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具 Owner: 18072937735 Summary: Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 Tags: latest:1.0.16 Version history: v1.0","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"python -m scripts.child_dangerous_behavior_recognition_analysis --list"},{"language":"text","snippet":"requests>=2.28.0"},{"language":"bash","snippet":"# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json"},{"language":"bash","snippet":"python -m scripts.child_dangerous_behavior_recognition_analysis --list"},{"language":"text","snippet":"requests>=2.28.0"},{"language":"bash","snippet":"# 分析本地监控视频\npython -m scripts.child_dangerous_behavior_recognition_analysis --input /path/to/monitor.mp4 --alert-threshold 0.6\n\n# 分析网络监控视频，调整预警阈值\npython -m scripts.child_dangerous_behavior_recognition_analysis --url https://example.com/monitor.mp4 --alert-threshold 0.5\n\n# 显示历史识别报告/显示识别报告清单列表/显示历史儿童危险行为报告（自动触发关键词：查看历史识别报告、历史报告、识别报告清单等）\npython -m scripts.child_dangerous_behavior_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.child_dangerous_behavior_recognition_analysis --input video.mp4 --output result.json"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: \"child-dangerous-behavior-recognition-analysis\"\ndescription: \"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护\"\nversion: \"1.0.18\"\nlicense: \"MIT-0\"\n---\n\n# 🧒 Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具\n\n> **智能健康/识别分析中枢** · 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 | **儿童危险行为识别分析工具** |\n| 🎯 核心目标 | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 |\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、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_DANGEROUS_BEHAVIOR_RECOGNITION` |\n\nThis capability enables real-time recognition of hazardous actions by children—such as climbing, playing with fire,\ntouching electrical sources, or lingering near windows—in settings like homes, kindergartens, or nurseries. By analyzing\nhuman skeletal keypoints and behavioral trajectories from video streams, the system instantly triggers local or remote\nalerts upon detecting high-risk behaviors, prompting guardians to intervene immediately. Ideal for 24/7 safety\nmonitoring in indoor and semi-open areas, it effectively reduces the risk of accidental injuries and enhances\nsupervision efficiency.\n\n本技能可实时识别儿童在家庭、幼儿园或托儿所等场景中的攀爬、玩火、触电源及窗边逗留等危险动作。系统通过视频流分析人体骨骼关键点与行为轨迹，一旦检测到高风险行为，立即触发本地或远程预警，提示监护人员及时干预。适用于室内及半开放区域的24小时安全监护，有效降低儿童意外伤害风险，提升监护效率。\n\n## 🎬 技能演示 | Skill Demo\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n## 🎯 任务目标 | Goals\n\n### 1. 🧩 技能用途\n\n通过监控视频对儿童活动进行危险行为识别，获取结构化的儿童危险行为识别报告\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 危险动作识别 |\n| 2 | 实时危险预警 |\n| 3 | 危险行为频次统计 |\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 URL 或文件需要进行儿童危险行为识别时，默认触发本技能 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童安全监护、危险行为识别，提及攀爬、玩火、触电、窗边危险、儿童安全等关键词，并且上传了视频文件 |\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** ：查看历史识别报告、危险行为识别报告清单、识别报告列表、查询历史报告、显示所有识别报告、儿童危险行为识别历史记录，查询儿童危险行为识别分析报告 |\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.child_dangerous_behavior_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_dangerous_behavior_recognition_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"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-dangerous-behavior-recognition-analysis\",\n  \"version\": \"1.0.16\",\n  \"publishedAt\": 1790552854746\n}"},{"path":"references/api_doc.md","content":"# API 接口文档\n\n此处用于存放宠物健康分析 API 的接口文档，待后续补充。\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## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动健康分析任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史报告\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_PET_HEALTH_ANALYSIS` - 开放平台宠物健康分析"},{"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":"Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 Skill: Child Hazardous Behavior Recognition Tool | 儿童危险行为识别分析工具 Owner: 18072937735 Summary: Detects climbing, playing with fire, touching power sources, and dangerous actions near windows, providing real-time alerts. It is suitable for child safety supervision in scenarios such as homes, kindergartens, and nurseries. | 儿童危险行为识别技能，识别攀爬、玩火、触电源、窗边危险动作并实时预警，适用于家庭、幼儿园、托儿所等场景儿童安全监护 Tags: latest:1.0.16 Version history: v1.0","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":883,"uniquenessScore":47,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T16:54:35.017Z","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":"2026-10-09T16:54:35.017Z","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":"2026-10-10T00:06:28.953Z","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"}]}}}