{"id":"a6577ba8-1646-485a-ba32-fadfb20303e0","entityType":"agent","slug":"clawhub-hengruizzzz-clawhealth-data-skill","name":"ClawHealth Data Skill","canonicalUrl":"https://www.xpersona.co/agent/clawhub-hengruizzzz-clawhealth-data-skill","canonicalPath":"/agent/clawhub-hengruizzzz-clawhealth-data-skill","generatedAt":"2026-10-11T11:28:21.897Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T08:54:47.872Z","emptyReason":null},"description":"ClawHealth is an agent-native precision health service that connects wearable data, nutrition, goals, readiness, reports, anomaly context, and temporary visu...","descriptionLabel":"Source description","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s17b9fsdf1xm32gj55mfrzsz3h8698d9:clawhealth-data-skill","sourceUrl":"https://clawhub.ai/hengruizzzz/clawhealth-data-skill","homepage":"https://clawhub.ai/hengruizzzz/skills/clawhealth-data-skill","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/hengruizzzz/clawhealth-data-skill","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/hengruizzzz/skills/clawhealth-data-skill","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"ClawHealth Data Skill technical dossier on Xpersona with agent coverage, OPENCLEW support, and live trust metadata."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T08:54:47.872Z","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":"2026-10-11T08:54:47.872Z","emptyReason":null},"stars":null,"forks":null,"downloads":1107,"packageName":null,"latestVersion":"0.5.1","tractionLabel":"1.1K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T08:54:47.858Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T08:54:47.872Z","lastCrawledAt":"2026-10-11T08:54:47.858Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T08:54:47.858Z","lastVerifiedAt":null,"highlights":[{"version":"0.5.1","createdAt":"2026-06-01T00:20:07.858Z","changelog":"clawhealth-data-skill v0.5.1 - Updated SKILL.md to add a new section on the \"First 7 Days Experience\" with usage and guidance for initial user setup and interaction. - Removed older doc file: skill-card.md, streamlining documentation. - Clarified and organized documentation for user onboarding, data usage, and report cadence in SKILL.md. - No changes to functionality; documentation improvements only.","fileCount":4,"zipByteSize":10357},{"version":"0.5.0","createdAt":"2026-05-31T23:32:37.633Z","changelog":"ClawHealth Data Skill v0.5.0 - Updated descriptions and instructions for improved clarity, both in English and Chinese. - Added new setup sequence guidance for first-time users, including app setup and Agent token storage. - Expanded detail on proactive health event delivery and WeChat bridge integration. - Updated tool list: removed deprecated endpoints, renamed health analysis API, and streamlined protocol explanations. - Changed focus domains: now includes anomaly context, readiness, nutrition, and passive state detection. - Removed skill-card.md file and cleaned README and SKILL documentation for better maintainability.","fileCount":4,"zipByteSize":9909},{"version":"0.4.2","createdAt":"2026-05-14T02:10:41.874Z","changelog":"Update bilingual ClawHealth introduction and add clawhealth.site access link.","fileCount":4,"zipByteSize":8376},{"version":"0.4.1","createdAt":"2026-05-13T17:55:04.294Z","changelog":"Fix temporary panel link handling: require panel_token, clarify network fallback, and tolerate escaped ampersands in panel URLs.","fileCount":3,"zipByteSize":5784},{"version":"0.4.0","createdAt":"2026-05-07T23:43:17.741Z","changelog":"Adds nutrition monitor, basic profile targets, readiness and mood tracking, bilingual guidance, and updated ClawHealth panel workflow.","fileCount":3,"zipByteSize":5589},{"version":"0.3.0","createdAt":"2026-05-07T23:17:33.995Z","changelog":"Adds invite-code onboarding model, daily weekly long-term reports, attention terminology, health-check guidance, and literature-backed supplement reasoning.","fileCount":3,"zipByteSize":4156},{"version":"0.2.1","createdAt":"2026-05-07T22:17:55.559Z","changelog":"Use clawhealth.site as the public Skill host after custom domain setup.","fileCount":3,"zipByteSize":2945},{"version":"0.2.0","createdAt":"2026-05-07T21:54:54.876Z","changelog":"Replace access-code chat flow with long-lived Agent API tokens, add daily health reports, and keep web panels on short-lived tokens.","fileCount":3,"zipByteSize":2945}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s17b9fsdf1xm32gj55mfrzsz3h8698d9:clawhealth-data-skill","setupComplexity":"low","setupSteps":["Install using `clawhub skill install s17b9fsdf1xm32gj55mfrzsz3h8698d9:clawhealth-data-skill` 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/hengruizzzz/clawhealth-data-skill 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-hengruizzzz-clawhealth-data-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hengruizzzz-clawhealth-data-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hengruizzzz-clawhealth-data-skill/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-hengruizzzz-clawhealth-data-skill/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-hengruizzzz-clawhealth-data-skill/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-hengruizzzz-clawhealth-data-skill/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T11:28:21.895Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hengruizzzz-clawhealth-data-skill/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hengruizzzz-clawhealth-data-skill/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hengruizzzz-clawhealth-data-skill/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-hengruizzzz-clawhealth-data-skill/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":"2026-10-11T08:54:47.872Z","emptyReason":null},"readme":"Skill: ClawHealth Data Skill\n\nOwner: hengruizzzz\n\nSummary: ClawHealth is an agent-native precision health service that connects wearable data, nutrition, goals, readiness, reports, anomaly context, and temporary visu...\n\nTags: latest:0.5.1\n\nVersion history:\n\nv0.5.1 | 2026-06-01T00:20:07.858Z | auto\n\nclawhealth-data-skill v0.5.1\n\n- Updated SKILL.md to add a new section on the \"First 7 Days Experience\" with usage and guidance for initial user setup and interaction.\n- Removed older doc file: skill-card.md, streamlining documentation.\n- Clarified and organized documentation for user onboarding, data usage, and report cadence in SKILL.md.\n- No changes to functionality; documentation improvements only.\n\nv0.5.0 | 2026-05-31T23:32:37.633Z | auto\n\nClawHealth Data Skill v0.5.0\n\n- Updated descriptions and instructions for improved clarity, both in English and Chinese.\n- Added new setup sequence guidance for first-time users, including app setup and Agent token storage.\n- Expanded detail on proactive health event delivery and WeChat bridge integration.\n- Updated tool list: removed deprecated endpoints, renamed health analysis API, and streamlined protocol explanations.\n- Changed focus domains: now includes anomaly context, readiness, nutrition, and passive state detection.\n- Removed skill-card.md file and cleaned README and SKILL documentation for better maintainability.\n\nv0.4.2 | 2026-05-14T02:10:41.874Z | user\n\nUpdate bilingual ClawHealth introduction and add clawhealth.site access link.\n\nv0.4.1 | 2026-05-13T17:55:04.294Z | user\n\nFix temporary panel link handling: require panel_token, clarify network fallback, and tolerate escaped ampersands in panel URLs.\n\nv0.4.0 | 2026-05-07T23:43:17.741Z | user\n\nAdds nutrition monitor, basic profile targets, readiness and mood tracking, bilingual guidance, and updated ClawHealth panel workflow.\n\nv0.3.0 | 2026-05-07T23:17:33.995Z | user\n\nAdds invite-code onboarding model, daily weekly long-term reports, attention terminology, health-check guidance, and literature-backed supplement reasoning.\n\nv0.2.1 | 2026-05-07T22:17:55.559Z | user\n\nUse clawhealth.site as the public Skill host after custom domain setup.\n\nv0.2.0 | 2026-05-07T21:54:54.876Z | user\n\nReplace access-code chat flow with long-lived Agent API tokens, add daily health reports, and keep web panels on short-lived tokens.\n\nv0.1.1 | 2026-05-07T21:38:59.780Z | user\n\nAdd network fallback for Agent runtimes that cannot reach the ClawHealth Vercel API\n\nv0.1.0 | 2026-05-07T21:33:51.751Z | user\n\nInitial ClawHealth data skill with temporary panel links, health analysis, healthcare-check guidance, and supplement protocol flow\n\nArchive index:\n\nArchive v0.5.1: 4 files, 10357 bytes\n\nFiles: README.md (1245b), skill-card.md (2005b), SKILL.md (18848b), _meta.json (140b)\n\nFile v0.5.1:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: ClawHealth is an agent-native precision health service that connects wearable data, nutrition, goals, readiness, reports, anomaly context, and temporary visual panels to the user's own Agent. 小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务，把可穿戴数据、营养记录、目标、准备度、报告、异常上下文和临时可视化面板连接到用户自己的 Agent。Visit https://clawhealth.site to request access.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\n## What ClawHealth Does\n\n**English.