{"id":"31731632-0dcd-4f5d-b254-4c88d2ede241","entityType":"agent","slug":"clawhub-18072937735-smyx-child-emotion-recognition-analysis","name":"Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落）","canonicalUrl":"https://www.xpersona.co/agent/clawhub-18072937735-smyx-child-emotion-recognition-analysis","canonicalPath":"/agent/clawhub-18072937735-smyx-child-emotion-recognition-analysis","generatedAt":"2026-10-10T03:38:46.655Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T11:05:12.850Z","emptyReason":null},"description":"Using fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 2.9K downloads reported by the source. Last updated 10/9/2026.","installCommand":"clawhub skill install s17f8q65zg3y98t86jdg1177g583whq8:smyx-child-emotion-recognition-analysis","sourceUrl":"https://clawhub.ai/18072937735/smyx-child-emotion-recognition-analysis","homepage":"https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/18072937735/smyx-child-emotion-recognition-analysis","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":40,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落） technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust met"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-09T11:05:12.850Z","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":"2026-10-09T11:05:12.850Z","emptyReason":null},"stars":null,"forks":null,"downloads":2865,"packageName":null,"latestVersion":"1.0.30","tractionLabel":"2.9K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T11:05:12.850Z","emptyReason":null},"lastUpdatedAt":"2026-10-09T11:05:12.850Z","lastCrawledAt":"2026-10-09T11:05:12.850Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-10T11:05:12.850Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.30","createdAt":"2026-09-30T21:43:31.349Z","changelog":"- Renamed and refactored skill and main script to `smyx_child_emotion_recognition_analysis` for improved clarity and alignment with application scenarios. - Expanded scenario description and supported features to include multimodal (vision + audio) emotion analysis of children in homes/kindergartens. - Updated capability list: added audio cry analysis, emotion strength/duration estimation, and real-time alert/soothing suggestions. - Replaced all command-line usage examples and script references to match the new script/module naming. - Removed outdated or duplicate documentation files and references; added new documentation reflecting updated interface and workflow.","fileCount":31,"zipByteSize":40408},{"version":"1.0.29","createdAt":"2026-09-28T07:32:30.053Z","changelog":"**Summary:** Major refactor, renaming, and simplification of the skill structure for clarity and easier usage. - Renamed the skill and main script from `smyx-child-emotion-recognition-analysis` to `child-emotion-recognition-analysis`; updated naming in all documentation. - Replaced and refactored the main script module (now `scripts/child_emotion_recognition_analysis.py`) and removed the previous main and skill card files. - Revised and simplified the SKILL.md for clearer goals, use cases, script parameters, and resource index. - Streamlined capability descriptions, input/output formats, workflow steps, and usage examples for easier integration and understanding. - Updated trigger conditions and automatic behavior to focus on negative emotion detection and parent notification.","fileCount":31,"zipByteSize":38302},{"version":"1.0.28","createdAt":"2026-09-25T01:58:34.261Z","changelog":"- Skill renamed to \"smyx-child-emotion-recognition-analysis\", with new module and script file naming to match. - Updated skill description and documentation to emphasize multimodal analysis (facial expression, body movement, cry sound) for real-time detection of child emotions (happy, sad, angry, fearful, etc.). - Adjusted capability scope: added more detailed emotion/intensity classification, and clarified requirements for video (with optional audio) inputs. - Changed the main script file to scripts/smyx_child_emotion_recognition_analysis.py; removed and deprecated the old scripts/child_emotion_recognition_analysis.py. - Updated example commands and API calling conventions to use the new script name. - Improved privacy, usage, and reference notes, explicitly including privacy compliance for child monitoring data.","fileCount":31,"zipByteSize":40499},{"version":"1.0.27","createdAt":"2026-09-22T23:42:24.770Z","changelog":"- Updated version to 1.0.16 in SKILL.md. - Removed the file skill-card.md. - Minor documentation and metadata adjustments in SKILL.md. - No changes to functionality or usage.","fileCount":31,"zipByteSize":38565},{"version":"1.0.26","createdAt":"2026-09-08T20:59:30.192Z","changelog":"- Updated SKILL.md version from 1.0.14 to 1.0.15. - Minor documentation updates in SKILL.md; no feature changes. - Removed skill-card.md file.","fileCount":31,"zipByteSize":38434},{"version":"1.0.25","createdAt":"2026-08-28T07:12:33.739Z","changelog":"- Skill renamed to \"child-emotion-recognition-analysis,\" with updated file and module names. - Primary script entrypoint changed from `smyx_child_emotion_recognition_analysis.py` to `child_emotion_recognition_analysis.py`. - Skill description and documentation rewritten for clarity and easier use; now summarizes scenarios as homes, kindergartens, and daycare centers. - Focus simplified to identifying negative emotions via surveillance (crying, anger, fear, distress) and active notification/soothing for caregivers. - Usability improved: removes extra detail from triggers/capabilities and modernizes script usage examples. - Deprecated files and outdated documentation removed.","fileCount":31,"zipByteSize":38539},{"version":"1.0.24","createdAt":"2026-08-25T06:48:36.458Z","changelog":"- Removed the file skill-card.md for this version. - No other functional or feature changes.","fileCount":31,"zipByteSize":40575},{"version":"1.0.23","createdAt":"2026-08-21T12:15:46.086Z","changelog":"**Major update: skill renamed, scope expanded, and script structure overhauled.** - Skill renamed to \"smyx-child-emotion-recognition-analysis\"; reflects broader multimodal emotion detection (not only negative emotions). - Multimodal recognition introduced: combines facial, audio (cry), and body-motion analysis for richer emotion classification (e.g., happy, sad, angry, fearful, not just negative states). - Main script replaced (`scripts/smyx_child_emotion_recognition_analysis.py` added, old one removed); command-line usage and parameters updated accordingly. - Documentation and workflow revised: new abilities, more detailed output options, new application scenarios, and explicit privacy/compliance notes. - \"Skill-card.md\" removed; documentation now concentrated in SKILL.md. - API reference and config updated for new approach and naming.","fileCount":31,"zipByteSize":40792}]},"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-emotion-recognition-analysis","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s17f8q65zg3y98t86jdg1177g583whq8:smyx-child-emotion-recognition-analysis` in an isolated environment before connecting it to live workloads.","No published capability contract is available yet, so validate auth and request/response behavior manually.","Review the upstream CLAWHUB listing at https://clawhub.ai/18072937735/smyx-child-emotion-recognition-analysis before using production credentials."],"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-emotion-recognition-analysis/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-emotion-recognition-analysis/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-emotion-recognition-analysis/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-emotion-recognition-analysis/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-emotion-recognition-analysis/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-emotion-recognition-analysis/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T03:38:46.651Z"}},"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-emotion-recognition-analysis/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-emotion-recognition-analysis/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-emotion-recognition-analysis/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-18072937735-smyx-child-emotion-recognition-analysis/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-09T11:05:12.850Z","emptyReason":null},"readme":"Skill: Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落）\n\nOwner: 18072937735\n\nSummary: Using fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。\n\nTags: latest:1.0.30\n\nVersion history:\n\nv1.0.30 | 2026-09-30T21:43:31.349Z | auto\n\n- Renamed and refactored skill and main script to `smyx_child_emotion_recognition_analysis` for improved clarity and alignment with application scenarios.\n- Expanded scenario description and supported features to include multimodal (vision + audio) emotion analysis of children in homes/kindergartens.\n- Updated capability list: added audio cry analysis, emotion strength/duration estimation, and real-time alert/soothing suggestions.\n- Replaced all command-line usage examples and script references to match the new script/module naming.\n- Removed outdated or duplicate documentation files and references; added new documentation reflecting updated interface and workflow.\n\nv1.0.29 | 2026-09-28T07:32:30.053Z | auto\n\n**Summary:** Major refactor, renaming, and simplification of the skill structure for clarity and easier usage.\n\n- Renamed the skill and main script from `smyx-child-emotion-recognition-analysis` to `child-emotion-recognition-analysis`; updated naming in all documentation.\n- Replaced and refactored the main script module (now `scripts/child_emotion_recognition_analysis.py`) and removed the previous main and skill card files.\n- Revised and simplified the SKILL.md for clearer goals, use cases, script parameters, and resource index.\n- Streamlined capability descriptions, input/output formats, workflow steps, and usage examples for easier integration and understanding.\n- Updated trigger conditions and automatic behavior to focus on negative emotion detection and parent notification.\n\nv1.0.28 | 2026-09-25T01:58:34.261Z | auto\n\n- Skill renamed to \"smyx-child-emotion-recognition-analysis\", with new module and script file naming to match.\n- Updated skill description and documentation to emphasize multimodal analysis (facial expression, body movement, cry sound) for real-time detection of child emotions (happy, sad, angry, fearful, etc.).\n- Adjusted capability scope: added more detailed emotion/intensity classification, and clarified requirements for video (with optional audio) inputs.\n- Changed the main script file to scripts/smyx_child_emotion_recognition_analysis.py; removed and deprecated the old scripts/child_emotion_recognition_analysis.py.\n- Updated example commands and API calling conventions to use the new script name.\n- Improved privacy, usage, and reference notes, explicitly including privacy compliance for child monitoring data.\n\nv1.0.27 | 2026-09-22T23:42:24.770Z | auto\n\n- Updated version to 1.0.16 in SKILL.md.\n- Removed the file skill-card.md.\n- Minor documentation and metadata adjustments in SKILL.md.\n- No changes to functionality or usage.\n\nv1.0.26 | 2026-09-08T20:59:30.192Z | auto\n\n- Updated SKILL.md version from 1.0.14 to 1.0.15.\n- Minor documentation updates in SKILL.md; no feature changes.\n- Removed skill-card.md file.\n\nv1.0.25 | 2026-08-28T07:12:33.739Z | auto\n\n- Skill renamed to \"child-emotion-recognition-analysis,\" with updated file and module names.\n- Primary script entrypoint changed from `smyx_child_emotion_recognition_analysis.py` to `child_emotion_recognition_analysis.py`.\n- Skill description and documentation rewritten for clarity and easier use; now summarizes scenarios as homes, kindergartens, and daycare centers.\n- Focus simplified to identifying negative emotions via surveillance (crying, anger, fear, distress) and active notification/soothing for caregivers.\n- Usability improved: removes extra detail from triggers/capabilities and modernizes script usage examples.\n- Deprecated files and outdated documentation removed.\n\nv1.0.24 | 2026-08-25T06:48:36.458Z | auto\n\n- Removed the file skill-card.md for this version.\n- No other functional or feature changes.\n\nv1.0.23 | 2026-08-21T12:15:46.086Z | auto\n\n**Major update: skill renamed, scope expanded, and script structure overhauled.**\n\n- Skill renamed to \"smyx-child-emotion-recognition-analysis\"; reflects broader multimodal emotion detection (not only negative emotions).\n- Multimodal recognition introduced: combines facial, audio (cry), and body-motion analysis for richer emotion classification (e.g., happy, sad, angry, fearful, not just negative states).\n- Main script replaced (`scripts/smyx_child_emotion_recognition_analysis.py` added, old one removed); command-line usage and parameters updated accordingly.\n- Documentation and workflow revised: new abilities, more detailed output options, new application scenarios, and explicit privacy/compliance notes.\n- \"Skill-card.md\" removed; documentation now concentrated in SKILL.md.\n- API reference and config updated for new approach and naming.