** ClawHealth is an agent-native precision health service. It lets a user's own Agent call structured health services instead of guessing from screenshots or generic advice. The current hosted service connects recent Apple Health / HealthKit data, nutrition records, personal goals, readiness signals, anomaly context, temporary visual panels, and feedback workflows. Users can request access and learn more at:\n\n```text\nhttps://clawhealth.site\n```\n\nAfter a user joins the test program, they use the ClawHealth iOS app to sync the latest 30 days of authorized health data and create an Agent Token. This skill then helps the Agent answer questions such as \"How am I doing today?\", \"What should I pay attention to this week?\", \"Am I ready to train hard?\", \"What did this meal do to my nutrition target?\", and \"Open my health panel.\"\n\n**中文。** 小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务。它不是让 Agent 凭截图或通用模板猜测，而是把用户授权的健康数据、营养记录、个人目标、恢复准备度、异常上下文、临时可视化面板和反馈流程，整理成 Agent 可以调用的结构化服务。欢迎前往官网注册体验：\n\n```text\nhttps://clawhealth.site\n```\n\n用户加入测试后，可以通过 ClawHealth iOS App 同步最近 30 天已授权的 Apple Health / HealthKit 数据，并创建 Agent Token。之后用户可以直接向自己的 Agent 提问，例如「我今天整体状态怎么样？」「这周需要关注什么？」「今天适合高强度训练吗？」「这顿饭对我的营养目标有什么影响？」「打开我的健康面板」。\n\nUse this skill when a user asks for a ClawHealth report, health-data analysis, readiness, nutrition, anomaly context, or a visual ClawHealth panel.\n\n## Natural User Experience\n\nNever make the user say endpoint names or function names during normal use. Natural prompts include:\n\n- \"Show my ClawHealth daily report.\"\n- \"帮我看看今天身体状态。\"\n- \"这周恢复怎么样？\"\n- \"打开我的健康面板。\"\n- \"记录这顿饭的营养。\"\n- \"今天适合训练吗？\"\n- \"帮我设置减脂目标。\"\n\nAfter setup, keep using the stored `customer_id` and Agent API token. Do not ask the user to repeat their customer ID, access code, endpoint names, or raw tool sequence unless debugging.\n\n## Setup Order\n\nUse this sequence for a new user:\n\n1. Ask the user to open the ClawHealth iOS app and finish beta login.\n2. The iOS app should request HealthKit permission during first setup and complete the first rolling 30-day sync.\n3. Ask the user to create an Agent Token in the app.\n4. Ask the user to copy the Agent setup prompt from the app. If the prompt includes the one-time token, store it securely as `Authorization: Bearer <token>` and do not repeat it in normal chat.\n5. Call `send_agent_heartbeat` with the current channel, then call `get_daily_health_report` for the first pattern check.\n6. If the Agent has a WeChat bridge, proactive reminders can be sent through that bridge. If not, return reminders in the current Agent conversation and suggest connecting WeChat later.\n\n新用户设置顺序：\n\n1. 让用户打开小爪健康 iOS App 并完成内测登录。\n2. iOS App 会在首次设置时请求 HealthKit 权限，并完成最近 30 天的首次同步。\n3. 让用户在 App 里创建 Agent Token。\n4. 让用户复制 App 里的 Agent 设置提示。如果提示里包含一次性 Token，请把它保存为 `Authorization: Bearer <token>`，之后不要在普通聊天里重复展示。\n5. 先调用 `send_agent_heartbeat`，再调用 `get_daily_health_report` 完成首次 pattern 检查。\n6. 如果 Agent 已经有微信桥接，就可以通过微信推送主动提醒；如果没有，就先在当前 Agent 对话里返回提醒，并引导之后连接微信。\n\n## Access Model\n\nClawHealth uses two token types:\n\n- Agent API token: long-lived token created in the ClawHealth iOS app. The app shows it once. Store and use it as `Authorization: Bearer <token>`. The backend stores only a hash. If the user deletes it in the app, the token stops working.\n- Panel token: short-lived token created by `create_panel_link`. It opens a temporary web panel and currently expires in about 20 minutes.\n\nRequired runtime values:\n\n- `customer_id`: supplied by the ClawHealth iOS app or copied Agent setup prompt.\n- `api_token`: long-lived Agent API token. Do not ask for the invite/access code in normal Agent chat.\n\nUse only this host:\n\n```text\nhttps://clawhealth.site\n```\n\nDo not use raw Vercel deployment URLs.\n\n## Proactive Health and WeChat Bridge\n\nClawHealth itself provides the health context, event queue, and polling contract. It does not directly log into a personal WeChat account.\n\nTwo modes are supported:\n\n- WeChat already connected: the Agent runtime calls ClawHealth, checks `poll_agent_events`, follows `next_poll_after_seconds`, and sends important reminders through its WeChat bridge.\n- WeChat not connected: answer inside the current Agent session and offer setup guidance for a bridge later.\n\nDo not poll aggressively. `poll_agent_events` is the cheap first step. Only call daily/weekly reports, readiness, nutrition, or health analysis when an event or user question requires it.\n\n主动健康的实现方式：\n\n- 小爪健康负责健康上下文、事件队列和低成本轮询协议，不直接登录用户个人微信。\n- 如果用户的 Agent 已经连接微信，Agent 调用小爪健康后，通过微信桥接把重要提醒发给用户。\n- 如果尚未连接微信，就先在当前 Agent 对话里返回提醒，并引导之后配置微信桥接。\n- 不要高频轮询。先调用 `poll_agent_events`，遵守 `next_poll_after_seconds`，只有必要时再调用日报、周报、准备度、营养或深度分析。\n\n## Report Modes\n\nChoose the report mode from the user's intent:\n\n- Daily report: first response for \"today\", \"now\", \"how am I doing\", \"日报\", \"今天\". Focus on top signal, missing data, and one next action.\n- Weekly report: use for \"this week\", \"weekly\", \"一周\", \"最近几天\". Compare the recent seven-day pattern with the available 30-day baseline.\n- Long-term report: use for \"long term\", \"baseline\", \"趋势\", \"长期\". Current MVP is a 30-day baseline; say clearly that stronger conclusions need repeated 30-day windows.\n- Deep analysis: use when the user asks why, wants charts, evidence, or domain-by-domain interpretation.\n- Nutrition monitor: use when the user asks about meals, calories, macros, protein, carbs, fat, fiber, or a food photo.\n- Readiness and passive state recognition: use when the user asks whether to train, asks about recovery readiness, or asks why ClawHealth detected strain, high arousal, recovery limits, or body-load changes.\n\n## First 7 Days Experience\n\nUse ClawHealth as a simple three-part product:\n\n- Trend analysis: help the user understand a period of accumulated Apple Health data.\n- Passive reminders: surface daily or proactive reminders when ClawHealth events indicate something worth noticing.\n- Active interaction: answer user questions through the Agent using ClawHealth tools.\n\nSuggested cadence:\n\n- First use: confirm the iOS app has synced recent Apple Health data, then run `get_daily_health_report` and `analyze_health_data` for the initial pattern check. Explain available data, missing data, and what the user can ask next.\n- Days 1-3: focus on daily summaries, sync reliability, missing-data guidance, and simple Agent questions. Avoid strong trend claims if only a few days are available.\n- Days 4-7: start comparing recent patterns. If enough data exists, run `get_weekly_health_report`, highlight changes versus available baseline, and create lightweight reminders only when useful.\n\n前三天和七天体验：\n\n- 首次使用：确认 iOS App 已同步最近 Apple Health 数据，然后调用 `get_daily_health_report` 和 `analyze_health_data` 做首次 pattern 检查。告诉用户目前有哪些数据、缺哪些数据、接下来可以问什么。\n- 1-3 天：重点是每日摘要、同步是否稳定、缺失数据提示，以及几个简单的主动提问入口。不要在数据很少时做过强趋势判断。\n- 4-7 天：开始做近期趋势比较。数据足够时调用 `get_weekly_health_report`，解释最近变化，并在必要时创建轻量提醒。\n\n## Tools\n\n### get_daily_health_report\n\nUse first for everyday check-ins.\n\n```http\nGET /api/clawhealth/daily-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Latest 30-day sync window\n- Overall summary\n- Top attention domains\n- Missing data\n- One practical next action\n- Relevant scientific references if needed\n\n### get_weekly_health_report\n\nUse for weekly review.\n\n```http\nGET /api/clawhealth/weekly-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Seven-day review against the available 30-day baseline\n- Domain-by-domain trend interpretation\n- Missing data\n- Citation keys and references returned by ClawHealth\n\n### get_long_term_health_report\n\nUse for baseline and longer-horizon questions.\n\n```http\nGET /api/clawhealth/long-term-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Current 30-day baseline quality\n- Persistent focus candidates\n- Next-cycle recommendation\n- Limits of the data\n\n### analyze_health_data\n\nUse when the user asks for deeper evidence, charts, or domain-by-domain interpretation.\n\n```http\nGET /api/clawhealth/health-analysis?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nUse only evidence returned by ClawHealth. Distinguish `attention`, `needs_data`, and `ok`.\n\n### create_panel_link\n\nUse when the user asks to see a visual panel.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn the exact temporary `panel_url`. Tell the user it expires in about 20 minutes.\n\nImportant:\n\n- A valid temporary panel link must contain both `customer_id` and `panel_token`.\n- If a chat renderer escapes the URL as `&amp;panel_token=...`, replace `&amp;` with `&` before returning/opening the link.\n- If the API call fails and you only have `https://clawhealth.site/health-panel?customer_id={customer_id}`, that is not a temporary panel link. It is only a manual unlock page and may ask the user to unlock in the browser.\n\n### update_basic_profile\n\nUse when the user gives age, sex, height, weight, goal, or activity level. This enables calorie and macro targets.\n\n```http\nPOST /api/clawhealth/profile\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"age\": 29,\n  \"sex\": \"male\",\n  \"height_cm\": 178,\n  \"weight_kg\": 74,\n  \"goal\": \"fat_loss\",\n  \"activity_level\": \"moderate\"\n}\n```\n\nReturn the saved profile and explain that targets use Mifflin-St Jeor plus activity and goal adjustment. It is an estimate, not measured metabolism.\n\n### record_meal_nutrition\n\nUse after the user provides a food photo, meal description, or Agent-estimated nutrition JSON.\n\nWorkflow:\n\n1. Estimate calories, protein, carbohydrate, fat, and fiber from the image/description.\n2. Be explicit that image-based nutrition is an estimate.\n3. Save the estimate to ClawHealth.\n4. Return daily totals and remaining targets.\n\n```http\nPOST /api/clawhealth/nutrition\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"meal_name\": \"lunch bowl\",\n  \"calories_kcal\": 650,\n  \"protein_g\": 38,\n  \"carbohydrate_g\": 72,\n  \"fat_g\": 21,\n  \"fiber_g\": 9,\n  \"confidence\": \"medium\",\n  \"raw_agent_json\": {}\n}\n```\n\nThe current MVP stores nutrition in ClawHealth. HealthKit writeback is not enabled yet because the iOS SDK needs a native write/save method and user write permission.\n\n### get_nutrition_summary\n\nUse when the user asks about calories, macros, remaining limits, or recent meals.\n\n```http\nGET /api/clawhealth/nutrition?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\n### record_mood\n\nUse when the user states mood, stress, energy, soreness, or subjective recovery.\n\n```http\nPOST /api/clawhealth/mood\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"mood_score\": 3,\n  \"energy_score\": 4,\n  \"stress_score\": 2,\n  \"note\": \"slept late but feels okay\"\n}\n```\n\n### get_readiness_check\n\nUse when the user asks whether to train, whether recovery is good, or how mood relates to HRV.\n\n```http\nGET /api/clawhealth/readiness?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain the readiness score as a transparent MVP heuristic from recovery, sleep, training, mood, and stress. Do not present it as a validated medical or performance diagnosis.\n\n### submit_feedback\n\nUse when the user wants to report a bug, improve a recommendation, or leave demo feedback.\n\n```http\nPOST /api/clawhealth/feedback\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"feedback\": \"text\",\n  \"context\": {}\n}\n```\n\n## Evidence, Literature, and State Recognition Rules\n\nClawHealth API responses include `scientific_references` and may include `state_model`. Use those first. You may cite them in normal language, but do not invent citations.\n\nWhen discussing passive state recognition:\n\n- Do not say the user \"is anxious\" or \"has an illness\" from wearable data.\n- Say \"physiological load\", \"high arousal\", \"recovery looks limited\", or \"strain signal\".\n- Explain which signals were used: HRV vs personal baseline, resting heart rate vs baseline, sleep debt, low-activity high heart rate, training-recovery conflict, respiratory/temperature/oxygen context if available.\n- Night events should be queued and summarized in the morning sleep/recovery report. Do not recommend waking the user for routine wellness alerts.\n- Prefer N-of-1 wording: \"compared with your recent baseline\", not generic thresholds.\n\nCurrent reference library:\n\n- Watson et al., 2015, AASM/SRS sleep-duration consensus, J Clin Sleep Med: adults should generally sleep 7+ hours regularly; use as sleep context, not diagnosis.\n- WHO, 2020 physical activity guidelines: adults should do regular activity, including 150-300 minutes moderate aerobic activity weekly where appropriate.\n- Zhang et al., 2016, CMAJ resting-heart-rate meta-analysis: higher resting heart rate is associated with higher population-level mortality risk; individual clinical context is required.\n- Maki et al., 2024, HRV/autonomic review: HRV is a non-invasive autonomic marker, but baseline and context matter.\n- Hjort et al., 2024, CGM variability review: glucose variability in people without diabetes is emerging and should be interpreted cautiously.\n- Kim et al., 2018, stress and HRV meta-analysis: HRV is useful for stress-response context but must be interpreted carefully.\n- Sensors, 2021, wearable stress systematic review: wearable stress work commonly uses HRV, HR, EDA, and respiration; HR alone is not enough.\n- International Journal of Medical Informatics, 2023, wearable stress ML systematic review: wearable stress models remain context-sensitive and need cautious generalization.\n- Frontiers in Physiology, 2013, HRV in normal and pathological sleep: sleep stages change autonomic balance, with NREM and REM showing different patterns.\n- Frontiers in Neurology, 2025, sleep deprivation and HRV meta-analysis: sleep loss is associated with autonomic changes reflected in HRV.\n- JMIR mHealth and uHealth, 2024, Fitbit/Garmin/WHOOP sleep accuracy review: consumer sleep trackers support longitudinal context but sleep-stage estimates are approximate.\n- Lancet Digital Health, 2020, Fitbit influenza-like illness surveillance: RHR and sleep changes can provide population-level physiological context.\n- Nature Biomedical Engineering, 2020, smartwatch pre-symptomatic COVID detection: extreme RHR elevations relative to individual baseline can indicate physiological changes, but this is not diagnostic.\n- IJERPH, 2021, HRV-guided training meta-analysis: HRV can guide training adjustment as a trend-based decision aid.\n- Sports Medicine, 2019, portable HRV accuracy meta-analysis: device, timing, posture, and artifact handling affect HRV reliability.\n- Mifflin et al., 1990, AJCN resting energy expenditure equation: use for estimated calorie target only.\n- Institute of Medicine / National Academies AMDR reference tables: adult macro ranges are commonly cited as carbohydrate 45-65%, fat 20-35%, and protein 10-35% of energy.\n- Jager et al., 2017, ISSN protein and exercise position stand: many exercising individuals use 1.4-2.0 g/kg/day as a protein target range.\n- Apple HealthKit Nutrition Type Identifiers: HealthKit supports dietary energy, protein, carbohydrate, fat, fiber, water, and related nutrition types.\n\n## Response Style\n\n- Match the user's language. Chinese and English are both supported.\n- Lead with what the data says, then what it may mean, then what to do next.\n- Say \"latest 30-day synced snapshot\" somewhere in the answer.\n- Use \"needs attention / 需要关注\", not \"Watch\".\n- Separate data from interpretation from next monitoring action.\n- When data is missing, say exactly which data needs authorization or syncing.\n- Keep daily reports concise. For \"deep analysis\", write a longer structured answer with headings: Data Coverage, Main Signals, Anomaly Context, Evidence Notes, Limits.\n- For food-photo estimates, return both a user-friendly explanation and a JSON-like nutrient breakdown before saving.\n- For readiness, separate objective wearable signals from subjective mood/stress entries.\n- Do not diagnose, treat, or make emergency recommendations.\n\n## Network Fallback\n\nIf the Agent runtime cannot reach `https://clawhealth.site` or TCP/HTTPS to the hosted API times out, do not keep retrying.\n\nTell the user:\n\n```text\nThe current Agent server cannot reach the ClawHealth API from its network, so I cannot create a temporary panel token right now. You can still open the manual unlock page directly:\nhttps://clawhealth.site/health-panel?customer_id={customer_id}\n```\n\nAsk the user to open that URL and unlock in the browser. Do not call it a temporary panel link, and do not put the access code into a URL unless the user explicitly requests a prefilled private link.\n\nFile v0.5.1:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\nClawHealth is an agent-native precision health service: it connects recent\nApple Health / HealthKit data, nutrition records, personal goals, readiness\nsignals, anomaly context, temporary visual panels,\nand feedback workflows to the user's own Agent.\n\n小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务。它把用户授权的\nApple Health / HealthKit 数据、营养记录、个人目标、恢复准备度、\n异常上下文、临时可视化面板和反馈流程，整理成 Agent 可以调用的结构化服务。\n\nRequest access / 注册体验:\n\n```text\nhttps://clawhealth.site\n```\n\nThe skill uses a long-lived Agent API token for normal Agent calls and a\nshort-lived panel token only for temporary web panels.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.5.1 --tags latest\n```\n\nThe user creates an Agent API token in the ClawHealth iOS app. The Agent uses\nthat token to request daily/weekly/long-term reports, deeper analysis,\nreadiness checks, nutrition summaries, mood tracking, and temporary panel links from\n`https://clawhealth.site`.\n\nFile v0.5.1:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.5.1\",\n  \"publishedAt\": 1780273207858\n}\n\nFile v0.5.1:skill-card.md\n\n## Description:\n\nClawHealth lets an agent query hosted ClawHealth services for synced wearable data, nutrition records, goals, readiness signals, anomaly context, temporary panels, and feedback workflows.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[hengruizzzz](https://clawhub.ai/user/hengruizzzz)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and their agents use this skill after ClawHealth iOS setup to request health reports, readiness checks, nutrition summaries, mood tracking, anomaly context, and temporary visual panel links.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill uses synced health, nutrition, profile, and mood data with a hosted service and a long-lived Agent API token.