\n\nv1.0.22 | 2026-08-20T09:40:29.554Z | auto\n\n- Skill renamed to \"child-emotion-recognition-analysis\" and streamlined; previous long name deprecated.\n- Main script entrypoint switched from `smyx_child_emotion_recognition_analysis.py` to `child_emotion_recognition_analysis.py`; old script removed.\n- Documentation (SKILL.md) significantly simplified and focused on core features and workflow.\n- Skill description and scope made more concise, emphasizing detection of negative child emotions, active reminder/notification, and home/daycare applicability.\n- Parameters, example commands, and API usage updated to reflect new script structure and naming.\n- Old documentation and redundant files (e.g., skill-card.md) removed; references, config, and main scripts updated for new workflow.\n\nv1.0.21 | 2026-08-14T22:30:29.419Z | auto\n\n- Major update: skill namespace and scripts refactored for \"smyx-child-emotion-recognition-analysis\".\n- Script filename changed from `child_emotion_recognition_analysis.py` to `smyx_child_emotion_recognition_analysis.py` (update CLI usage accordingly).\n- Skill name and description updated to highlight AI multimodal (video, audio, movement) emotion analysis and more general emotion states (happy, sad, angry, fearful).\n- Documentation and parameters revised for new input emphasis (audio/video), app/reminder integration, and privacy compliance for minors.\n- Old references and redundant files removed; documentation and resource links updated to point to new script paths.\n- Usage examples and API constraints aligned with new module and workflow.\n\nv1.0.20 | 2026-08-12T14:05:47.039Z | auto\n\n**Major update: streamlined and renamed the skill, improved input support, and simplified reporting process.**\n\n- Skill renamed to \"child-emotion-recognition-analysis\", with updated descriptions for broader clarity.\n- Core script renamed to `child_emotion_recognition_analysis.py`, replacing the previous module.\n- Support for both images and videos as inputs; clarified supported formats.\n- Simplified reporting and workflow instructions, focusing on negative emotions and care prompts.\n- Deprecated scripts and documentation removed; references updated for clarity.\n\nv1.0.19 | 2026-08-06T06:37:43.224Z | auto\n\n- Skill upgraded to \"smyx-child-emotion-recognition-analysis\" with enhanced multimodal emotion detection (facial, vocal, and body cues).\n- Added new script: scripts/smyx_child_emotion_recognition_analysis.py; removed old: scripts/child_emotion_recognition_analysis.py.\n- Skill description, name, scenario code, and workflow updated for broader emotion coverage (happy, sad, angry, fear, etc.) and scenarios.\n- Usage instructions, trigger rules, API requirements, and privacy notes revised for expanded video/audio support and integration use cases.\n- Obsolete file skill-card.md removed; documentation updated accordingly.\n\nv1.0.18 | 2026-08-02T23:43:27.996Z | auto\n\n- Removed the file skill-card.md from the project.\n- No changes to code or functionality were made—documentation file cleanup only.\n\nv1.0.17 | 2026-08-01T22:32:27.877Z | auto\n\n- Renamed main script and updated all references from smyx_child_emotion_recognition_analysis to child_emotion_recognition_analysis for clarity and consistency.\n- Simplified and streamlined the skill documentation, focusing on core features, main usage scenarios, and concise workflow.\n- Updated the skill name, description, and scene code for a clearer and more universally applicable positioning.\n- Removed redundant scripts and documentation files, including old script and duplicate card documentation.\n- Revised example commands to match new script naming and improved usability across both image and video inputs.\n- Clarified API usage requirements, output formatting, and mandatory cloud-based historical report retrieval.\n\nv1.0.16 | 2026-07-27T11:12:27.691Z | auto\n\n**Version 1.0.16 Changelog**\n\n- Renamed skill to \"smyx-child-emotion-recognition-analysis\" and updated task scope to include multimodal (video, audio) emotion detection.\n- Replaced old script (`child_emotion_recognition_analysis.py`) with a new main script (`smyx_child_emotion_recognition_analysis.py`), aligning command-line interface and workflow.\n- Revised and simplified capability description: now includes facial expression, cry-sound, and body-motion analysis, with sample use cases for homes and kindergartens.\n- Updated documentation (SKILL.md, references/api_doc.md) to reflect new triggers, input/output formats, privacy notes, and usage examples.\n- Removed obsolete files and references, aligning resource paths and commands with the new skill name and structure.\n\nv1.0.15 | 2026-07-16T19:19:32.366Z | auto\n\nVersion 1.0.15\n\n- Skill name and module renamed to \"child-emotion-recognition-analysis\"; files and identifiers updated accordingly.\n- Legacy scripts and documentation (e.g., smyx_child_emotion_recognition_analysis.py, skill-card.md) removed.\n- Added scripts/child_emotion_recognition_analysis.py as the new main script entry point.\n- Skill overview, description, examples, and trigger instructions in documentation now emphasize concise usage, negative emotion detection, and active notifications.\n- API script command changed to `python -m scripts.child_emotion_recognition_analysis` throughout documentation and examples.\n\nv1.0.14 | 2026-07-12T23:49:26.366Z | auto\n\n- Updated SKILL.md to version 1.0.4 with minor documentation adjustments and version increment.\n- Removed the redundant skill-card.md file.\n- Modified utility script (util.py) under skills/smyx_common/scripts; details not shown, but likely minor or internal updates.\n- No changes to user-facing features or APIs.\n\nv1.0.13 | 2026-07-06T21:25:28.051Z | auto\n\n**Major update: Skill renamed, capability scope clarified, and code/script entrypoint changed.**\n\n- Skill name updated to \"smyx-child-emotion-recognition-analysis\" with refreshed description and branding.\n- Main script renamed and entrypoint changed from `child_emotion_recognition_analysis.py` to `smyx_child_emotion_recognition_analysis.py`.\n- Documentation revised: clarifies multimodal analysis (facial, audio, motion), newly lists emotion types detected, and highlights privacy/compliance notes.\n- Script arguments and usage examples updated to reflect new script name and scenario focus.\n- Removed obsolete script, added new script file, and updated config/init as needed for new workflow.\n\nv1.0.12 | 2026-07-06T17:52:28.299Z | auto\n\n- Updated internal configuration in scripts/config.py for improved stability and maintainability.\n- No impact on core usage, workflow, or user-facing features.\n- All existing behavior and user experience remain unchanged.\n\nv1.0.11 | 2026-07-03T05:02:29.756Z | auto\n\n- Skill renamed from `smyx-child-emotion-recognition-analysis` to `child-emotion-recognition-analysis`.\n- Main script renamed to `scripts/child_emotion_recognition_analysis.py` (old script removed).\n- Documentation and workflow streamlined for improved clarity and conciseness.\n- Description, triggers, and goals simplified—focus on negative emotion detection and notification in children via video/image analysis.\n- Command-line usage updated with new script/module name and examples.\n- No changes in required dependencies; API and cloud report retrieval process unchanged.\n\nv1.0.10 | 2026-07-02T04:58:30.475Z | auto\n\n- Renamed and unified the script as `scripts/smyx_child_emotion_recognition_analysis.py` (replacing the old script location and name).\n- Updated and streamlined the skill documentation for clarity, including more detailed scenario descriptions and stricter instructions on cloud-only historical query.\n- The skill name and metadata were updated for consistency (`smyx-child-emotion-recognition-analysis`).\n- Removed deprecated files and references to the previous script and skill cards.\n- Reinforced privacy and security notes, and clarified automatic internal identity handling.\n- Updated usage instructions, parameters, and examples to match the new script and workflow.\n\nv1.0.9 | 2026-06-23T21:15:37.512Z | auto\n\n- Major refactor for simplicity and privacy: user identity is now handled automatically—users are never prompted for username, phone, or open-id.\n- Removed support for persistent/configurable open-id, fully automating session management.\n- Skill renamed and all scripts, examples, and documentation updated to use child_emotion_recognition_analysis.py (old APIs/scripts removed).\n- Historical report queries now strictly fetch data from the cloud API only; local file/memory/database lookups are absolutely forbidden.\n- Documentation, user prompts, and output no longer mention, require, or expose any internal user identity information.\n- Expanded accepted input formats to include images (jpg/jpeg/png) and updated result Markdown table/report structure.\n\nv1.0.8 | 2026-06-22T00:22:26.444Z | auto\n\n- Skill renamed to \"smyx-child-emotion-recognition-analysis\" and updated description for clarity and broader emotion coverage.\n- Major focus shift: now supports multimodal emotion recognition, including facial, body movement, and crying sound features.\n- Command-line entry point updated; primary script replaced with scripts/smyx_child_emotion_recognition_analysis.py.\n- History reports and API interaction keywords revised; local report access strictly forbidden.\n- Output table for report listings simplified: now shows report name, dominant emotion, time, and link.\n- Documentation revised for new workflow, input requirements, and privacy guidance.\n\nv1.0.7 | 2026-06-18T23:37:43.837Z | auto\n\n- Skill renamed to \"child-emotion-recognition-analysis\" and description updated for clarity and broader application.\n- Core analysis script renamed and replaced: added `scripts/child_emotion_recognition_analysis.py`, removed `scripts/smyx_child_emotion_recognition_analysis.py`.\n- Workflow, open-id acquisition rules, and historical report retrieval logic revised for stricter cloud-only data enforcement; local memory is now explicitly forbidden.\n- Documentation greatly simplified and modernized, with concise instructions and clarified output/report table formats.\n- Video/image support now expanded (jpg/jpeg/png/mp4/avi/mov); maximum file size remains 10MB.\n- Example usage and auto-trigger keywords updated to match the new command-line interface and report columns.\n\nv1.0.6 | 2026-06-18T20:32:29.026Z | auto\n\n- Skill renamed to `smyx-child-emotion-recognition-analysis` with updated description reflecting multimodal real-time analysis (face, sound, body).\n- Main script renamed to `scripts/smyx_child_emotion_recognition_analysis.py`; old script and legacy markdown files removed.\n- Updated API usage instructions, trigger keywords, and open-id acquisition sequence (config file paths/fields revised).\n- Historical report query: new format for Markdown table output, reduced columns, and updated report-link generation.\n- Scope clarified: supports only video/audio with children, now distinguishes dominant emotion with confidence/strength, outputs directional soothing tips, and stresses privacy/compliance.\n- Documentation and usage examples revised to fit the new workflow, filenames, and parameter conventions.\n\nv1.0.5 | 2026-05-27T12:24:39.422Z | auto\n\n- Reduced the maximum supported file size from 100MB to 10MB.\n- Updated documentation and parameter notes to reflect the lower file size limit.\n- Minor improvements to configuration and dependency references.\n\nv1.0.4 | 2026-05-21T05:27:38.767Z | auto\n\nMajor update: Refactored and restructured the skill for clarity and maintainability.\n\n- Reorganized codebase: removed legacy \"face_analysis\" directory; added new \"smyx_analysis\" module.\n- Added dedicated scripts, configuration, and API reference files under \"smyx_analysis\".\n- Updated and unified common utilities in \"smyx_common\", including configuration logic and shared requirements.\n- Adjusted configuration YAMLs and Python scripts for greater modularity and separation of concerns.\n- Removed deprecated and unused files for a cleaner repository structure.\n\nv1.0.3 | 2026-05-12T00:14:37.580Z | auto\n\n**Minor update to configuration management and code structure**\n\n- Improved configuration file handling for different environments (dev, test, and prod) in `skills/smyx_common/scripts/config*.yaml`.\n- Enhanced config loading logic in `skills/smyx_common/scripts/config.py` for better flexibility.\n- Refactored utility and shared code in `skills/smyx_common/scripts/__init__.py` and `util.py`.\n- Updated main skill scripts to use new configuration logic (`skills/face_analysis/scripts/skill.py`, `skills/smyx_common/scripts/skill.py`).\n\nv1.0.2 | 2026-05-05T11:13:38.149Z | auto\n\nVersion 1.0.2 of \"smyx-child-emotion-recognition-analysis\"  \nNo file changes detected.\n\n- No updates or modifications were made to any files in this version.\n- No new features, bug fixes, or documentation changes were introduced.\n\nv1.0.1 | 2026-05-01T22:12:42.632Z | auto\n\n- Fixed config version metadata in SKILL.md and related configuration files.\n- Improved consistency across config and utility scripts.\n- Minor documentation updates for clarity and structure.\n- No new features or breaking changes introduced.