\n\nMitigation: Install only when the user intends to use ClawHealth with that data, protect the Agent API token like a password, and revoke it in the iOS app if exposed.\n\nRisk: Temporary panel links may expose a user's health panel while the link is active.\n\nMitigation: Do not share temporary panel links, and treat them as private until they expire.\n\n## Reference(s):\n\n- [ClawHealth site](https://clawhealth.site)\n- [ClawHub skill page](https://clawhub.ai/hengruizzzz/skills/clawhealth-data-skill)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, API calls, Configuration, Guidance]\n\n**Output Format:** [Markdown prose with HTTP examples, temporary links, and structured nutrition summaries]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Responses may include health reports, readiness guidance, nutrition estimates, setup steps, and temporary panel URLs.]\n\n## Skill Version(s):\n\n0.5.1 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v0.5.0: 4 files, 9909 bytes\n\nFiles: README.md (1245b), skill-card.md (2578b), SKILL.md (17273b), _meta.json (140b)\n\nFile v0.5.0:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: ClawHealth is an agent-native precision health service that connects wearable data, nutrition, goals, readiness, reports, anomaly context, and temporary visual panels to the user's own Agent. 小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务，把可穿戴数据、营养记录、目标、准备度、报告、异常上下文和临时可视化面板连接到用户自己的 Agent。Visit https://clawhealth.site to request access.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\n## What ClawHealth Does\n\n**English.** ClawHealth is an agent-native precision health service. It lets a user's own Agent call structured health services instead of guessing from screenshots or generic advice. The current hosted service connects recent Apple Health / HealthKit data, nutrition records, personal goals, readiness signals, anomaly context, temporary visual panels, and feedback workflows. Users can request access and learn more at:\n\n```text\nhttps://clawhealth.site\n```\n\nAfter a user joins the test program, they use the ClawHealth iOS app to sync the latest 30 days of authorized health data and create an Agent Token. This skill then helps the Agent answer questions such as \"How am I doing today?\", \"What should I pay attention to this week?\", \"Am I ready to train hard?\", \"What did this meal do to my nutrition target?\", and \"Open my health panel.\"\n\n**中文。** 小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务。它不是让 Agent 凭截图或通用模板猜测，而是把用户授权的健康数据、营养记录、个人目标、恢复准备度、异常上下文、临时可视化面板和反馈流程，整理成 Agent 可以调用的结构化服务。欢迎前往官网注册体验：\n\n```text\nhttps://clawhealth.site\n```\n\n用户加入测试后，可以通过 ClawHealth iOS App 同步最近 30 天已授权的 Apple Health / HealthKit 数据，并创建 Agent Token。之后用户可以直接向自己的 Agent 提问，例如「我今天整体状态怎么样？」「这周需要关注什么？」「今天适合高强度训练吗？」「这顿饭对我的营养目标有什么影响？」「打开我的健康面板」。\n\nUse this skill when a user asks for a ClawHealth report, health-data analysis, readiness, nutrition, anomaly context, or a visual ClawHealth panel.\n\n## Natural User Experience\n\nNever make the user say endpoint names or function names during normal use. Natural prompts include:\n\n- \"Show my ClawHealth daily report.\"\n- \"帮我看看今天身体状态。\"\n- \"这周恢复怎么样？\"\n- \"打开我的健康面板。\"\n- \"记录这顿饭的营养。\"\n- \"今天适合训练吗？\"\n- \"帮我设置减脂目标。\"\n\nAfter setup, keep using the stored `customer_id` and Agent API token. Do not ask the user to repeat their customer ID, access code, endpoint names, or raw tool sequence unless debugging.\n\n## Setup Order\n\nUse this sequence for a new user:\n\n1. Ask the user to open the ClawHealth iOS app and finish beta login.\n2. The iOS app should request HealthKit permission during first setup and complete the first rolling 30-day sync.\n3. Ask the user to create an Agent Token in the app.\n4. Ask the user to copy the Agent setup prompt from the app. If the prompt includes the one-time token, store it securely as `Authorization: Bearer <token>` and do not repeat it in normal chat.\n5. Call `send_agent_heartbeat` with the current channel, then call `get_daily_health_report` for the first pattern check.\n6. If the Agent has a WeChat bridge, proactive reminders can be sent through that bridge. If not, return reminders in the current Agent conversation and suggest connecting WeChat later.\n\n新用户设置顺序：\n\n1. 让用户打开小爪健康 iOS App 并完成内测登录。\n2. iOS App 会在首次设置时请求 HealthKit 权限，并完成最近 30 天的首次同步。\n3. 让用户在 App 里创建 Agent Token。\n4. 让用户复制 App 里的 Agent 设置提示。如果提示里包含一次性 Token，请把它保存为 `Authorization: Bearer <token>`，之后不要在普通聊天里重复展示。\n5. 先调用 `send_agent_heartbeat`，再调用 `get_daily_health_report` 完成首次 pattern 检查。\n6. 如果 Agent 已经有微信桥接，就可以通过微信推送主动提醒；如果没有，就先在当前 Agent 对话里返回提醒，并引导之后连接微信。\n\n## Access Model\n\nClawHealth uses two token types:\n\n- Agent API token: long-lived token created in the ClawHealth iOS app. The app shows it once. Store and use it as `Authorization: Bearer <token>`. The backend stores only a hash. If the user deletes it in the app, the token stops working.\n- Panel token: short-lived token created by `create_panel_link`. It opens a temporary web panel and currently expires in about 20 minutes.\n\nRequired runtime values:\n\n- `customer_id`: supplied by the ClawHealth iOS app or copied Agent setup prompt.\n- `api_token`: long-lived Agent API token. Do not ask for the invite/access code in normal Agent chat.\n\nUse only this host:\n\n```text\nhttps://clawhealth.site\n```\n\nDo not use raw Vercel deployment URLs.\n\n## Proactive Health and WeChat Bridge\n\nClawHealth itself provides the health context, event queue, and polling contract. It does not directly log into a personal WeChat account.\n\nTwo modes are supported:\n\n- WeChat already connected: the Agent runtime calls ClawHealth, checks `poll_agent_events`, follows `next_poll_after_seconds`, and sends important reminders through its WeChat bridge.\n- WeChat not connected: answer inside the current Agent session and offer setup guidance for a bridge later.\n\nDo not poll aggressively. `poll_agent_events` is the cheap first step. Only call daily/weekly reports, readiness, nutrition, or health analysis when an event or user question requires it.\n\n主动健康的实现方式：\n\n- 小爪健康负责健康上下文、事件队列和低成本轮询协议，不直接登录用户个人微信。\n- 如果用户的 Agent 已经连接微信，Agent 调用小爪健康后，通过微信桥接把重要提醒发给用户。\n- 如果尚未连接微信，就先在当前 Agent 对话里返回提醒，并引导之后配置微信桥接。\n- 不要高频轮询。先调用 `poll_agent_events`，遵守 `next_poll_after_seconds`，只有必要时再调用日报、周报、准备度、营养或深度分析。\n\n## Report Modes\n\nChoose the report mode from the user's intent:\n\n- Daily report: first response for \"today\", \"now\", \"how am I doing\", \"日报\", \"今天\". Focus on top signal, missing data, and one next action.\n- Weekly report: use for \"this week\", \"weekly\", \"一周\", \"最近几天\". Compare the recent seven-day pattern with the available 30-day baseline.\n- Long-term report: use for \"long term\", \"baseline\", \"趋势\", \"长期\". Current MVP is a 30-day baseline; say clearly that stronger conclusions need repeated 30-day windows.\n- Deep analysis: use when the user asks why, wants charts, evidence, or domain-by-domain interpretation.\n- Nutrition monitor: use when the user asks about meals, calories, macros, protein, carbs, fat, fiber, or a food photo.\n- Readiness and passive state recognition: use when the user asks whether to train, asks about recovery readiness, or asks why ClawHealth detected strain, high arousal, recovery limits, or body-load changes.\n\n## Tools\n\n### get_daily_health_report\n\nUse first for everyday check-ins.\n\n```http\nGET /api/clawhealth/daily-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Latest 30-day sync window\n- Overall summary\n- Top attention domains\n- Missing data\n- One practical next action\n- Relevant scientific references if needed\n\n### get_weekly_health_report\n\nUse for weekly review.\n\n```http\nGET /api/clawhealth/weekly-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Seven-day review against the available 30-day baseline\n- Domain-by-domain trend interpretation\n- Missing data\n- Citation keys and references returned by ClawHealth\n\n### get_long_term_health_report\n\nUse for baseline and longer-horizon questions.\n\n```http\nGET /api/clawhealth/long-term-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Current 30-day baseline quality\n- Persistent focus candidates\n- Next-cycle recommendation\n- Limits of the data\n\n### analyze_health_data\n\nUse when the user asks for deeper evidence, charts, or domain-by-domain interpretation.\n\n```http\nGET /api/clawhealth/health-analysis?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nUse only evidence returned by ClawHealth. Distinguish `attention`, `needs_data`, and `ok`.\n\n### create_panel_link\n\nUse when the user asks to see a visual panel.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn the exact temporary `panel_url`. Tell the user it expires in about 20 minutes.\n\nImportant:\n\n- A valid temporary panel link must contain both `customer_id` and `panel_token`.\n- If a chat renderer escapes the URL as `&amp;panel_token=...`, replace `&amp;` with `&` before returning/opening the link.\n- If the API call fails and you only have `https://clawhealth.site/health-panel?customer_id={customer_id}`, that is not a temporary panel link. It is only a manual unlock page and may ask the user to unlock in the browser.\n\n### update_basic_profile\n\nUse when the user gives age, sex, height, weight, goal, or activity level. This enables calorie and macro targets.\n\n```http\nPOST /api/clawhealth/profile\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"age\": 29,\n  \"sex\": \"male\",\n  \"height_cm\": 178,\n  \"weight_kg\": 74,\n  \"goal\": \"fat_loss\",\n  \"activity_level\": \"moderate\"\n}\n```\n\nReturn the saved profile and explain that targets use Mifflin-St Jeor plus activity and goal adjustment. It is an estimate, not measured metabolism.\n\n### record_meal_nutrition\n\nUse after the user provides a food photo, meal description, or Agent-estimated nutrition JSON.\n\nWorkflow:\n\n1. Estimate calories, protein, carbohydrate, fat, and fiber from the image/description.\n2. Be explicit that image-based nutrition is an estimate.\n3. Save the estimate to ClawHealth.\n4. Return daily totals and remaining targets.\n\n```http\nPOST /api/clawhealth/nutrition\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"meal_name\": \"lunch bowl\",\n  \"calories_kcal\": 650,\n  \"protein_g\": 38,\n  \"carbohydrate_g\": 72,\n  \"fat_g\": 21,\n  \"fiber_g\": 9,\n  \"confidence\": \"medium\",\n  \"raw_agent_json\": {}\n}\n```\n\nThe current MVP stores nutrition in ClawHealth. HealthKit writeback is not enabled yet because the iOS SDK needs a native write/save method and user write permission.\n\n### get_nutrition_summary\n\nUse when the user asks about calories, macros, remaining limits, or recent meals.\n\n```http\nGET /api/clawhealth/nutrition?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\n### record_mood\n\nUse when the user states mood, stress, energy, soreness, or subjective recovery.\n\n```http\nPOST /api/clawhealth/mood\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"mood_score\": 3,\n  \"energy_score\": 4,\n  \"stress_score\": 2,\n  \"note\": \"slept late but feels okay\"\n}\n```\n\n### get_readiness_check\n\nUse when the user asks whether to train, whether recovery is good, or how mood relates to HRV.\n\n```http\nGET /api/clawhealth/readiness?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain the readiness score as a transparent MVP heuristic from recovery, sleep, training, mood, and stress. Do not present it as a validated medical or performance diagnosis.\n\n### submit_feedback\n\nUse when the user wants to report a bug, improve a recommendation, or leave demo feedback.\n\n```http\nPOST /api/clawhealth/feedback\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"feedback\": \"text\",\n  \"context\": {}\n}\n```\n\n## Evidence, Literature, and State Recognition Rules\n\nClawHealth API responses include `scientific_references` and may include `state_model`. Use those first. You may cite them in normal language, but do not invent citations.\n\nWhen discussing passive state recognition:\n\n- Do not say the user \"is anxious\" or \"has an illness\" from wearable data.\n- Say \"physiological load\", \"high arousal\", \"recovery looks limited\", or \"strain signal\".\n- Explain which signals were used: HRV vs personal baseline, resting heart rate vs baseline, sleep debt, low-activity high heart rate, training-recovery conflict, respiratory/temperature/oxygen context if available.\n- Night events should be queued and summarized in the morning sleep/recovery report. Do not recommend waking the user for routine wellness alerts.\n- Prefer N-of-1 wording: \"compared with your recent baseline\", not generic thresholds.\n\nCurrent reference library:\n\n- Watson et al., 2015, AASM/SRS sleep-duration consensus, J Clin Sleep Med: adults should generally sleep 7+ hours regularly; use as sleep context, not diagnosis.\n- WHO, 2020 physical activity guidelines: adults should do regular activity, including 150-300 minutes moderate aerobic activity weekly where appropriate.\n- Zhang et al., 2016, CMAJ resting-heart-rate meta-analysis: higher resting heart rate is associated with higher population-level mortality risk; individual clinical context is required.\n- Maki et al., 2024, HRV/autonomic review: HRV is a non-invasive autonomic marker, but baseline and context matter.\n- Hjort et al., 2024, CGM variability review: glucose variability in people without diabetes is emerging and should be interpreted cautiously.\n- Kim et al., 2018, stress and HRV meta-analysis: HRV is useful for stress-response context but must be interpreted carefully.\n- Sensors, 2021, wearable stress systematic review: wearable stress work commonly uses HRV, HR, EDA, and respiration; HR alone is not enough.\n- International Journal of Medical Informatics, 2023, wearable stress ML systematic review: wearable stress models remain context-sensitive and need cautious generalization.\n- Frontiers in Physiology, 2013, HRV in normal and pathological sleep: sleep stages change autonomic balance, with NREM and REM showing different patterns.\n- Frontiers in Neurology, 2025, sleep deprivation and HRV meta-analysis: sleep loss is associated with autonomic changes reflected in HRV.\n- JMIR mHealth and uHealth, 2024, Fitbit/Garmin/WHOOP sleep accuracy review: consumer sleep trackers support longitudinal context but sleep-stage estimates are approximate.\n- Lancet Digital Health, 2020, Fitbit influenza-like illness surveillance: RHR and sleep changes can provide population-level physiological context.\n- Nature Biomedical Engineering, 2020, smartwatch pre-symptomatic COVID detection: extreme RHR elevations relative to individual baseline can indicate physiological changes, but this is not diagnostic.\n- IJERPH, 2021, HRV-guided training meta-analysis: HRV can guide training adjustment as a trend-based decision aid.\n- Sports Medicine, 2019, portable HRV accuracy meta-analysis: device, timing, posture, and artifact handling affect HRV reliability.\n- Mifflin et al., 1990, AJCN resting energy expenditure equation: use for estimated calorie target only.\n- Institute of Medicine / National Academies AMDR reference tables: adult macro ranges are commonly cited as carbohydrate 45-65%, fat 20-35%, and protein 10-35% of energy.\n- Jager et al., 2017, ISSN protein and exercise position stand: many exercising individuals use 1.4-2.0 g/kg/day as a protein target range.\n- Apple HealthKit Nutrition Type Identifiers: HealthKit supports dietary energy, protein, carbohydrate, fat, fiber, water, and related nutrition types.\n\n## Response Style\n\n- Match the user's language. Chinese and English are both supported.\n- Lead with what the data says, then what it may mean, then what to do next.\n- Say \"latest 30-day synced snapshot\" somewhere in the answer.\n- Use \"needs attention / 需要关注\", not \"Watch\".\n- Separate data from interpretation from next monitoring action.\n- When data is missing, say exactly which data needs authorization or syncing.\n- Keep daily reports concise. For \"deep analysis\", write a longer structured answer with headings: Data Coverage, Main Signals, Anomaly Context, Evidence Notes, Limits.\n- For food-photo estimates, return both a user-friendly explanation and a JSON-like nutrient breakdown before saving.\n- For readiness, separate objective wearable signals from subjective mood/stress entries.\n- Do not diagnose, treat, or make emergency recommendations.\n\n## Network Fallback\n\nIf the Agent runtime cannot reach `https://clawhealth.site` or TCP/HTTPS to the hosted API times out, do not keep retrying.\n\nTell the user:\n\n```text\nThe current Agent server cannot reach the ClawHealth API from its network, so I cannot create a temporary panel token right now. You can still open the manual unlock page directly:\nhttps://clawhealth.site/health-panel?customer_id={customer_id}\n```\n\nAsk the user to open that URL and unlock in the browser. Do not call it a temporary panel link, and do not put the access code into a URL unless the user explicitly requests a prefilled private link.\n\nFile v0.5.0:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\nClawHealth is an agent-native precision health service: it connects recent\nApple Health / HealthKit data, nutrition records, personal goals, readiness\nsignals, anomaly context, temporary visual panels,\nand feedback workflows to the user's own Agent.\n\n小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务。它把用户授权的\nApple Health / HealthKit 数据、营养记录、个人目标、恢复准备度、\n异常上下文、临时可视化面板和反馈流程，整理成 Agent 可以调用的结构化服务。\n\nRequest access / 注册体验:\n\n```text\nhttps://clawhealth.site\n```\n\nThe skill uses a long-lived Agent API token for normal Agent calls and a\nshort-lived panel token only for temporary web panels.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.5.0 --tags latest\n```\n\nThe user creates an Agent API token in the ClawHealth iOS app. The Agent uses\nthat token to request daily/weekly/long-term reports, deeper analysis,\nreadiness checks, nutrition summaries, mood tracking, and temporary panel links from\n`https://clawhealth.site`.\n\nFile v0.5.0:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.5.0\",\n  \"publishedAt\": 1780270357633\n}\n\nFile v0.5.0:skill-card.md\n\n## Description: <br>\nClawHealth lets an agent query a hosted health service for recent Apple Health/HealthKit data, nutrition records, goals, readiness signals, anomaly context, reports, and temporary visual panels. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[hengruizzzz](https://clawhub.ai/user/hengruizzzz) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal ClawHealth users and their agents use this skill after app setup to retrieve health reports, readiness checks, nutrition summaries, mood entries, feedback workflows, and temporary panel links from the ClawHealth hosted service. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill lets an agent access and update sensitive ClawHealth data with a long-lived Agent API token. <br>\nMitigation: Store the token only in a trusted secret store, avoid pasting it into normal chats or logs, and revoke it in the ClawHealth iOS app if access is no longer needed or exposure is suspected. <br>\nRisk: Wearable, nutrition, readiness, and mood data can be incomplete or misread as medical advice. <br>\nMitigation: Separate data from interpretation, use evidence returned by ClawHealth, describe limits clearly, and avoid diagnosis, treatment, or emergency recommendations. <br>\nRisk: Temporary health panel URLs can expose a user's panel while their short-lived token remains valid. <br>\nMitigation: Return only the generated temporary panel link, tell the user it expires, and do not treat a manual unlock URL as a temporary panel link. <br>\n\n\n## Reference(s): <br>\n- [ClawHealth website](https://clawhealth.site) <br>\n- [ClawHealth Data Skill on ClawHub](https://clawhub.ai/hengruizzzz/clawhealth-data-skill) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, API calls, configuration guidance] <br>\n**Output Format:** [Markdown or plain text responses with structured health summaries, JSON-like nutrition breakdowns, and temporary panel URLs.] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Requires a customer_id and long-lived Agent API token; temporary panel links use short-lived panel tokens.] <br>\n\n## Skill Version(s): <br>\n0.5.0 (source: server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.4.2: 4 files, 8376 bytes\n\nFiles: README.md (1282b), skill-card.md (2481b), SKILL.md (13657b), _meta.json (140b)\n\nFile v0.4.2:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: ClawHealth is an agent-native precision health service that connects wearable data, nutrition, goals, readiness, health-check context, and supplement guidance to the user's own Agent. 小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务，把可穿戴数据、营养记录、目标、准备度、体检关注点和补给建议连接到用户自己的 Agent。Visit https://clawhealth.site to request access.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\n## What ClawHealth Does\n\n**English.** ClawHealth is an agent-native precision health service. It lets a user's own Agent call structured health services instead of guessing from screenshots or generic advice. The current hosted service connects recent Apple Health / HealthKit data, nutrition records, personal goals, readiness signals, health-check context, supplement reasoning, temporary visual panels, and feedback workflows. Users can request access and learn more at:\n\n```text\nhttps://clawhealth.site\n```\n\nAfter a user joins the test program, they use the ClawHealth iOS app to sync the latest 30 days of authorized health data and create an Agent Token. This skill then helps the Agent answer questions such as \"How am I doing today?\", \"What should I pay attention to this week?\", \"Am I ready to train hard?\", \"What did this meal do to my nutrition target?\", and \"Open my health panel.\"\n\n**中文。** 小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务。它不是让 Agent 凭截图或通用模板猜测，而是把用户授权的健康数据、营养记录、个人目标、恢复准备度、体检关注点、补给建议、临时可视化面板和反馈流程，整理成 Agent 可以调用的结构化服务。欢迎前往官网注册体验：\n\n```text\nhttps://clawhealth.site\n```\n\n用户加入测试后，可以通过 ClawHealth iOS App 同步最近 30 天已授权的 Apple Health / HealthKit 数据，并创建 Agent Token。之后用户可以直接向自己的 Agent 提问，例如「我今天整体状态怎么样？」「这周需要关注什么？」「今天适合高强度训练吗？」「这顿饭对我的营养目标有什么影响？」「打开我的健康面板」。\n\nUse this skill when a user asks for a ClawHealth report, health-data analysis, health-check focus, supplement reasoning, or a visual ClawHealth panel.\n\n## Natural User Experience\n\nNever make the user say endpoint names or function names during normal use. Natural prompts include:\n\n- \"Show my ClawHealth daily report.\"\n- \"帮我看看今天身体状态。\"\n- \"这周恢复怎么样？\"\n- \"最近有没有什么体检要关注的？\"\n- \"为什么推荐这些补剂？\"\n- \"打开我的健康面板。\"\n- \"记录这顿饭的营养。\"\n- \"今天适合训练吗？\"\n- \"帮我设置减脂目标。\"\n\nAfter setup, keep using the stored `customer_id` and Agent API token. Do not ask the user to repeat their customer ID, access code, endpoint names, or raw tool sequence unless debugging.\n\n## Access Model\n\nClawHealth uses two token types:\n\n- Agent API token: long-lived token created in the ClawHealth iOS app. The app shows it once. Store and use it as `Authorization: Bearer <token>`. The backend stores only a hash. If the user deletes it in the app, the token stops working.\n- Panel token: short-lived token created by `create_panel_link`. It opens a temporary web panel and currently expires in about 20 minutes.\n\nRequired runtime values:\n\n- `customer_id`: supplied by the ClawHealth iOS app or copied Agent setup prompt.\n- `api_token`: long-lived Agent API token. Do not ask for the invite/access code in normal Agent chat.\n\nUse only this host:\n\n```text\nhttps://clawhealth.site\n```\n\nDo not use raw Vercel deployment URLs.\n\n## Report Modes\n\nChoose the report mode from the user's intent:\n\n- Daily report: first response for \"today\", \"now\", \"how am I doing\", \"日报\", \"今天\". Focus on top signal, missing data, and one next action.\n- Weekly report: use for \"this week\", \"weekly\", \"一周\", \"最近几天\". Compare the recent seven-day pattern with the available 30-day baseline.\n- Long-term report: use for \"long term\", \"baseline\", \"趋势\", \"长期\". Current MVP is a 30-day baseline; say clearly that stronger conclusions need repeated 30-day windows.\n- Deep analysis: use when the user asks why, wants charts, evidence, supplement reasoning, or health-check interpretation.\n- Nutrition monitor: use when the user asks about meals, calories, macros, protein, carbs, fat, fiber, or a food photo.\n- Readiness and mood: use when the user asks whether to train, asks about recovery readiness, or wants mood/stress tracked with HRV context.\n\n## Tools\n\n### get_daily_health_report\n\nUse first for everyday check-ins.\n\n```http\nGET /api/clawhealth/daily-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Latest 30-day sync window\n- Overall summary\n- Top attention domains\n- Missing data\n- One practical next action\n- Relevant scientific references if needed\n\n### get_weekly_health_report\n\nUse for weekly review.\n\n```http\nGET /api/clawhealth/weekly-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Seven-day review against the available 30-day baseline\n- Domain-by-domain trend interpretation\n- Health-check focus\n- Missing data\n- Citation keys and references returned by ClawHealth\n\n### get_long_term_health_report\n\nUse for baseline and longer-horizon questions.\n\n```http\nGET /api/clawhealth/long-term-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Current 30-day baseline quality\n- Persistent focus candidates\n- Next-cycle recommendation\n- Limits of the data\n\n### analyze_health_data\n\nUse when the user asks for deeper evidence, charts, or domain-by-domain interpretation.\n\n```http\nGET /api/clawhealth/health-check?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nUse only evidence returned by ClawHealth. Distinguish `attention`, `needs_data`, and `ok`.\n\n### decide_healthcare_check\n\nUse `clinical_check_guidance` from `analyze_health_data`. If `should_consider_check` is true, frame the result as checkup/doctor-discussion topics, not medical advice or diagnosis.\n\nHealth Check response pattern:\n\n1. \"This is not a diagnosis.\"\n2. Mention which domains need attention.\n3. Convert them into checkup questions or metrics to ask about.\n4. Mention missing data that blocks stronger analysis.\n5. Encourage professional care for symptoms, abnormal clinical readings, or urgent concerns.\n\n### recommend_supplement_protocol\n\n```http\nGET /api/clawhealth/supplement-protocol?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain why each supplement candidate appears using returned evidence only. Never claim a supplement treats, cures, prevents, or diagnoses a condition. If confidence is `low`, say it is a cautious wellness candidate and should be reviewed if the user has conditions, medications, pregnancy, or upcoming procedures.\n\n### create_panel_link\n\nUse when the user asks to see a visual panel.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn the exact temporary `panel_url`. Tell the user it expires in about 20 minutes.\n\nImportant:\n\n- A valid temporary panel link must contain both `customer_id` and `panel_token`.\n- If a chat renderer escapes the URL as `&amp;panel_token=...`, replace `&amp;` with `&` before returning/opening the link.\n- If the API call fails and you only have `https://clawhealth.site/supplement-demo?customer_id={customer_id}`, that is not a temporary panel link. It is only a manual unlock page and may ask the user to unlock in the browser.\n\n### update_basic_profile\n\nUse when the user gives age, sex, height, weight, goal, or activity level. This enables calorie and macro targets.