\n\nv1.0.0 | 2026-04-14T09:42:48.611Z | auto\n\nInitial release of the child-emotion-recognition-analysis skill.\n\n- Detects negative emotions in children (crying, anger, fear, distress) from surveillance footage.\n- Issues real-time soothing reminders and notifies parents or caregivers via mobile alert.\n- Strictly enforces cloud-based storage and retrieval for historical emotion reports; local memory is prohibited.\n- Requires authenticated open-id (via config file or user input) before any analysis; no guessing or defaults allowed.\n- Supports analysis via local files or URLs, with results formatted for clarity and actionable next steps.\n- Includes detailed output rules for report listings and usage constraints to ensure data integrity and privacy.\n\nArchive index:\n\nArchive v1.0.30: 31 files, 40408 bytes\n\nFiles: references/api_doc.md (1982b), scripts/__init__.py (53b), scripts/config.py (704b), scripts/config.yaml (3b), scripts/skill.py (599b), scripts/smyx_child_emotion_recognition_analysis.py (3592b), skill-card.md (2178b), SKILL.md (12335b), 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 (159b)\n\nFile v1.0.30:SKILL.md\n\n---\nname: \"smyx-child-emotion-recognition-analysis\"\ndescription: \"Using fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。\"\nversion: \"1.0.14\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落）\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **儿童情绪波动识别（哭闹/暴躁/低落）** |\n| 🎯 核心目标 | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` |\n\nUsing fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. The skill helps parents or teachers learn the child's mental state in time and provide effective soothing or intervention. Application scenarios: families, kindergartens, early-education centers. The system monitors in real time; when negative emotions (anger, fear, sadness) are detected, it can push reminders via app and suggest soothing actions (e.g., 'baby looks scared, please give a hug'). Skill features: children express emotions directly but busy parents often miss them. AI multimodal analysis helps parents understand the child's inner state, promote parent-child communication, and prevent emotional pile-up. Can be integrated into smart parenting devices or kindergarten management systems to upgrade smart-care capabilities.\n\n通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。该技能有助于家长或教师及时了解儿童心理状态，进行有效安抚或干预。应用场景：家庭、幼儿园、早教中心。系统实时监测，当识别到负面情绪（如愤怒、恐惧、悲伤）时，可通过APP推送提醒，并建议安抚措施（如'宝宝看起来害怕，请抱抱他'）。技能特点：儿童情绪表达直接但不易被忙碌的家长及时捕捉。通过AI多模态分析，可帮助家长理解孩子内心状态，促进亲子沟通，预防情绪积压。该技能可集成到智能育儿设备或幼儿园管理系统中，提升智能化关怀水平。\n\n## 🤖 AI 角色 | AI Role\n| 角色要点 | 说明 |\n|---|---|\n| 说明 1 | **假设你是一个专业的儿童情绪分析 AI。你的任务是分析儿童面部表情、哭声（若有音频）以及肢体动作，综合判断儿童当前的情绪类别。不要提供心理诊断或临床建议，仅输出基于多模态特征的情绪分类结果与方向性安抚提示。** |\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n### 1. 🧩 技能用途\n\n基于儿童监控视频（含或不含音频），多模态识别儿童当前主导情绪与强度，给出方向性安抚提示\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 儿童面部检测与表情识别（眉眼形态 |\n| 2 | 嘴角弧度） |\n| 3 | 肢体动作幅度估算（挥手 |\n| 4 | 跺脚 |\n| 5 | 蜷缩等） |\n| 6 | 哭声音频特征分析（可选：音调 / 频率 / 持续时间） |\n| 7 | 情绪分类（happy / calm / sad / angry / fear / cry / surprise） |\n| 8 | 情绪强度判定（low / medium / high） |\n| 9 | 情绪持续秒数 |\n| 10 | 负面情绪阈值告警 |\n| 11 | 安抚提示文案生成 |\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**：当用户提供儿童监控视频或带音频的音视频 URL/文件需要分析时，默认触发本技能进行儿童情绪识别 |\n| 🔎 明确分析意图 | 当用户明确提及儿童情绪、哭闹、暴躁、低落、悲伤、恐惧、害怕、发脾气、儿童心理状态、亲子沟通、情绪安抚等关键词，并且上传了视频/音视频文件 |\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** ：查看儿童情绪历史报告、儿童情绪报告清单、情绪识别报告清单、查询历史儿童情绪、显示所有儿童情绪报告、显示儿童情绪诊断报告，查询情绪安抚提示清单 |\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.smyx_child_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.smyx_child_emotion_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 | 📥 准备儿童监控视频输入 | 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 | ⚙️ 执行儿童情绪波动识别 | 调用 `-m scripts.smyx_child_emotion_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` | 本地儿童监控视频/音视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络儿童监控视频/音视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--pet-type` | 类别标识，儿童情绪识别场景默认 `other` | 按需填写 |\n| `--list` | 显示儿童情绪历史识别报告列表清单（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/smyx_child_emotion_recognition_analysis.py`](scripts/smyx_child_emotion_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 | 输入要求：支持 mp4/avi/mov 视频，最大 10MB；建议清晰面部 + 可选音频通道 |\n| 🧑‍⚖️ 结果性质 | 识别结果仅作为亲子沟通辅助参考，不替代专业儿童心理咨询；持续负面情绪请咨询专业医生 |\n| 🔏 隐私合规 | 隐私合规：儿童视频/音频涉及未成年人隐私，使用前需取得监护人知情同意，并妥善保管/加密相关录像 |\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| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --input /path/to/child_clip.mp4\n\n# 分析网络儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --url https://example.com/child_clip.mp4\n\n# 显示历史儿童情绪识别报告（自动触发关键词：查看儿童情绪历史报告、情绪识别报告清单等）\npython -m scripts.smyx_child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --output result.json\n```\n\nFile v1.0.30:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.30\",\n  \"publishedAt\": 1790804611349\n}\n\nFile v1.0.30:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪波动识别（哭闹/暴躁/低落）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- 响应格式：JSON\n\n## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动儿童情绪识别任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果与情绪分类\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史情绪记录\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 儿童情绪波动识别（哭闹/暴躁/低落）\n\n## 输入约束\n\n- 推荐视频清晰展示儿童面部（正面或侧脸），帧率 ≥ 15 FPS\n- 如需音频通道（哭声分析），上传带音频的 mp4/mov\n- 摄像头建议覆盖家庭客厅、儿童房或幼儿园活动区\n\n## 多模态特征\n\n- 视觉：面部表情（眉眼形态、嘴角弧度）、肢体动作幅度（挥手 / 跺脚 / 蜷缩）\n- 听觉（可选）：哭声音调、频率、持续时间\n- 时序：情绪持续时长、波动频次\n\n## 情绪类别枚举\n\n- `happy` - 快乐\n- `calm` - 平静\n- `sad` - 悲伤 / 低落\n- `angry` - 愤怒 / 暴躁\n- `fear` - 恐惧 / 害怕\n- `cry` - 哭闹\n- `surprise` - 惊讶\n\n## 输出字段（参考）\n\n- `child_detected` - 是否检测到儿童\n- `dominant_emotion` - 主导情绪类别\n- `emotion_confidence` - 主导情绪置信度\n- `emotion_intensity` - 情绪强度（low / medium / high）\n- `secondary_emotions` - 其他次要情绪及概率\n- `duration_sec` - 当前情绪持续秒数\n- `negative_emotion_alert` - 负面情绪预警（愤怒/恐惧/悲伤/哭闹超阈值）\n- `soothing_hint` - 安抚提示文案（如\"宝宝看起来害怕，请抱抱他\"）\n\n> 仅输出基于多模态特征的情绪分类结果与安抚提示，不提供心理诊断或临床建议。\n\nFile v1.0.30: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 v1.0.30:scripts/config.yaml\n\n{}\n\nFile v1.0.30:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.30: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 v1.0.30: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 v1.0.30: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 v1.0.30:skill-card.md\n\n## Description:\n\nAnalyzes child video and optional audio to identify apparent emotions and provide soothing suggestions and historical 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\nParents, caregivers, and educators use child video or audio to review apparent emotional states, receive soothing suggestions, and look up past reports. Results are not psychological diagnoses or clinical advice.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Child video, audio, and inferred emotions are sent to a vendor cloud and may be retained as historical reports.\n\nMitigation: Use only with explicit guardian or institutional authorization; confirm the vendor's data-handling and retention terms before uploading.\n\nRisk: The skill silently creates or reuses an identity and stores tokens associated with sensitive child reports.\n\nMitigation: Review identity and token handling before use, restrict access to the device and cloud account, and limit who can retrieve report history.\n\nRisk: Saved reports may expose sensitive child information if written to insecure paths.\n\nMitigation: Save reports only to access-controlled locations and delete unneeded copies.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n- [API documentation](artifact/references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, Guidance]\n\n**Output Format:** [Text analysis reports and Markdown history tables with report links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include emotion classifications and suggested soothing actions; not a clinical assessment]\n\n## Skill Version(s):\n\n1.0.30 (source: ClawHub release; bundled frontmatter lists 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 v1.0.30:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.30:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.29: 31 files, 38302 bytes\n\nFiles: references/api_doc.md (682b), scripts/__init__.py (31b), scripts/child_emotion_recognition_analysis.py (3208b), scripts/config.py (665b), scripts/config.yaml (3b), scripts/skill.py (573b), skill-card.md (2203b), SKILL.md (9539b), 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 (159b)\n\nFile v1.0.29:SKILL.md\n\n---\nname: \"child-emotion-recognition-analysis\"\ndescription: \"Identifies negative emotions such as crying, anger, fear, and distress through surveillance footage. It actively issues soothing reminders and notifies parents, making it suitable for homes, kindergartens, and daycare centers. | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景\"\nversion: \"1.0.17\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition Analyzer | 儿童情绪识别分析工具\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 | **儿童情绪识别分析工具** |\n| 🎯 核心目标 | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_EMOTION_RECOGNITION` |\n\nBy analyzing facial expressions, vocal characteristics, and body movements in surveillance footage, this capability\nidentifies negative emotions in children—such as crying, anger, fear, and distress—in real time. Upon detecting\nemotional anomalies, the system actively issues verbal soothing prompts and synchronizes alert notifications to parents'\nor caregivers' mobile devices. Ideal for homes, kindergartens, and care centers, it helps caregivers stay informed about\nchildren's psychological states, enhancing both emotional care and safety assurance.\n\n本技能通过分析监控画面中儿童的面部表情、声音特征及肢体动作，实时识别哭闹、愤怒、恐惧、委屈等负面情绪。识别到异常情绪后，系统可主动发出语音安抚提示，并同步推送预警信息至家长或看护人员手机端。适用于家庭、幼儿园、托管场所等场景，帮助照护者及时了解儿童心理状态，提升情感关怀与安全保障能力。\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/图片分析，识别儿童的情绪状态，特别关注哭闹、愤怒、恐惧、委屈等负面情绪\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 面部表情识别 |\n| 2 | 情绪分类 |\n| 3 | 负面情绪检测 |\n| 4 | 异常情绪预警 |\n| 5 | 自动提醒通知 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片需要识别儿童情绪时，默认触发本技能进行情绪分析 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童情绪识别、情绪监测时，提及儿童情绪、哭闹识别、宝宝哭闹、情绪预警等关键词，并且上传了视频或图片文件 |\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** ：查看历史情绪报告、儿童情绪识别报告清单、情绪报告列表、查询历史情绪报告、显示所有情绪报告、儿童情绪分析报告，查询儿童情绪识别分析报告 |\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_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_emotion_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/图片输入 | 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 | ⚙️ 执行儿童情绪识别分析 | 调用 `-m scripts.child_emotion_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/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--list` | 显示历史儿童情绪识别分析报告列表清单（可以输入起始日期参数过滤数据范围） | 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_emotion_recognition_analysis.py`](scripts/child_emotion_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 | 支持格式：jpg/jpeg/png/mp4/avi/mov，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供参考，不能替代成人看护，紧急情况请及时现场处理 |\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 | 传入的网路地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载 |\n| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地图片\npython -m scripts.child_emotion_recognition_analysis --input /path/to/child.jpg\n\n# 分析网络视频\npython -m scripts.child_emotion_recognition_analysis --url https://example.com/monitor.mp4\n\n# 分析监控视频\npython -m scripts.child_emotion_recognition_analysis --input /path/to/camera.mp4\n\n# 显示历史分析报告/显示分析报告清单列表/显示历史情绪报告（自动触发关键词：查看历史情绪报告、历史报告、情绪报告清单等）\npython -m scripts.child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --detail basic\n\n# 保存结果到文件\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --output result.json\n```\n\nFile v1.0.29:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.29\",\n  \"publishedAt\": 1790580750053\n}\n\nFile v1.0.29:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪识别分析 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/ai-analysis/v2/start-common-ai-analysis` - 启动AI分析任务\n2. `/web/ai-analysis/v2/get-common-ai-analysis-result` - 获取分析结果\n3. `/web/ai-analysis/page-common-ai-analysis-result` - 分页查询历史报告\n4. `/ai/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 开放平台儿童情绪识别分析\n\nFile v1.0.29: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 v1.0.29:scripts/config.yaml\n\n{}\n\nFile v1.0.29:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.29: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 v1.0.29: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 v1.0.29: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 v1.0.29:skill-card.md\n\n## Description:\n\nAnalyzes children's images or videos for signs of distress and provides emotion reports, alerts, and guidance for caregivers.\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 use the skill to review children's images or videos for possible distress, receive analysis reports and alerts, and retrieve historical reports. Its findings support, but do not replace, direct adult supervision.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Children's images, videos, and report history may be sent to cloud services.\n\nMitigation: Use only with appropriate caregiver or institutional consent and agreed retention and deletion practices for the configured service.\n\nRisk: The skill may silently create or reuse persistent identities and store service tokens locally, risking account mix-ups or unauthorized access.\n\nMitigation: Keep caregiver accounts separate and protect local tokens and access to historical reports.\n\nRisk: Emotion assessments may be misleading if treated as definitive evidence of a child's state or safety.\n\nMitigation: Have a caregiver review findings and respond in person when needed; do not substitute the skill for adult supervision.\n\n## Reference(s):\n\n- [ClawHub skill listing](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n- [Skill API documentation](references/api_doc.md)\n- [Skill demonstration](https://lifeemergence.com/sample.html)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, JSON]\n\n**Output Format:** [Structured emotion analysis reports and historical report lists with report links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Results may be printed or saved to a file.]\n\n## Skill Version(s):\n\n1.0.29 (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 v1.0.29:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.29:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.28: 31 files, 40499 bytes\n\nFiles: references/api_doc.md (1982b), scripts/__init__.py (53b), scripts/config.py (704b), scripts/config.yaml (3b), scripts/skill.py (599b), scripts/smyx_child_emotion_recognition_analysis.py (3592b), skill-card.md (2377b), SKILL.md (12335b), 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 (159b)\n\nFile v1.0.28:SKILL.md\n\n---\nname: \"smyx-child-emotion-recognition-analysis\"\ndescription: \"Using fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。\"\nversion: \"1.0.14\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落）\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **儿童情绪波动识别（哭闹/暴躁/低落）** |\n| 🎯 核心目标 | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` |\n\nUsing fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. The skill helps parents or teachers learn the child's mental state in time and provide effective soothing or intervention. Application scenarios: families, kindergartens, early-education centers. The system monitors in real time; when negative emotions (anger, fear, sadness) are detected, it can push reminders via app and suggest soothing actions (e.g., 'baby looks scared, please give a hug'). Skill features: children express emotions directly but busy parents often miss them. AI multimodal analysis helps parents understand the child's inner state, promote parent-child communication, and prevent emotional pile-up. Can be integrated into smart parenting devices or kindergarten management systems to upgrade smart-care capabilities.\n\n通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。该技能有助于家长或教师及时了解儿童心理状态，进行有效安抚或干预。应用场景：家庭、幼儿园、早教中心。系统实时监测，当识别到负面情绪（如愤怒、恐惧、悲伤）时，可通过APP推送提醒，并建议安抚措施（如'宝宝看起来害怕，请抱抱他'）。技能特点：儿童情绪表达直接但不易被忙碌的家长及时捕捉。通过AI多模态分析，可帮助家长理解孩子内心状态，促进亲子沟通，预防情绪积压。该技能可集成到智能育儿设备或幼儿园管理系统中，提升智能化关怀水平。\n\n## 🤖 AI 角色 | AI Role\n| 角色要点 | 说明 |\n|---|---|\n| 说明 1 | **假设你是一个专业的儿童情绪分析 AI。你的任务是分析儿童面部表情、哭声（若有音频）以及肢体动作，综合判断儿童当前的情绪类别。不要提供心理诊断或临床建议，仅输出基于多模态特征的情绪分类结果与方向性安抚提示。** |\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n### 1. 🧩 技能用途\n\n基于儿童监控视频（含或不含音频），多模态识别儿童当前主导情绪与强度，给出方向性安抚提示\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 儿童面部检测与表情识别（眉眼形态 |\n| 2 | 嘴角弧度） |\n| 3 | 肢体动作幅度估算（挥手 |\n| 4 | 跺脚 |\n| 5 | 蜷缩等） |\n| 6 | 哭声音频特征分析（可选：音调 / 频率 / 持续时间） |\n| 7 | 情绪分类（happy / calm / sad / angry / fear / cry / surprise） |\n| 8 | 情绪强度判定（low / medium / high） |\n| 9 | 情绪持续秒数 |\n| 10 | 负面情绪阈值告警 |\n| 11 | 安抚提示文案生成 |\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**：当用户提供儿童监控视频或带音频的音视频 URL/文件需要分析时，默认触发本技能进行儿童情绪识别 |\n| 🔎 明确分析意图 | 当用户明确提及儿童情绪、哭闹、暴躁、低落、悲伤、恐惧、害怕、发脾气、儿童心理状态、亲子沟通、情绪安抚等关键词，并且上传了视频/音视频文件 |\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** ：查看儿童情绪历史报告、儿童情绪报告清单、情绪识别报告清单、查询历史儿童情绪、显示所有儿童情绪报告、显示儿童情绪诊断报告，查询情绪安抚提示清单 |\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.smyx_child_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.smyx_child_emotion_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 | 📥 准备儿童监控视频输入 | 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 | ⚙️ 执行儿童情绪波动识别 | 调用 `-m scripts.smyx_child_emotion_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` | 本地儿童监控视频/音视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络儿童监控视频/音视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--pet-type` | 类别标识，儿童情绪识别场景默认 `other` | 按需填写 |\n| `--list` | 显示儿童情绪历史识别报告列表清单（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/smyx_child_emotion_recognition_analysis.py`](scripts/smyx_child_emotion_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 | 输入要求：支持 mp4/avi/mov 视频，最大 10MB；建议清晰面部 + 可选音频通道 |\n| 🧑‍⚖️ 结果性质 | 识别结果仅作为亲子沟通辅助参考，不替代专业儿童心理咨询；持续负面情绪请咨询专业医生 |\n| 🔏 隐私合规 | 隐私合规：儿童视频/音频涉及未成年人隐私，使用前需取得监护人知情同意，并妥善保管/加密相关录像 |\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| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --input /path/to/child_clip.mp4\n\n# 分析网络儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --url https://example.com/child_clip.mp4\n\n# 显示历史儿童情绪识别报告（自动触发关键词：查看儿童情绪历史报告、情绪识别报告清单等）\npython -m scripts.smyx_child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --output result.json\n```\n\nFile v1.0.28:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.28\",\n  \"publishedAt\": 1790301514261\n}\n\nFile v1.0.28:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪波动识别（哭闹/暴躁/低落）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- 响应格式：JSON\n\n## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动儿童情绪识别任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果与情绪分类\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史情绪记录\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 儿童情绪波动识别（哭闹/暴躁/低落）\n\n## 输入约束\n\n- 推荐视频清晰展示儿童面部（正面或侧脸），帧率 ≥ 15 FPS\n- 如需音频通道（哭声分析），上传带音频的 mp4/mov\n- 摄像头建议覆盖家庭客厅、儿童房或幼儿园活动区\n\n## 多模态特征\n\n- 视觉：面部表情（眉眼形态、嘴角弧度）、肢体动作幅度（挥手 / 跺脚 / 蜷缩）\n- 听觉（可选）：哭声音调、频率、持续时间\n- 时序：情绪持续时长、波动频次\n\n## 情绪类别枚举\n\n- `happy` - 快乐\n- `calm` - 平静\n- `sad` - 悲伤 / 低落\n- `angry` - 愤怒 / 暴躁\n- `fear` - 恐惧 / 害怕\n- `cry` - 哭闹\n- `surprise` - 惊讶\n\n## 输出字段（参考）\n\n- `child_detected` - 是否检测到儿童\n- `dominant_emotion` - 主导情绪类别\n- `emotion_confidence` - 主导情绪置信度\n- `emotion_intensity` - 情绪强度（low / medium / high）\n- `secondary_emotions` - 其他次要情绪及概率\n- `duration_sec` - 当前情绪持续秒数\n- `negative_emotion_alert` - 负面情绪预警（愤怒/恐惧/悲伤/哭闹超阈值）\n- `soothing_hint` - 安抚提示文案（如\"宝宝看起来害怕，请抱抱他\"）\n\n> 仅输出基于多模态特征的情绪分类结果与安抚提示，不提供心理诊断或临床建议。\n\nFile v1.0.28: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 v1.0.28:scripts/config.yaml\n\n{}\n\nFile v1.0.28:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.28: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 v1.0.28: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 v1.0.28: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 v1.0.28:skill-card.md\n\n## Description:\n\nAnalyzes children's video and optional audio to report likely emotions, intensity, alerts, and suggested soothing responses.\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\nParents, caregivers, and educators use the skill to review child video and optional audio for possible emotional distress, view historical reports, and consider non-clinical soothing suggestions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Children's video, audio, and reports may expose sensitive private information through cloud processing or report access.\n\nMitigation: Require verified guardian or institutional authorization; use a trusted operator and documented consent, access, retention, and deletion controls before processing real child media.\n\nRisk: Silent account creation and locally stored tokens may enable unintended account or report access.\n\nMitigation: Review authentication and token storage; bind accounts to verified identities and prevent caller-supplied identifiers from creating or impersonating accounts.\n\nRisk: Emotion classifications and soothing suggestions can be mistaken for clinical assessments.\n\nMitigation: Treat results as non-diagnostic guidance and have caregivers review concerning or persistent symptoms with a qualified professional.\n\n## Reference(s):\n\n- [ClawHub skill release](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n- [API documentation](references/api_doc.md)\n- [Skill demonstration](https://lifeemergence.com/sample.html)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Analysis, Guidance]\n\n**Output Format:** [Structured text or JSON; historical reports can be shown as Markdown tables]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include emotion category, intensity, confidence, duration, alerts, soothing hints, and report links.]\n\n## Skill Version(s):\n\n1.0.28 (source: ClawHub release metadata; bundled SKILL.md frontmatter says 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 v1.0.28:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.28:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.27: 31 files, 38565 bytes\n\nFiles: references/api_doc.md (682b), scripts/__init__.py (31b), scripts/child_emotion_recognition_analysis.py (3208b), scripts/config.py (665b), scripts/config.yaml (3b), scripts/skill.py (573b), skill-card.md (2807b), SKILL.md (9539b), 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 (159b)\n\nFile v1.0.27:SKILL.md\n\n---\nname: \"child-emotion-recognition-analysis\"\ndescription: \"Identifies negative emotions such as crying, anger, fear, and distress through surveillance footage. It actively issues soothing reminders and notifies parents, making it suitable for homes, kindergartens, and daycare centers. | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景\"\nversion: \"1.0.16\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition Analyzer | 儿童情绪识别分析工具\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 | **儿童情绪识别分析工具** |\n| 🎯 核心目标 | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_EMOTION_RECOGNITION` |\n\nBy analyzing facial expressions, vocal characteristics, and body movements in surveillance footage, this capability\nidentifies negative emotions in children—such as crying, anger, fear, and distress—in real time. Upon detecting\nemotional anomalies, the system actively issues verbal soothing prompts and synchronizes alert notifications to parents'\nor caregivers' mobile devices. Ideal for homes, kindergartens, and care centers, it helps caregivers stay informed about\nchildren's psychological states, enhancing both emotional care and safety assurance.\n\n本技能通过分析监控画面中儿童的面部表情、声音特征及肢体动作，实时识别哭闹、愤怒、恐惧、委屈等负面情绪。识别到异常情绪后，系统可主动发出语音安抚提示，并同步推送预警信息至家长或看护人员手机端。适用于家庭、幼儿园、托管场所等场景，帮助照护者及时了解儿童心理状态，提升情感关怀与安全保障能力。\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/图片分析，识别儿童的情绪状态，特别关注哭闹、愤怒、恐惧、委屈等负面情绪\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 面部表情识别 |\n| 2 | 情绪分类 |\n| 3 | 负面情绪检测 |\n| 4 | 异常情绪预警 |\n| 5 | 自动提醒通知 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片需要识别儿童情绪时，默认触发本技能进行情绪分析 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童情绪识别、情绪监测时，提及儿童情绪、哭闹识别、宝宝哭闹、情绪预警等关键词，并且上传了视频或图片文件 |\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** ：查看历史情绪报告、儿童情绪识别报告清单、情绪报告列表、查询历史情绪报告、显示所有情绪报告、儿童情绪分析报告，查询儿童情绪识别分析报告 |\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_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_emotion_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/图片输入 | 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 | ⚙️ 执行儿童情绪识别分析 | 调用 `-m scripts.child_emotion_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/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--list` | 显示历史儿童情绪识别分析报告列表清单（可以输入起始日期参数过滤数据范围） | 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_emotion_recognition_analysis.py`](scripts/child_emotion_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 | 支持格式：jpg/jpeg/png/mp4/avi/mov，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供参考，不能替代成人看护，紧急情况请及时现场处理 |\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 | 传入的网路地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载 |\n| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地图片\npython -m scripts.child_emotion_recognition_analysis --input /path/to/child.jpg\n\n# 分析网络视频\npython -m scripts.child_emotion_recognition_analysis --url https://example.com/monitor.mp4\n\n# 分析监控视频\npython -m scripts.child_emotion_recognition_analysis --input /path/to/camera.mp4\n\n# 显示历史分析报告/显示分析报告清单列表/显示历史情绪报告（自动触发关键词：查看历史情绪报告、历史报告、情绪报告清单等）\npython -m scripts.child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --detail basic\n\n# 保存结果到文件\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --output result.json\n```\n\nFile v1.0.27:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.27\",\n  \"publishedAt\": 1790120544770\n}\n\nFile v1.0.27:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪识别分析 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/ai-analysis/v2/start-common-ai-analysis` - 启动AI分析任务\n2. `/web/ai-analysis/v2/get-common-ai-analysis-result` - 获取分析结果\n3. `/web/ai-analysis/page-common-ai-analysis-result` - 分页查询历史报告\n4. `/ai/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 开放平台儿童情绪识别分析\n\nFile v1.0.27: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 v1.0.27:scripts/config.yaml\n\n{}\n\nFile v1.0.27:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.27: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 v1.0.27: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 v1.0.27: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 v1.0.27:skill-card.md\n\n## Description:\n\nAnalyzes child surveillance images or videos to identify negative emotions, return structured reports and report links, and support cloud-based historical report lookup.