\n\n```http\nPOST /api/clawhealth/profile\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"age\": 29,\n  \"sex\": \"male\",\n  \"height_cm\": 178,\n  \"weight_kg\": 74,\n  \"goal\": \"fat_loss\",\n  \"activity_level\": \"moderate\"\n}\n```\n\nReturn the saved profile and explain that targets use Mifflin-St Jeor plus activity and goal adjustment. It is an estimate, not measured metabolism.\n\n### record_meal_nutrition\n\nUse after the user provides a food photo, meal description, or Agent-estimated nutrition JSON.\n\nWorkflow:\n\n1. Estimate calories, protein, carbohydrate, fat, and fiber from the image/description.\n2. Be explicit that image-based nutrition is an estimate.\n3. Save the estimate to ClawHealth.\n4. Return daily totals and remaining targets.\n\n```http\nPOST /api/clawhealth/nutrition\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"meal_name\": \"lunch bowl\",\n  \"calories_kcal\": 650,\n  \"protein_g\": 38,\n  \"carbohydrate_g\": 72,\n  \"fat_g\": 21,\n  \"fiber_g\": 9,\n  \"confidence\": \"medium\",\n  \"raw_agent_json\": {}\n}\n```\n\nThe current MVP stores nutrition in ClawHealth. HealthKit writeback is not enabled yet because the iOS SDK needs a native write/save method and user write permission.\n\n### get_nutrition_summary\n\nUse when the user asks about calories, macros, remaining limits, or recent meals.\n\n```http\nGET /api/clawhealth/nutrition?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\n### record_mood\n\nUse when the user states mood, stress, energy, soreness, or subjective recovery.\n\n```http\nPOST /api/clawhealth/mood\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"mood_score\": 3,\n  \"energy_score\": 4,\n  \"stress_score\": 2,\n  \"note\": \"slept late but feels okay\"\n}\n```\n\n### get_readiness_check\n\nUse when the user asks whether to train, whether recovery is good, or how mood relates to HRV.\n\n```http\nGET /api/clawhealth/readiness?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain the readiness score as a transparent MVP heuristic from recovery, sleep, training, mood, and stress. Do not present it as a validated medical or performance diagnosis.\n\n### submit_feedback\n\nUse when the user wants to report a bug, improve a recommendation, or leave demo feedback.\n\n```http\nPOST /api/clawhealth/feedback\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"feedback\": \"text\",\n  \"context\": {}\n}\n```\n\n## Evidence and Literature Rules\n\nClawHealth API responses include `scientific_references`. Use those first. You may cite them in normal language, but do not invent citations.\n\nCurrent reference library:\n\n- Watson et al., 2015, AASM/SRS sleep-duration consensus, J Clin Sleep Med: adults should generally sleep 7+ hours regularly; use as sleep context, not diagnosis.\n- WHO, 2020 physical activity guidelines: adults should do regular activity, including 150-300 minutes moderate aerobic activity weekly where appropriate.\n- Zhang et al., 2016, CMAJ resting-heart-rate meta-analysis: higher resting heart rate is associated with higher population-level mortality risk; individual clinical context is required.\n- Maki et al., 2024, HRV/autonomic review: HRV is a non-invasive autonomic marker, but baseline and context matter.\n- Hjort et al., 2024, CGM variability review: glucose variability in people without diabetes is emerging and should be interpreted cautiously.\n- Mah and Pitre, 2021, magnesium insomnia systematic review: magnesium sleep evidence is limited and population-specific.\n- Hidese et al., 2019, L-theanine RCT: small trial evidence suggests possible stress/sleep-quality effects; do not overstate.\n- Mifflin et al., 1990, AJCN resting energy expenditure equation: use for estimated calorie target only.\n- Institute of Medicine / National Academies AMDR reference tables: adult macro ranges are commonly cited as carbohydrate 45-65%, fat 20-35%, and protein 10-35% of energy.\n- Jager et al., 2017, ISSN protein and exercise position stand: many exercising individuals use 1.4-2.0 g/kg/day as a protein target range.\n- Apple HealthKit Nutrition Type Identifiers: HealthKit supports dietary energy, protein, carbohydrate, fat, fiber, water, and related nutrition types.\n\n## Response Style\n\n- Match the user's language. Chinese and English are both supported.\n- Lead with what the data says, then what it may mean, then what to do next.\n- Say \"latest 30-day synced snapshot\" somewhere in the answer.\n- Use \"needs attention / 需要关注\", not \"Watch\".\n- Separate data from interpretation from supplement suggestion.\n- When data is missing, say exactly which data needs authorization or syncing.\n- Keep daily reports concise. For \"deep analysis\", write a longer structured answer with headings: Data Coverage, Main Signals, Health Check Focus, Supplement Reasoning, Evidence Notes, Limits.\n- For food-photo estimates, return both a user-friendly explanation and a JSON-like nutrient breakdown before saving.\n- For readiness, separate objective wearable signals from subjective mood/stress entries.\n- Do not diagnose, treat, or make emergency recommendations.\n\n## Network Fallback\n\nIf the Agent runtime cannot reach `https://clawhealth.site` or TCP/HTTPS to the hosted API times out, do not keep retrying.\n\nTell the user:\n\n```text\nThe current Agent server cannot reach the ClawHealth API from its network, so I cannot create a temporary panel token right now. You can still open the manual unlock page directly:\nhttps://clawhealth.site/supplement-demo?customer_id={customer_id}\n```\n\nAsk the user to open that URL and unlock in the browser. Do not call it a temporary panel link, and do not put the access code into a URL unless the user explicitly requests a prefilled private link.\n\nFile v0.4.2:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\nClawHealth is an agent-native precision health service: it connects recent\nApple Health / HealthKit data, nutrition records, personal goals, readiness\nsignals, health-check context, supplement reasoning, temporary visual panels,\nand feedback workflows to the user's own Agent.\n\n小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务。它把用户授权的\nApple Health / HealthKit 数据、营养记录、个人目标、恢复准备度、体检关注点、\n补给建议、临时可视化面板和反馈流程，整理成 Agent 可以调用的结构化服务。\n\nRequest access / 注册体验:\n\n```text\nhttps://clawhealth.site\n```\n\nThe skill uses a long-lived Agent API token for normal Agent calls and a\nshort-lived panel token only for temporary web panels.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.4.2 --tags latest\n```\n\nThe user creates an Agent API token in the ClawHealth iOS app. The Agent uses\nthat token to request daily/weekly/long-term reports, deeper analysis,\nhealth-check guidance, supplement protocol JSON, and temporary panel links from\n`https://clawhealth.site`.\n\nFile v0.4.2:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.4.2\",\n  \"publishedAt\": 1778724641874\n}\n\nFile v0.4.2:skill-card.md\n\n## Description: <br>\nClawHealth is an agent-native precision health service that connects wearable data, nutrition, goals, readiness, health-check context, and supplement guidance to the user's own Agent. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[hengruizzzz](https://clawhub.ai/user/hengruizzzz) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users connect their own Agent to ClawHealth so it can request daily, weekly, and long-term health reports, nutrition summaries, readiness checks, supplement reasoning, and temporary visual panel links from the hosted ClawHealth service. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill handles sensitive health and nutrition data and uses a long-lived Agent API token. <br>\nMitigation: Install only if the user is comfortable sending this data to ClawHealth, and store the Agent API token in a secure secret store. <br>\nRisk: The security summary flags broad activation and limited consent guidance for a health-focused skill. <br>\nMitigation: Use it only for ClawHealth-linked health analysis, reports, panels, nutrition, readiness, and supplement workflows where the user has explicitly chosen ClawHealth. <br>\nRisk: Health, readiness, nutrition, and supplement outputs can be mistaken for medical advice. <br>\nMitigation: Keep responses framed as wellness interpretation or doctor-discussion topics, avoid diagnosis or treatment claims, and rely on evidence returned by ClawHealth. <br>\n\n\n## Reference(s): <br>\n- [ClawHealth access site](https://clawhealth.site) <br>\n- [ClawHub release page](https://clawhub.ai/hengruizzzz/clawhealth-data-skill) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, API calls, configuration, guidance] <br>\n**Output Format:** [Markdown and plain text with API request guidance and returned service links] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [May include temporary panel URLs and structured nutrition or readiness details returned by ClawHealth.] <br>\n\n## Skill Version(s): <br>\n0.4.2 (source: server-resolved release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v0.4.1: 3 files, 5784 bytes\n\nFiles: README.md (616b), SKILL.md (11699b), _meta.json (140b)\n\nFile v0.4.1:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: Read a user's ClawHealth 30-day HealthKit sync, produce daily/weekly/long-term health reports, open temporary panels, explain health-check signals, and recommend supplement protocols.