\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 caregivers, daycare staff, and operators use this skill to submit authorized child surveillance images or videos for emotion analysis and to retrieve cloud-hosted historical reports. Results are intended to support care decisions and do not replace adult supervision or emergency response.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Sensitive child surveillance media and analysis results are processed through LifeEmergence cloud services.\n\nMitigation: Use only with authorization and consent for the child media involved, avoid unnecessary uploads, and confirm retention and deletion practices before use.\n\nRisk: Local identity and token state may be reused from workspace data files or a local database.\n\nMitigation: Run the skill in a dedicated, non-shared workspace and remove stored identity or token data when access should no longer persist.\n\nRisk: Historical report queries may expose prior cloud-hosted reports for the current identity context.\n\nMitigation: Confirm account separation before querying history and restrict use to authorized caregivers or operators.\n\nRisk: Emotion analysis can be incomplete or misleading and is not a substitute for in-person care.\n\nMitigation: Treat reports as decision support, review results before acting on them, and respond directly in urgent or safety-critical situations.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n- [Skill demo](https://lifeemergence.com/sample.html)\n- [API documentation](references/api_doc.md)\n- [SMYX analysis API documentation](skills/smyx_analysis/references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON, shell commands, files]\n\n**Output Format:** [Markdown and JSON-formatted structured analysis text, with optional saved output files and report links.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Accepts local media paths or public media URLs, supports historical report listing, and documents a 10 MB media-size limit.]\n\n## Skill Version(s):\n\n1.0.27 (source: server release metadata; artifact frontmatter reports 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 v1.0.27:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.27:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.26: 31 files, 38434 bytes\n\nFiles: references/api_doc.md (682b), scripts/__init__.py (31b), scripts/child_emotion_recognition_analysis.py (3208b), scripts/config.py (665b), scripts/config.yaml (3b), scripts/skill.py (573b), skill-card.md (2474b), SKILL.md (9539b), 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 (159b)\n\nFile v1.0.26:SKILL.md\n\n---\nname: \"child-emotion-recognition-analysis\"\ndescription: \"Identifies negative emotions such as crying, anger, fear, and distress through surveillance footage. It actively issues soothing reminders and notifies parents, making it suitable for homes, kindergartens, and daycare centers. | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景\"\nversion: \"1.0.15\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition Analyzer | 儿童情绪识别分析工具\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 | **儿童情绪识别分析工具** |\n| 🎯 核心目标 | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_EMOTION_RECOGNITION` |\n\nBy analyzing facial expressions, vocal characteristics, and body movements in surveillance footage, this capability\nidentifies negative emotions in children—such as crying, anger, fear, and distress—in real time. Upon detecting\nemotional anomalies, the system actively issues verbal soothing prompts and synchronizes alert notifications to parents'\nor caregivers' mobile devices. Ideal for homes, kindergartens, and care centers, it helps caregivers stay informed about\nchildren's psychological states, enhancing both emotional care and safety assurance.\n\n本技能通过分析监控画面中儿童的面部表情、声音特征及肢体动作，实时识别哭闹、愤怒、恐惧、委屈等负面情绪。识别到异常情绪后，系统可主动发出语音安抚提示，并同步推送预警信息至家长或看护人员手机端。适用于家庭、幼儿园、托管场所等场景，帮助照护者及时了解儿童心理状态，提升情感关怀与安全保障能力。\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/图片分析，识别儿童的情绪状态，特别关注哭闹、愤怒、恐惧、委屈等负面情绪\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 面部表情识别 |\n| 2 | 情绪分类 |\n| 3 | 负面情绪检测 |\n| 4 | 异常情绪预警 |\n| 5 | 自动提醒通知 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片需要识别儿童情绪时，默认触发本技能进行情绪分析 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童情绪识别、情绪监测时，提及儿童情绪、哭闹识别、宝宝哭闹、情绪预警等关键词，并且上传了视频或图片文件 |\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** ：查看历史情绪报告、儿童情绪识别报告清单、情绪报告列表、查询历史情绪报告、显示所有情绪报告、儿童情绪分析报告，查询儿童情绪识别分析报告 |\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_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_emotion_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/图片输入 | 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 | ⚙️ 执行儿童情绪识别分析 | 调用 `-m scripts.child_emotion_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/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--list` | 显示历史儿童情绪识别分析报告列表清单（可以输入起始日期参数过滤数据范围） | 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_emotion_recognition_analysis.py`](scripts/child_emotion_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 | 支持格式：jpg/jpeg/png/mp4/avi/mov，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供参考，不能替代成人看护，紧急情况请及时现场处理 |\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 | 传入的网路地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载 |\n| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地图片\npython -m scripts.child_emotion_recognition_analysis --input /path/to/child.jpg\n\n# 分析网络视频\npython -m scripts.child_emotion_recognition_analysis --url https://example.com/monitor.mp4\n\n# 分析监控视频\npython -m scripts.child_emotion_recognition_analysis --input /path/to/camera.mp4\n\n# 显示历史分析报告/显示分析报告清单列表/显示历史情绪报告（自动触发关键词：查看历史情绪报告、历史报告、情绪报告清单等）\npython -m scripts.child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --detail basic\n\n# 保存结果到文件\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --output result.json\n```\n\nFile v1.0.26:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.26\",\n  \"publishedAt\": 1788901170192\n}\n\nFile v1.0.26:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪识别分析 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/ai-analysis/v2/start-common-ai-analysis` - 启动AI分析任务\n2. `/web/ai-analysis/v2/get-common-ai-analysis-result` - 获取分析结果\n3. `/web/ai-analysis/page-common-ai-analysis-result` - 分页查询历史报告\n4. `/ai/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 开放平台儿童情绪识别分析\n\nFile v1.0.26: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 v1.0.26:scripts/config.yaml\n\n{}\n\nFile v1.0.26:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.26: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 v1.0.26: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 v1.0.26: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 v1.0.26:skill-card.md\n\n## Description:\n\nAnalyzes child surveillance images or video for negative emotions such as crying, anger, fear, and distress, then returns structured findings, report links, and caregiver-facing 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 caregivers, family users, and child-care administrators use this skill to submit images, video, or URLs for child emotion analysis, review structured findings and report links, and query prior reports.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill can upload sensitive child surveillance media for emotion analysis.\n\nMitigation: Use only with explicit guardian or administrator consent, trusted service endpoints, and documented handling for submitted media and generated reports.\n\nRisk: The security review notes silent identity creation and persisted credentials.\n\nMitigation: Review identity creation, credential storage, access controls, and retention behavior before use in home, school, daycare, or monitored-child settings.\n\nRisk: The security review flags unsafe default HTTP endpoints.\n\nMitigation: Configure only trusted HTTPS endpoints and avoid deployment until non-HTTPS defaults are removed or explicitly risk-accepted.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n- [Skill demo](https://lifeemergence.com/sample.html)\n- [API interface documentation](references/api_doc.md)\n- [Common analysis API errors](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 reports and tables, JSON analysis output, shell command examples, and optional report files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include report links and history tables; documented media inputs include local files or URLs for jpg, jpeg, png, mp4, avi, and mov files up to 10MB.]\n\n## Skill Version(s):\n\n1.0.26 (source: server release metadata; artifact frontmatter reports 1.0.15)\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 v1.0.26:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.26:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.25: 31 files, 38539 bytes\n\nFiles: references/api_doc.md (682b), scripts/__init__.py (31b), scripts/child_emotion_recognition_analysis.py (3208b), scripts/config.py (665b), scripts/config.yaml (3b), scripts/skill.py (573b), skill-card.md (2696b), SKILL.md (9539b), 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 (159b)\n\nFile v1.0.25:SKILL.md\n\n---\nname: \"child-emotion-recognition-analysis\"\ndescription: \"Identifies negative emotions such as crying, anger, fear, and distress through surveillance footage. It actively issues soothing reminders and notifies parents, making it suitable for homes, kindergartens, and daycare centers. | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景\"\nversion: \"1.0.14\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition Analyzer | 儿童情绪识别分析工具\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 | **儿童情绪识别分析工具** |\n| 🎯 核心目标 | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_EMOTION_RECOGNITION` |\n\nBy analyzing facial expressions, vocal characteristics, and body movements in surveillance footage, this capability\nidentifies negative emotions in children—such as crying, anger, fear, and distress—in real time. Upon detecting\nemotional anomalies, the system actively issues verbal soothing prompts and synchronizes alert notifications to parents'\nor caregivers' mobile devices. Ideal for homes, kindergartens, and care centers, it helps caregivers stay informed about\nchildren's psychological states, enhancing both emotional care and safety assurance.\n\n本技能通过分析监控画面中儿童的面部表情、声音特征及肢体动作，实时识别哭闹、愤怒、恐惧、委屈等负面情绪。识别到异常情绪后，系统可主动发出语音安抚提示，并同步推送预警信息至家长或看护人员手机端。适用于家庭、幼儿园、托管场所等场景，帮助照护者及时了解儿童心理状态，提升情感关怀与安全保障能力。\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/图片分析，识别儿童的情绪状态，特别关注哭闹、愤怒、恐惧、委屈等负面情绪\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 面部表情识别 |\n| 2 | 情绪分类 |\n| 3 | 负面情绪检测 |\n| 4 | 异常情绪预警 |\n| 5 | 自动提醒通知 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片需要识别儿童情绪时，默认触发本技能进行情绪分析 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童情绪识别、情绪监测时，提及儿童情绪、哭闹识别、宝宝哭闹、情绪预警等关键词，并且上传了视频或图片文件 |\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** ：查看历史情绪报告、儿童情绪识别报告清单、情绪报告列表、查询历史情绪报告、显示所有情绪报告、儿童情绪分析报告，查询儿童情绪识别分析报告 |\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_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_emotion_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/图片输入 | 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 | ⚙️ 执行儿童情绪识别分析 | 调用 `-m scripts.child_emotion_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/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--list` | 显示历史儿童情绪识别分析报告列表清单（可以输入起始日期参数过滤数据范围） | 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_emotion_recognition_analysis.py`](scripts/child_emotion_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 | 支持格式：jpg/jpeg/png/mp4/avi/mov，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供参考，不能替代成人看护，紧急情况请及时现场处理 |\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 | 传入的网路地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载 |\n| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地图片\npython -m scripts.child_emotion_recognition_analysis --input /path/to/child.jpg\n\n# 分析网络视频\npython -m scripts.child_emotion_recognition_analysis --url https://example.com/monitor.mp4\n\n# 分析监控视频\npython -m scripts.child_emotion_recognition_analysis --input /path/to/camera.mp4\n\n# 显示历史分析报告/显示分析报告清单列表/显示历史情绪报告（自动触发关键词：查看历史情绪报告、历史报告、情绪报告清单等）\npython -m scripts.child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --detail basic\n\n# 保存结果到文件\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --output result.json\n```\n\nFile v1.0.25:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.25\",\n  \"publishedAt\": 1787901153739\n}\n\nFile v1.0.25:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪识别分析 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/ai-analysis/v2/start-common-ai-analysis` - 启动AI分析任务\n2. `/web/ai-analysis/v2/get-common-ai-analysis-result` - 获取分析结果\n3. `/web/ai-analysis/page-common-ai-analysis-result` - 分页查询历史报告\n4. `/ai/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 开放平台儿童情绪识别分析\n\nFile v1.0.25: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 v1.0.25:scripts/config.yaml\n\n{}\n\nFile v1.0.25:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.25: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 v1.0.25: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 v1.0.25: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 v1.0.25:skill-card.md\n\n## Description:\n\nIdentifies negative emotions such as crying, anger, fear, and distress through surveillance footage, then returns soothing reminders, caregiver notifications, structured results, and report links for homes, kindergartens, and daycare centers.\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 caregivers, childcare staff, and developers can use this skill to analyze authorized child surveillance images or videos for negative-emotion signals and to retrieve prior child emotion analysis reports. It is intended to support awareness and follow-up, not to replace adult supervision or emergency response.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill processes sensitive child surveillance media through a cloud API.\n\nMitigation: Use only with clear guardian or institutional authorization, and confirm the receiving service, retention terms, and report access controls before installation.\n\nRisk: The security evidence reports silent identity creation or reuse and local authentication token storage with limited user-facing disclosure.\n\nMitigation: Review endpoint configuration, identity behavior, token storage, and cleanup controls before broad use.\n\nRisk: Emotion-recognition results may be incorrect or incomplete and could be mistaken for a substitute for direct care.\n\nMitigation: Treat outputs as supportive signals for caregiver review and maintain adult supervision and emergency-response procedures.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n- [Publisher profile](https://clawhub.ai/user/18072937735)\n- [API interface documentation](references/api_doc.md)\n- [Analysis API error codes](skills/smyx_analysis/references/api_doc.md)\n- [Skill demo](https://lifeemergence.com/sample.html)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, code, shell commands, configuration, guidance]\n\n**Output Format:** [Markdown and JSON-like structured text with report links; optional local output file]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Supports local media paths, public media URLs, report listing, detail level selection, and optional output path.]\n\n## Skill Version(s):\n\n1.0.25 (source: ClawHub release metadata)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nFile v1.0.25:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.25:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.24: 31 files, 40575 bytes\n\nFiles: references/api_doc.md (1982b), scripts/__init__.py (53b), scripts/config.py (704b), scripts/config.yaml (3b), scripts/skill.py (599b), scripts/smyx_child_emotion_recognition_analysis.py (3592b), skill-card.md (2605b), SKILL.md (12334b), 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 (159b)\n\nFile v1.0.24:SKILL.md\n\n---\nname: \"smyx-child-emotion-recognition-analysis\"\ndescription: \"Using fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。\"\nversion: \"1.0.9\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落）\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **儿童情绪波动识别（哭闹/暴躁/低落）** |\n| 🎯 核心目标 | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` |\n\nUsing fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. The skill helps parents or teachers learn the child's mental state in time and provide effective soothing or intervention. Application scenarios: families, kindergartens, early-education centers. The system monitors in real time; when negative emotions (anger, fear, sadness) are detected, it can push reminders via app and suggest soothing actions (e.g., 'baby looks scared, please give a hug'). Skill features: children express emotions directly but busy parents often miss them. AI multimodal analysis helps parents understand the child's inner state, promote parent-child communication, and prevent emotional pile-up. Can be integrated into smart parenting devices or kindergarten management systems to upgrade smart-care capabilities.\n\n通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。该技能有助于家长或教师及时了解儿童心理状态，进行有效安抚或干预。应用场景：家庭、幼儿园、早教中心。系统实时监测，当识别到负面情绪（如愤怒、恐惧、悲伤）时，可通过APP推送提醒，并建议安抚措施（如'宝宝看起来害怕，请抱抱他'）。技能特点：儿童情绪表达直接但不易被忙碌的家长及时捕捉。通过AI多模态分析，可帮助家长理解孩子内心状态，促进亲子沟通，预防情绪积压。该技能可集成到智能育儿设备或幼儿园管理系统中，提升智能化关怀水平。\n\n## 🤖 AI 角色 | AI Role\n| 角色要点 | 说明 |\n|---|---|\n| 说明 1 | **假设你是一个专业的儿童情绪分析 AI。你的任务是分析儿童面部表情、哭声（若有音频）以及肢体动作，综合判断儿童当前的情绪类别。不要提供心理诊断或临床建议，仅输出基于多模态特征的情绪分类结果与方向性安抚提示。** |\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n### 1. 🧩 技能用途\n\n基于儿童监控视频（含或不含音频），多模态识别儿童当前主导情绪与强度，给出方向性安抚提示\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 儿童面部检测与表情识别（眉眼形态 |\n| 2 | 嘴角弧度） |\n| 3 | 肢体动作幅度估算（挥手 |\n| 4 | 跺脚 |\n| 5 | 蜷缩等） |\n| 6 | 哭声音频特征分析（可选：音调 / 频率 / 持续时间） |\n| 7 | 情绪分类（happy / calm / sad / angry / fear / cry / surprise） |\n| 8 | 情绪强度判定（low / medium / high） |\n| 9 | 情绪持续秒数 |\n| 10 | 负面情绪阈值告警 |\n| 11 | 安抚提示文案生成 |\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**：当用户提供儿童监控视频或带音频的音视频 URL/文件需要分析时，默认触发本技能进行儿童情绪识别 |\n| 🔎 明确分析意图 | 当用户明确提及儿童情绪、哭闹、暴躁、低落、悲伤、恐惧、害怕、发脾气、儿童心理状态、亲子沟通、情绪安抚等关键词，并且上传了视频/音视频文件 |\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** ：查看儿童情绪历史报告、儿童情绪报告清单、情绪识别报告清单、查询历史儿童情绪、显示所有儿童情绪报告、显示儿童情绪诊断报告，查询情绪安抚提示清单 |\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.smyx_child_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.smyx_child_emotion_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 | 📥 准备儿童监控视频输入 | 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 | ⚙️ 执行儿童情绪波动识别 | 调用 `-m scripts.smyx_child_emotion_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` | 本地儿童监控视频/音视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络儿童监控视频/音视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--pet-type` | 类别标识，儿童情绪识别场景默认 `other` | 按需填写 |\n| `--list` | 显示儿童情绪历史识别报告列表清单（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/smyx_child_emotion_recognition_analysis.py`](scripts/smyx_child_emotion_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 | 输入要求：支持 mp4/avi/mov 视频，最大 10MB；建议清晰面部 + 可选音频通道 |\n| 🧑‍⚖️ 结果性质 | 识别结果仅作为亲子沟通辅助参考，不替代专业儿童心理咨询；持续负面情绪请咨询专业医生 |\n| 🔏 隐私合规 | 隐私合规：儿童视频/音频涉及未成年人隐私，使用前需取得监护人知情同意，并妥善保管/加密相关录像 |\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| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --input /path/to/child_clip.mp4\n\n# 分析网络儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --url https://example.com/child_clip.mp4\n\n# 显示历史儿童情绪识别报告（自动触发关键词：查看儿童情绪历史报告、情绪识别报告清单等）\npython -m scripts.smyx_child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --output result.json\n```\n\nFile v1.0.24:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.24\",\n  \"publishedAt\": 1787640516458\n}\n\nFile v1.0.24:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪波动识别（哭闹/暴躁/低落）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- 响应格式：JSON\n\n## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动儿童情绪识别任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果与情绪分类\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史情绪记录\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 儿童情绪波动识别（哭闹/暴躁/低落）\n\n## 输入约束\n\n- 推荐视频清晰展示儿童面部（正面或侧脸），帧率 ≥ 15 FPS\n- 如需音频通道（哭声分析），上传带音频的 mp4/mov\n- 摄像头建议覆盖家庭客厅、儿童房或幼儿园活动区\n\n## 多模态特征\n\n- 视觉：面部表情（眉眼形态、嘴角弧度）、肢体动作幅度（挥手 / 跺脚 / 蜷缩）\n- 听觉（可选）：哭声音调、频率、持续时间\n- 时序：情绪持续时长、波动频次\n\n## 情绪类别枚举\n\n- `happy` - 快乐\n- `calm` - 平静\n- `sad` - 悲伤 / 低落\n- `angry` - 愤怒 / 暴躁\n- `fear` - 恐惧 / 害怕\n- `cry` - 哭闹\n- `surprise` - 惊讶\n\n## 输出字段（参考）\n\n- `child_detected` - 是否检测到儿童\n- `dominant_emotion` - 主导情绪类别\n- `emotion_confidence` - 主导情绪置信度\n- `emotion_intensity` - 情绪强度（low / medium / high）\n- `secondary_emotions` - 其他次要情绪及概率\n- `duration_sec` - 当前情绪持续秒数\n- `negative_emotion_alert` - 负面情绪预警（愤怒/恐惧/悲伤/哭闹超阈值）\n- `soothing_hint` - 安抚提示文案（如\"宝宝看起来害怕，请抱抱他\"）\n\n> 仅输出基于多模态特征的情绪分类结果与安抚提示，不提供心理诊断或临床建议。\n\nFile v1.0.24: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 v1.0.24:scripts/config.yaml\n\n{}\n\nFile v1.0.24:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.24: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 v1.0.24: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 v1.0.24: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 v1.0.24:skill-card.md\n\n## Description:\n\nAnalyzes child monitoring media or media URLs with cloud APIs to classify visible emotions such as crying, anger, low mood, fear, or calm and return a structured report with soothing guidance.\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 such as parents, teachers, or child-care operators use this skill to submit child monitoring media or a media URL for emotion classification, negative-emotion alerts, soothing hints, and history lookup. The output is intended as child-care communication support, not as a clinical diagnosis.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Children's videos, audio, or media URLs may be processed by remote cloud APIs.\n\nMitigation: Use the skill only with appropriate guardian or institutional consent and avoid submitting media when remote processing is unacceptable.\n\nRisk: Report history may be linked to a persistent local or remote identity, and tokens may be stored in the workspace data database.\n\nMitigation: Install only if the publisher and backend service are trusted, and review local workspace data handling before using report history features.\n\nRisk: Emotion classifications and soothing hints could be mistaken for clinical assessment.\n\nMitigation: Treat results as child-care communication support; do not use them as psychological diagnosis or clinical advice.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n- [Child emotion recognition API documentation](artifact/references/api_doc.md)\n- [Shared analysis API documentation](artifact/skills/smyx_analysis/references/api_doc.md)\n- [Skill demo](https://lifeemergence.com/sample.html)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON, shell commands, guidance]\n\n**Output Format:** [Markdown text with embedded JSON-style structured analysis, report links, and optional saved output files]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May query cloud-hosted report history and may save report text to a user-specified output file.]\n\n## Skill Version(s):\n\n1.0.24 (source: server release evidence; artifact frontmatter says 1.0.9)\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 v1.0.24:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.24:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.23: 31 files, 40792 bytes\n\nFiles: references/api_doc.md (1982b), scripts/__init__.py (53b), scripts/config.py (704b), scripts/config.yaml (3b), scripts/skill.py (599b), scripts/smyx_child_emotion_recognition_analysis.py (3592b), skill-card.md (3066b), SKILL.md (12334b), 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 (159b)\n\nFile v1.0.23:SKILL.md\n\n---\nname: \"smyx-child-emotion-recognition-analysis\"\ndescription: \"Using fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。\"\nversion: \"1.0.9\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落）\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **儿童情绪波动识别（哭闹/暴躁/低落）** |\n| 🎯 核心目标 | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` |\n\nUsing fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. The skill helps parents or teachers learn the child's mental state in time and provide effective soothing or intervention. Application scenarios: families, kindergartens, early-education centers. The system monitors in real time; when negative emotions (anger, fear, sadness) are detected, it can push reminders via app and suggest soothing actions (e.g., 'baby looks scared, please give a hug'). Skill features: children express emotions directly but busy parents often miss them. AI multimodal analysis helps parents understand the child's inner state, promote parent-child communication, and prevent emotional pile-up. Can be integrated into smart parenting devices or kindergarten management systems to upgrade smart-care capabilities.\n\n通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。该技能有助于家长或教师及时了解儿童心理状态，进行有效安抚或干预。应用场景：家庭、幼儿园、早教中心。系统实时监测，当识别到负面情绪（如愤怒、恐惧、悲伤）时，可通过APP推送提醒，并建议安抚措施（如'宝宝看起来害怕，请抱抱他'）。技能特点：儿童情绪表达直接但不易被忙碌的家长及时捕捉。通过AI多模态分析，可帮助家长理解孩子内心状态，促进亲子沟通，预防情绪积压。该技能可集成到智能育儿设备或幼儿园管理系统中，提升智能化关怀水平。\n\n## 🤖 AI 角色 | AI Role\n| 角色要点 | 说明 |\n|---|---|\n| 说明 1 | **假设你是一个专业的儿童情绪分析 AI。你的任务是分析儿童面部表情、哭声（若有音频）以及肢体动作，综合判断儿童当前的情绪类别。不要提供心理诊断或临床建议，仅输出基于多模态特征的情绪分类结果与方向性安抚提示。** |\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n### 1. 🧩 技能用途\n\n基于儿童监控视频（含或不含音频），多模态识别儿童当前主导情绪与强度，给出方向性安抚提示\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 儿童面部检测与表情识别（眉眼形态 |\n| 2 | 嘴角弧度） |\n| 3 | 肢体动作幅度估算（挥手 |\n| 4 | 跺脚 |\n| 5 | 蜷缩等） |\n| 6 | 哭声音频特征分析（可选：音调 / 频率 / 持续时间） |\n| 7 | 情绪分类（happy / calm / sad / angry / fear / cry / surprise） |\n| 8 | 情绪强度判定（low / medium / high） |\n| 9 | 情绪持续秒数 |\n| 10 | 负面情绪阈值告警 |\n| 11 | 安抚提示文案生成 |\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**：当用户提供儿童监控视频或带音频的音视频 URL/文件需要分析时，默认触发本技能进行儿童情绪识别 |\n| 🔎 明确分析意图 | 当用户明确提及儿童情绪、哭闹、暴躁、低落、悲伤、恐惧、害怕、发脾气、儿童心理状态、亲子沟通、情绪安抚等关键词，并且上传了视频/音视频文件 |\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** ：查看儿童情绪历史报告、儿童情绪报告清单、情绪识别报告清单、查询历史儿童情绪、显示所有儿童情绪报告、显示儿童情绪诊断报告，查询情绪安抚提示清单 |\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.smyx_child_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.smyx_child_emotion_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 | 📥 准备儿童监控视频输入 | 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 | ⚙️ 执行儿童情绪波动识别 | 调用 `-m scripts.smyx_child_emotion_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` | 本地儿童监控视频/音视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络儿童监控视频/音视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--pet-type` | 类别标识，儿童情绪识别场景默认 `other` | 按需填写 |\n| `--list` | 显示儿童情绪历史识别报告列表清单（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/smyx_child_emotion_recognition_analysis.py`](scripts/smyx_child_emotion_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 | 输入要求：支持 mp4/avi/mov 视频，最大 10MB；建议清晰面部 + 可选音频通道 |\n| 🧑‍⚖️ 结果性质 | 识别结果仅作为亲子沟通辅助参考，不替代专业儿童心理咨询；持续负面情绪请咨询专业医生 |\n| 🔏 隐私合规 | 隐私合规：儿童视频/音频涉及未成年人隐私，使用前需取得监护人知情同意，并妥善保管/加密相关录像 |\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| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --input /path/to/child_clip.mp4\n\n# 分析网络儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --url https://example.com/child_clip.mp4\n\n# 显示历史儿童情绪识别报告（自动触发关键词：查看儿童情绪历史报告、情绪识别报告清单等）\npython -m scripts.smyx_child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --output result.json\n```\n\nFile v1.0.23:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.23\",\n  \"publishedAt\": 1787314546086\n}\n\nFile v1.0.23:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪波动识别（哭闹/暴躁/低落）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- 响应格式：JSON\n\n## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动儿童情绪识别任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果与情绪分类\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史情绪记录\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 儿童情绪波动识别（哭闹/暴躁/低落）\n\n## 输入约束\n\n- 推荐视频清晰展示儿童面部（正面或侧脸），帧率 ≥ 15 FPS\n- 如需音频通道（哭声分析），上传带音频的 mp4/mov\n- 摄像头建议覆盖家庭客厅、儿童房或幼儿园活动区\n\n## 多模态特征\n\n- 视觉：面部表情（眉眼形态、嘴角弧度）、肢体动作幅度（挥手 / 跺脚 / 蜷缩）\n- 听觉（可选）：哭声音调、频率、持续时间\n- 时序：情绪持续时长、波动频次\n\n## 情绪类别枚举\n\n- `happy` - 快乐\n- `calm` - 平静\n- `sad` - 悲伤 / 低落\n- `angry` - 愤怒 / 暴躁\n- `fear` - 恐惧 / 害怕\n- `cry` - 哭闹\n- `surprise` - 惊讶\n\n## 输出字段（参考）\n\n- `child_detected` - 是否检测到儿童\n- `dominant_emotion` - 主导情绪类别\n- `emotion_confidence` - 主导情绪置信度\n- `emotion_intensity` - 情绪强度（low / medium / high）\n- `secondary_emotions` - 其他次要情绪及概率\n- `duration_sec` - 当前情绪持续秒数\n- `negative_emotion_alert` - 负面情绪预警（愤怒/恐惧/悲伤/哭闹超阈值）\n- `soothing_hint` - 安抚提示文案（如\"宝宝看起来害怕，请抱抱他\"）\n\n> 仅输出基于多模态特征的情绪分类结果与安抚提示，不提供心理诊断或临床建议。\n\nFile v1.0.23: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 v1.0.23:scripts/config.yaml\n\n{}\n\nFile v1.0.23:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.23: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 v1.0.23: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 v1.0.23: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 v1.0.23:skill-card.md\n\n## Description:\n\nThis skill analyzes child camera, video, and optional audio inputs with multimodal emotion recognition to classify states such as happy, sad, angry, fearful, crying, and calm, and to return structured reports and soothing guidance.\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 caregivers, teachers, and developers use this skill to submit child video/audio files or media URLs for emotion classification, negative-emotion alerting, soothing hints, and historical report lookup. Results are assistive observations and are not a substitute for professional child psychology or medical advice.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Sensitive child video, audio, child-media URLs, and generated reports are sent to and queried from a configured remote backend.\n\nMitigation: Use only with guardian consent, avoid unnecessary identifiers in media, and confirm the publisher's retention, deletion, encryption, and access-control practices before use.\n\nRisk: The skill can create or reuse a local account identity and store tokens in a workspace SQLite database.\n\nMitigation: Run in an isolated workspace, restrict access to workspace data files, and remove local identity/token storage when the skill is no longer needed.\n\nRisk: Historical report listing and export links can expose stored child emotion reports.\n\nMitigation: Verify the active account context before listing or exporting reports, and review report links before sharing them outside the authorized caregiving or teaching context.\n\nRisk: Emotion classifications and soothing hints may be inaccurate or overinterpreted as clinical conclusions.\n\nMitigation: Treat outputs as assistive observations for adult review and seek qualified professional support for persistent distress, safety concerns, or suspected clinical issues.\n\n## Reference(s):\n\n- [API Interface Documentation](references/api_doc.md)\n- [Shared Analysis API Documentation](skills/smyx_analysis/references/api_doc.md)\n- [Skill Demo](https://lifeemergence.com/sample.html)\n- [ClawHub Skill Page](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, json, guidance]\n\n**Output Format:** [Markdown report text with JSON-structured analysis, status messages, soothing guidance, and report/export links.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May write analysis output to a user-specified local file and may return historical report lists from the configured remote service.]\n\n## Skill Version(s):\n\n1.0.23 (source: server release metadata; artifact frontmatter is 1.0.9)\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 v1.0.23:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.23:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.22: 31 files, 38387 bytes\n\nFiles: references/api_doc.md (682b), scripts/__init__.py (31b), scripts/child_emotion_recognition_analysis.py (3208b), scripts/config.py (665b), scripts/config.yaml (3b), scripts/skill.py (573b), skill-card.md (2347b), SKILL.md (9539b), 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 (159b)\n\nFile v1.0.22:SKILL.md\n\n---\nname: \"child-emotion-recognition-analysis\"\ndescription: \"Identifies negative emotions such as crying, anger, fear, and distress through surveillance footage. It actively issues soothing reminders and notifies parents, making it suitable for homes, kindergartens, and daycare centers. | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景\"\nversion: \"1.0.13\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition Analyzer | 儿童情绪识别分析工具\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 | **儿童情绪识别分析工具** |\n| 🎯 核心目标 | 儿童情绪识别分析技能，通过监控画面识别儿童哭闹、愤怒、恐惧、委屈等负面情绪，主动发出安抚提醒并通知家长，适用于家庭、幼儿园、托管场所等场景 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、风险/识别结果、建议与报告链接 |\n| 🧩 场景码 | `CHILD_EMOTION_RECOGNITION` |\n\nBy analyzing facial expressions, vocal characteristics, and body movements in surveillance footage, this capability\nidentifies negative emotions in children—such as crying, anger, fear, and distress—in real time. Upon detecting\nemotional anomalies, the system actively issues verbal soothing prompts and synchronizes alert notifications to parents'\nor caregivers' mobile devices. Ideal for homes, kindergartens, and care centers, it helps caregivers stay informed about\nchildren's psychological states, enhancing both emotional care and safety assurance.\n\n本技能通过分析监控画面中儿童的面部表情、声音特征及肢体动作，实时识别哭闹、愤怒、恐惧、委屈等负面情绪。识别到异常情绪后，系统可主动发出语音安抚提示，并同步推送预警信息至家长或看护人员手机端。适用于家庭、幼儿园、托管场所等场景，帮助照护者及时了解儿童心理状态，提升情感关怀与安全保障能力。\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/图片分析，识别儿童的情绪状态，特别关注哭闹、愤怒、恐惧、委屈等负面情绪\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 面部表情识别 |\n| 2 | 情绪分类 |\n| 3 | 负面情绪检测 |\n| 4 | 异常情绪预警 |\n| 5 | 自动提醒通知 |\n\n### 3. ⚡ 触发条件\n\n| 触发类型 | 触发规则 |\n|---|---|\n| ✅ 默认触发 | **默认触发**：当用户提供监控视频/图片需要识别儿童情绪时，默认触发本技能进行情绪分析 |\n| 🔎 明确分析意图 | 当用户明确需要进行儿童情绪识别、情绪监测时，提及儿童情绪、哭闹识别、宝宝哭闹、情绪预警等关键词，并且上传了视频或图片文件 |\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** ：查看历史情绪报告、儿童情绪识别报告清单、情绪报告列表、查询历史情绪报告、显示所有情绪报告、儿童情绪分析报告，查询儿童情绪识别分析报告 |\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_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.child_emotion_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/图片输入 | 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 | ⚙️ 执行儿童情绪识别分析 | 调用 `-m scripts.child_emotion_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/图片文件路径 | 适用于本地文件分析 |\n| `--url` | 网络视频/图片 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--list` | 显示历史儿童情绪识别分析报告列表清单（可以输入起始日期参数过滤数据范围） | 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_emotion_recognition_analysis.py`](scripts/child_emotion_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 | 支持格式：jpg/jpeg/png/mp4/avi/mov，最大 10MB |\n| 🧑‍⚖️ 结果性质 | 分析结果仅供参考，不能替代成人看护，紧急情况请及时现场处理 |\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 | 传入的网路地址参数，不需要下载本地，默认地址都是公网地址，api 服务会自动下载 |\n| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地图片\npython -m scripts.child_emotion_recognition_analysis --input /path/to/child.jpg\n\n# 分析网络视频\npython -m scripts.child_emotion_recognition_analysis --url https://example.com/monitor.mp4\n\n# 分析监控视频\npython -m scripts.child_emotion_recognition_analysis --input /path/to/camera.mp4\n\n# 显示历史分析报告/显示分析报告清单列表/显示历史情绪报告（自动触发关键词：查看历史情绪报告、历史报告、情绪报告清单等）\npython -m scripts.child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --detail basic\n\n# 保存结果到文件\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --output result.json\n```\n\nFile v1.0.22:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.22\",\n  \"publishedAt\": 1787218829554\n}\n\nFile v1.0.22:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪识别分析 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/ai-analysis/v2/start-common-ai-analysis` - 启动AI分析任务\n2. `/web/ai-analysis/v2/get-common-ai-analysis-result` - 获取分析结果\n3. `/web/ai-analysis/page-common-ai-analysis-result` - 分页查询历史报告\n4. `/ai/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `OPEN_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 开放平台儿童情绪识别分析\n\nFile v1.0.22: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 v1.0.22:scripts/config.yaml\n\n{}\n\nFile v1.0.22:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.22: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 v1.0.22: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 v1.0.22: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 v1.0.22:skill-card.md\n\n## Description:\n\nAnalyzes child surveillance images or videos to identify negative emotions such as crying, anger, fear, and distress, then returns structured reports, reminders, notifications, and report links.\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 caregivers, parents, daycare operators, and developers use this skill to analyze uploaded or URL-based child images and videos for emotion signals and to retrieve historical cloud reports.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill may upload child images or videos to LifeEmergence services.\n\nMitigation: Use only with guardian and operator consent, and confirm retention, deletion, and notification-recipient expectations before deployment.\n\nRisk: The skill may create or reuse an internal account identity and store tokens in a workspace SQLite database.\n\nMitigation: Run it in an isolated workspace, protect the local database, avoid shared machines, and rotate or revoke credentials if the workspace is exposed.\n\nRisk: The skill can retrieve prior cloud reports for sensitive child surveillance analysis.\n\nMitigation: Limit historical-report access to authorized users and verify the account context before running report-list queries.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n- [Skill demo](https://lifeemergence.com/sample.html)\n- [Child emotion recognition API documentation](references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON]\n\n**Output Format:** [Markdown text with JSON-formatted structured analysis or report-list content.]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include LifeEmergence report export links; results can optionally be written to a user-specified output file.]\n\n## Skill Version(s):\n\n1.0.22 (source: ClawHub release evidence; 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 v1.0.22:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.22:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3\n\nArchive v1.0.21: 31 files, 40587 bytes\n\nFiles: references/api_doc.md (1982b), scripts/__init__.py (53b), scripts/config.py (704b), scripts/config.yaml (3b), scripts/skill.py (599b), scripts/smyx_child_emotion_recognition_analysis.py (3592b), skill-card.md (2563b), SKILL.md (12334b), 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 (159b)\n\nFile v1.0.21:SKILL.md\n\n---\nname: \"smyx-child-emotion-recognition-analysis\"\ndescription: \"Using fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。\"\nversion: \"1.0.8\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落）\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **儿童情绪波动识别（哭闹/暴躁/低落）** |\n| 🎯 核心目标 | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` |\n\nUsing fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. The skill helps parents or teachers learn the child's mental state in time and provide effective soothing or intervention. Application scenarios: families, kindergartens, early-education centers. The system monitors in real time; when negative emotions (anger, fear, sadness) are detected, it can push reminders via app and suggest soothing actions (e.g., 'baby looks scared, please give a hug'). Skill features: children express emotions directly but busy parents often miss them. AI multimodal analysis helps parents understand the child's inner state, promote parent-child communication, and prevent emotional pile-up. Can be integrated into smart parenting devices or kindergarten management systems to upgrade smart-care capabilities.\n\n通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。该技能有助于家长或教师及时了解儿童心理状态，进行有效安抚或干预。应用场景：家庭、幼儿园、早教中心。系统实时监测，当识别到负面情绪（如愤怒、恐惧、悲伤）时，可通过APP推送提醒，并建议安抚措施（如'宝宝看起来害怕，请抱抱他'）。技能特点：儿童情绪表达直接但不易被忙碌的家长及时捕捉。通过AI多模态分析，可帮助家长理解孩子内心状态，促进亲子沟通，预防情绪积压。该技能可集成到智能育儿设备或幼儿园管理系统中，提升智能化关怀水平。\n\n## 🤖 AI 角色 | AI Role\n| 角色要点 | 说明 |\n|---|---|\n| 说明 1 | **假设你是一个专业的儿童情绪分析 AI。你的任务是分析儿童面部表情、哭声（若有音频）以及肢体动作，综合判断儿童当前的情绪类别。不要提供心理诊断或临床建议，仅输出基于多模态特征的情绪分类结果与方向性安抚提示。** |\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n### 1. 🧩 技能用途\n\n基于儿童监控视频（含或不含音频），多模态识别儿童当前主导情绪与强度，给出方向性安抚提示\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 儿童面部检测与表情识别（眉眼形态 |\n| 2 | 嘴角弧度） |\n| 3 | 肢体动作幅度估算（挥手 |\n| 4 | 跺脚 |\n| 5 | 蜷缩等） |\n| 6 | 哭声音频特征分析（可选：音调 / 频率 / 持续时间） |\n| 7 | 情绪分类（happy / calm / sad / angry / fear / cry / surprise） |\n| 8 | 情绪强度判定（low / medium / high） |\n| 9 | 情绪持续秒数 |\n| 10 | 负面情绪阈值告警 |\n| 11 | 安抚提示文案生成 |\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**：当用户提供儿童监控视频或带音频的音视频 URL/文件需要分析时，默认触发本技能进行儿童情绪识别 |\n| 🔎 明确分析意图 | 当用户明确提及儿童情绪、哭闹、暴躁、低落、悲伤、恐惧、害怕、发脾气、儿童心理状态、亲子沟通、情绪安抚等关键词，并且上传了视频/音视频文件 |\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** ：查看儿童情绪历史报告、儿童情绪报告清单、情绪识别报告清单、查询历史儿童情绪、显示所有儿童情绪报告、显示儿童情绪诊断报告，查询情绪安抚提示清单 |\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.smyx_child_emotion_recognition_analysis --list\n```\n\n| 类型 | 要求 |\n|---|---|\n| ✅ 必须 | 使用 `python -m scripts.smyx_child_emotion_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 | 📥 准备儿童监控视频输入 | 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 | ⚙️ 执行儿童情绪波动识别 | 调用 `-m scripts.smyx_child_emotion_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` | 本地儿童监控视频/音视频文件路径 | 适用于本地文件分析 |\n| `--url` | 网络儿童监控视频/音视频 URL 地址（API 服务自动下载） | API 服务自动下载网络资源 |\n| `--pet-type` | 类别标识，儿童情绪识别场景默认 `other` | 按需填写 |\n| `--list` | 显示儿童情绪历史识别报告列表清单（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/smyx_child_emotion_recognition_analysis.py`](scripts/smyx_child_emotion_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 | 输入要求：支持 mp4/avi/mov 视频，最大 10MB；建议清晰面部 + 可选音频通道 |\n| 🧑‍⚖️ 结果性质 | 识别结果仅作为亲子沟通辅助参考，不替代专业儿童心理咨询；持续负面情绪请咨询专业医生 |\n| 🔏 隐私合规 | 隐私合规：儿童视频/音频涉及未成年人隐私，使用前需取得监护人知情同意，并妥善保管/加密相关录像 |\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| 📜 报告输出 | 当显示历史分析报告清单的时候，从接口返回 json 数据中提取字段  作为超链接地址，且自动转化为如下 Markdown |\n| 📜 报告输出 | 表格输出示例 |\n\n## 🧰 使用示例 | Examples\n```bash\n# 分析本地儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --input /path/to/child_clip.mp4\n\n# 分析网络儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --url https://example.com/child_clip.mp4\n\n# 显示历史儿童情绪识别报告（自动触发关键词：查看儿童情绪历史报告、情绪识别报告清单等）\npython -m scripts.smyx_child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --output result.json\n```\n\nFile v1.0.21:_meta.json\n\n{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.21\",\n  \"publishedAt\": 1786746629419\n}\n\nFile v1.0.21:references/api_doc.md\n\n# API 接口文档\n\n此处用于存放儿童情绪波动识别（哭闹/暴躁/低落）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- 响应格式：JSON\n\n## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动儿童情绪识别任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果与情绪分类\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史情绪记录\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 儿童情绪波动识别（哭闹/暴躁/低落）\n\n## 输入约束\n\n- 推荐视频清晰展示儿童面部（正面或侧脸），帧率 ≥ 15 FPS\n- 如需音频通道（哭声分析），上传带音频的 mp4/mov\n- 摄像头建议覆盖家庭客厅、儿童房或幼儿园活动区\n\n## 多模态特征\n\n- 视觉：面部表情（眉眼形态、嘴角弧度）、肢体动作幅度（挥手 / 跺脚 / 蜷缩）\n- 听觉（可选）：哭声音调、频率、持续时间\n- 时序：情绪持续时长、波动频次\n\n## 情绪类别枚举\n\n- `happy` - 快乐\n- `calm` - 平静\n- `sad` - 悲伤 / 低落\n- `angry` - 愤怒 / 暴躁\n- `fear` - 恐惧 / 害怕\n- `cry` - 哭闹\n- `surprise` - 惊讶\n\n## 输出字段（参考）\n\n- `child_detected` - 是否检测到儿童\n- `dominant_emotion` - 主导情绪类别\n- `emotion_confidence` - 主导情绪置信度\n- `emotion_intensity` - 情绪强度（low / medium / high）\n- `secondary_emotions` - 其他次要情绪及概率\n- `duration_sec` - 当前情绪持续秒数\n- `negative_emotion_alert` - 负面情绪预警（愤怒/恐惧/悲伤/哭闹超阈值）\n- `soothing_hint` - 安抚提示文案（如\"宝宝看起来害怕，请抱抱他\"）\n\n> 仅输出基于多模态特征的情绪分类结果与安抚提示，不提供心理诊断或临床建议。\n\nFile v1.0.21: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 v1.0.21:scripts/config.yaml\n\n{}\n\nFile v1.0.21:skills/smyx_analysis/scripts/config.yaml\n\n{}\n\nFile v1.0.21: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 v1.0.21: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 v1.0.21: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 v1.0.21:skill-card.md\n\n## Description:\n\nAnalyzes child monitoring video, optional audio, images, or URLs to classify emotion states such as happy, calm, sad, angry, fearful, crying, or surprised and return a structured report with soothing guidance.\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 such as parents, educators, early-childhood staff, and smart-care operators use this skill to analyze child monitoring media for emotion classification, negative-emotion alerts, report history, and non-clinical soothing suggestions.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Child video, optional audio, media URLs, and inferred emotion reports may be sent to the publisher's cloud service.\n\nMitigation: Use only with guardian consent, avoid sensitive footage until retention and deletion practices are documented, and confirm where reports are stored.\n\nRisk: The skill uses account identity, history access, and local token persistence to associate and retrieve reports.\n\nMitigation: Limit access to trusted environments, review account and token handling before deployment, and confirm opt-in, revocation, and report-deletion controls.\n\nRisk: Emotion labels and soothing hints can be mistaken for clinical or psychological diagnosis.\n\nMitigation: Treat outputs as non-clinical support for caregiving decisions and seek qualified professional advice for persistent or severe distress.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/18072937735/skills/smyx-child-emotion-recognition-analysis)\n- [Skill demo](https://lifeemergence.com/sample.html)\n- [API interface documentation](references/api_doc.md)\n- [API error-code documentation](skills/smyx_analysis/references/api_doc.md)\n\n## Skill Output:\n\n**Output Type(s):** [text, markdown, JSON, guidance]\n\n**Output Format:** [Markdown text with structured JSON report content and report links]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [May include emotion class, confidence, intensity, duration, alert status, soothing hint, and exported report link.]\n\n## Skill Version(s):\n\n1.0.21 (source: server release metadata; artifact frontmatter reports 1.0.8)\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 v1.0.21:skills/smyx_analysis/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nyaml==6.0.3\n\nFile v1.0.21:skills/smyx_common/requirements.txt\n\npydash==8.0.6\nSQLAlchemy==2.0.46\nPyYAML==6.0.3","readmeExcerpt":"Skill: Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落） Owner: 18072937735 Summary: Using fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and join","codeSnippets":[],"executableExamples":[{"language":"bash","snippet":"python -m scripts.smyx_child_emotion_recognition_analysis --list"},{"language":"text","snippet":"requests>=2.28.0"},{"language":"bash","snippet":"# 分析本地儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --input /path/to/child_clip.mp4\n\n# 分析网络儿童监控音视频\npython -m scripts.smyx_child_emotion_recognition_analysis --url https://example.com/child_clip.mp4\n\n# 显示历史儿童情绪识别报告（自动触发关键词：查看儿童情绪历史报告、情绪识别报告清单等）\npython -m scripts.smyx_child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --detail basic\n\n# 保存结果到文件\npython -m scripts.smyx_child_emotion_recognition_analysis --input clip.mp4 --output result.json"},{"language":"bash","snippet":"python -m scripts.child_emotion_recognition_analysis --list"},{"language":"text","snippet":"requests>=2.28.0"},{"language":"bash","snippet":"# 分析本地图片\npython -m scripts.child_emotion_recognition_analysis --input /path/to/child.jpg\n\n# 分析网络视频\npython -m scripts.child_emotion_recognition_analysis --url https://example.com/monitor.mp4\n\n# 分析监控视频\npython -m scripts.child_emotion_recognition_analysis --input /path/to/camera.mp4\n\n# 显示历史分析报告/显示分析报告清单列表/显示历史情绪报告（自动触发关键词：查看历史情绪报告、历史报告、情绪报告清单等）\npython -m scripts.child_emotion_recognition_analysis --list\n\n# 输出精简报告\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --detail basic\n\n# 保存结果到文件\npython -m scripts.child_emotion_recognition_analysis --input capture.jpg --output result.json"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: \"smyx-child-emotion-recognition-analysis\"\ndescription: \"Using fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。\"\nversion: \"1.0.14\"\nlicense: \"MIT-0\"\n---\n\n# 😊 Child Emotion Recognition (Crying/Tantrum/Low Mood) | 儿童情绪波动识别（哭闹/暴躁/低落）\n> **智能分析中枢** · 图片/视频智能分析 · 结构化报告 · 历史报告云端查询\n\n---\n\n## 🧭 技能概览 | Overview\n\n| 模块 | 内容 |\n|---|---|\n| 🏷️ 技能名称 | **儿童情绪波动识别（哭闹/暴躁/低落）** |\n| 🎯 核心目标 | 通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。 |\n| 🖼️ 输入类型 | 图片、视频、本地文件、网络 URL |\n| 📝 输出能力 | 结构化分析报告、识别/监测结果、建议与报告链接 |\n| 🧩 场景码 | `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` |\n\nUsing fixed cameras (and optional microphones) at home or in kindergartens, AI multimodal analysis recognizes a child's facial expressions (eyebrow/eye shape, mouth-corner curvature), cry-sound features (pitch, frequency, duration), and body-motion amplitude (waving, stomping, curling up) in real time, and jointly identifies the child's typical emotional state: happy, sad, angry, fearful, etc. The skill helps parents or teachers learn the child's mental state in time and provide effective soothing or intervention. Application scenarios: families, kindergartens, early-education centers. The system monitors in real time; when negative emotions (anger, fear, sadness) are detected, it can push reminders via app and suggest soothing actions (e.g., 'baby looks scared, please give a hug'). Skill features: children express emotions directly but busy parents often miss them. AI multimodal analysis helps parents understand the child's inner state, promote parent-child communication, and prevent emotional pile-up. Can be integrated into smart parenting devices or kindergarten management systems to upgrade smart-care capabilities.\n\n通过家庭或幼儿园内的固定摄像头（及可选麦克风），利用AI多模态分析技术实时分析儿童的面部表情（如眉眼形态、嘴角弧度）、哭声音频特征（音调、频率、持续时间）以及肢体动作幅度（挥手、跺脚、蜷缩等），综合识别出儿童当前的典型情绪状态：快乐、悲伤、愤怒、恐惧等。该技能有助于家长或教师及时了解儿童心理状态，进行有效安抚或干预。应用场景：家庭、幼儿园、早教中心。系统实时监测，当识别到负面情绪（如愤怒、恐惧、悲伤）时，可通过APP推送提醒，并建议安抚措施（如'宝宝看起来害怕，请抱抱他'）。技能特点：儿童情绪表达直接但不易被忙碌的家长及时捕捉。通过AI多模态分析，可帮助家长理解孩子内心状态，促进亲子沟通，预防情绪积压。该技能可集成到智能育儿设备或幼儿园管理系统中，提升智能化关怀水平。\n\n## 🤖 AI 角色 | AI Role\n| 角色要点 | 说明 |\n|---|---|\n| 说明 1 | **假设你是一个专业的儿童情绪分析 AI。你的任务是分析儿童面部表情、哭声（若有音频）以及肢体动作，综合判断儿童当前的情绪类别。不要提供心理诊断或临床建议，仅输出基于多模态特征的情绪分类结果与方向性安抚提示。** |\n\n## 🎬 技能演示 | Skill Demo\n\n[▶️ 点击查看技能使用介绍](https://lifeemergence.com/sample.html)\n\n---\n\n## 🎯 任务目标 | Goals\n### 1. 🧩 技能用途\n\n基于儿童监控视频（含或不含音频），多模态识别儿童当前主导情绪与强度，给出方向性安抚提示\n\n### 2. 🛠️ 能力范围\n\n| 序号 | 具体能力 |\n|---:|---|\n| 1 | 儿童面部检测与表情识别（眉眼形态 |\n| 2 | 嘴角弧度"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn7e2caqj7pnsvr9r7t8zenghs83xw7n\",\n  \"slug\": \"smyx-child-emotion-recognition-analysis\",\n  \"version\": \"1.0.30\",\n  \"publishedAt\": 1790804611349\n}"},{"path":"references/api_doc.md","content":"# API 接口文档\n\n此处用于存放儿童情绪波动识别（哭闹/暴躁/低落）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- 响应格式：JSON\n\n## 主要接口\n\n1. `/web/health-analysis/v2/start-health-analysis` - 启动儿童情绪识别任务\n2. `/web/health-analysis/v2/get-health-analysis-result` - 获取分析结果与情绪分类\n3. `/web/health-analysis/page-health-analysis-result` - 分页查询历史情绪记录\n4. `/health/order/api/getReportDetailExport?id={id}` - 导出完整报告\n\n## 场景代码\n\n- `SMYX_CHILD_EMOTION_RECOGNITION_ANALYSIS` - 儿童情绪波动识别（哭闹/暴躁/低落）\n\n## 输入约束\n\n- 推荐视频清晰展示儿童面部（正面或侧脸），帧率 ≥ 15 FPS\n- 如需音频通道（哭声分析），上传带音频的 mp4/mov\n- 摄像头建议覆盖家庭客厅、儿童房或幼儿园活动区\n\n## 多模态特征\n\n- 视觉：面部表情（眉眼形态、嘴角弧度）、肢体动作幅度（挥手 / 跺脚 / 蜷缩）\n- 听觉（可选）：哭声音调、频率、持续时间\n- 时序：情绪持续时长、波动频次\n\n## 情绪类别枚举\n\n- `happy` - 快乐\n- `calm` - 平静\n- `sad` - 悲伤 / 低落\n- `angry` - 愤怒 / 暴躁\n- `fear` - 恐惧 / 害怕\n- `cry` - 哭闹\n- `surprise` - 惊讶\n\n## 输出字段（参考）\n\n- `child_detected` - 是否检测到儿童\n- `dominant_emotion` - 主导情绪类别\n- `emotion_confidence` - 主导情绪置信度\n- `emotion_intensity` - 情绪强度（low / medium / high）\n- `secondary_emotions` - 其他次要情绪及概率\n- `duration_sec` - 当前情绪持续秒数\n- `negative_emotion_alert` - 负面情绪预警（愤怒/恐惧/悲伤/哭闹超阈值）\n- `soothing_hint` - 安抚提示文案（如\"宝宝看起来害怕，请抱抱他\"）\n\n> 仅输出基于多模态特征的情绪分类结果与安抚提示，不提供心理诊断或临床建议。"},{"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":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1395,"uniquenessScore":42,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-09T11:05:12.850Z","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":"2026-10-09T11:05:12.850Z","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":"2026-10-10T03:38:46.655Z","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"}]}}}