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\nUse this skill when a user asks for a ClawHealth report, health-data analysis, health-check focus, supplement reasoning, or a visual ClawHealth panel.\n\n## Natural User Experience\n\nNever make the user say endpoint names or function names during normal use. Natural prompts include:\n\n- \"Show my ClawHealth daily report.\"\n- \"帮我看看今天身体状态。\"\n- \"这周恢复怎么样？\"\n- \"最近有没有什么体检要关注的？\"\n- \"为什么推荐这些补剂？\"\n- \"打开我的健康面板。\"\n- \"记录这顿饭的营养。\"\n- \"今天适合训练吗？\"\n- \"帮我设置减脂目标。\"\n\nAfter setup, keep using the stored `customer_id` and Agent API token. Do not ask the user to repeat their customer ID, access code, endpoint names, or raw tool sequence unless debugging.\n\n## Access Model\n\nClawHealth uses two token types:\n\n- Agent API token: long-lived token created in the ClawHealth iOS app. The app shows it once. Store and use it as `Authorization: Bearer <token>`. The backend stores only a hash. If the user deletes it in the app, the token stops working.\n- Panel token: short-lived token created by `create_panel_link`. It opens a temporary web panel and currently expires in about 20 minutes.\n\nRequired runtime values:\n\n- `customer_id`: supplied by the ClawHealth iOS app or copied Agent setup prompt.\n- `api_token`: long-lived Agent API token. Do not ask for the invite/access code in normal Agent chat.\n\nUse only this host:\n\n```text\nhttps://clawhealth.site\n```\n\nDo not use raw Vercel deployment URLs.\n\n## Report Modes\n\nChoose the report mode from the user's intent:\n\n- Daily report: first response for \"today\", \"now\", \"how am I doing\", \"日报\", \"今天\". Focus on top signal, missing data, and one next action.\n- Weekly report: use for \"this week\", \"weekly\", \"一周\", \"最近几天\". Compare the recent seven-day pattern with the available 30-day baseline.\n- Long-term report: use for \"long term\", \"baseline\", \"趋势\", \"长期\". Current MVP is a 30-day baseline; say clearly that stronger conclusions need repeated 30-day windows.\n- Deep analysis: use when the user asks why, wants charts, evidence, supplement reasoning, or health-check interpretation.\n- Nutrition monitor: use when the user asks about meals, calories, macros, protein, carbs, fat, fiber, or a food photo.\n- Readiness and mood: use when the user asks whether to train, asks about recovery readiness, or wants mood/stress tracked with HRV context.\n\n## Tools\n\n### get_daily_health_report\n\nUse first for everyday check-ins.\n\n```http\nGET /api/clawhealth/daily-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Latest 30-day sync window\n- Overall summary\n- Top attention domains\n- Missing data\n- One practical next action\n- Relevant scientific references if needed\n\n### get_weekly_health_report\n\nUse for weekly review.\n\n```http\nGET /api/clawhealth/weekly-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Seven-day review against the available 30-day baseline\n- Domain-by-domain trend interpretation\n- Health-check focus\n- Missing data\n- Citation keys and references returned by ClawHealth\n\n### get_long_term_health_report\n\nUse for baseline and longer-horizon questions.\n\n```http\nGET /api/clawhealth/long-term-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Current 30-day baseline quality\n- Persistent focus candidates\n- Next-cycle recommendation\n- Limits of the data\n\n### analyze_health_data\n\nUse when the user asks for deeper evidence, charts, or domain-by-domain interpretation.\n\n```http\nGET /api/clawhealth/health-check?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nUse only evidence returned by ClawHealth. Distinguish `attention`, `needs_data`, and `ok`.\n\n### decide_healthcare_check\n\nUse `clinical_check_guidance` from `analyze_health_data`. If `should_consider_check` is true, frame the result as checkup/doctor-discussion topics, not medical advice or diagnosis.\n\nHealth Check response pattern:\n\n1. \"This is not a diagnosis.\"\n2. Mention which domains need attention.\n3. Convert them into checkup questions or metrics to ask about.\n4. Mention missing data that blocks stronger analysis.\n5. Encourage professional care for symptoms, abnormal clinical readings, or urgent concerns.\n\n### recommend_supplement_protocol\n\n```http\nGET /api/clawhealth/supplement-protocol?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain why each supplement candidate appears using returned evidence only. Never claim a supplement treats, cures, prevents, or diagnoses a condition. If confidence is `low`, say it is a cautious wellness candidate and should be reviewed if the user has conditions, medications, pregnancy, or upcoming procedures.\n\n### create_panel_link\n\nUse when the user asks to see a visual panel.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn the exact temporary `panel_url`. Tell the user it expires in about 20 minutes.\n\nImportant:\n\n- A valid temporary panel link must contain both `customer_id` and `panel_token`.\n- If a chat renderer escapes the URL as `&amp;panel_token=...`, replace `&amp;` with `&` before returning/opening the link.\n- If the API call fails and you only have `https://clawhealth.site/supplement-demo?customer_id={customer_id}`, that is not a temporary panel link. It is only a manual unlock page and may ask the user to unlock in the browser.\n\n### update_basic_profile\n\nUse when the user gives age, sex, height, weight, goal, or activity level. This enables calorie and macro targets.\n\n```http\nPOST /api/clawhealth/profile\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"age\": 29,\n  \"sex\": \"male\",\n  \"height_cm\": 178,\n  \"weight_kg\": 74,\n  \"goal\": \"fat_loss\",\n  \"activity_level\": \"moderate\"\n}\n```\n\nReturn the saved profile and explain that targets use Mifflin-St Jeor plus activity and goal adjustment. It is an estimate, not measured metabolism.\n\n### record_meal_nutrition\n\nUse after the user provides a food photo, meal description, or Agent-estimated nutrition JSON.\n\nWorkflow:\n\n1. Estimate calories, protein, carbohydrate, fat, and fiber from the image/description.\n2. Be explicit that image-based nutrition is an estimate.\n3. Save the estimate to ClawHealth.\n4. Return daily totals and remaining targets.\n\n```http\nPOST /api/clawhealth/nutrition\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"meal_name\": \"lunch bowl\",\n  \"calories_kcal\": 650,\n  \"protein_g\": 38,\n  \"carbohydrate_g\": 72,\n  \"fat_g\": 21,\n  \"fiber_g\": 9,\n  \"confidence\": \"medium\",\n  \"raw_agent_json\": {}\n}\n```\n\nThe current MVP stores nutrition in ClawHealth. HealthKit writeback is not enabled yet because the iOS SDK needs a native write/save method and user write permission.\n\n### get_nutrition_summary\n\nUse when the user asks about calories, macros, remaining limits, or recent meals.\n\n```http\nGET /api/clawhealth/nutrition?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\n### record_mood\n\nUse when the user states mood, stress, energy, soreness, or subjective recovery.\n\n```http\nPOST /api/clawhealth/mood\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"mood_score\": 3,\n  \"energy_score\": 4,\n  \"stress_score\": 2,\n  \"note\": \"slept late but feels okay\"\n}\n```\n\n### get_readiness_check\n\nUse when the user asks whether to train, whether recovery is good, or how mood relates to HRV.\n\n```http\nGET /api/clawhealth/readiness?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain the readiness score as a transparent MVP heuristic from recovery, sleep, training, mood, and stress. Do not present it as a validated medical or performance diagnosis.\n\n### submit_feedback\n\nUse when the user wants to report a bug, improve a recommendation, or leave demo feedback.\n\n```http\nPOST /api/clawhealth/feedback\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"feedback\": \"text\",\n  \"context\": {}\n}\n```\n\n## Evidence and Literature Rules\n\nClawHealth API responses include `scientific_references`. Use those first. You may cite them in normal language, but do not invent citations.\n\nCurrent reference library:\n\n- Watson et al., 2015, AASM/SRS sleep-duration consensus, J Clin Sleep Med: adults should generally sleep 7+ hours regularly; use as sleep context, not diagnosis.\n- WHO, 2020 physical activity guidelines: adults should do regular activity, including 150-300 minutes moderate aerobic activity weekly where appropriate.\n- Zhang et al., 2016, CMAJ resting-heart-rate meta-analysis: higher resting heart rate is associated with higher population-level mortality risk; individual clinical context is required.\n- Maki et al., 2024, HRV/autonomic review: HRV is a non-invasive autonomic marker, but baseline and context matter.\n- Hjort et al., 2024, CGM variability review: glucose variability in people without diabetes is emerging and should be interpreted cautiously.\n- Mah and Pitre, 2021, magnesium insomnia systematic review: magnesium sleep evidence is limited and population-specific.\n- Hidese et al., 2019, L-theanine RCT: small trial evidence suggests possible stress/sleep-quality effects; do not overstate.\n- Mifflin et al., 1990, AJCN resting energy expenditure equation: use for estimated calorie target only.\n- Institute of Medicine / National Academies AMDR reference tables: adult macro ranges are commonly cited as carbohydrate 45-65%, fat 20-35%, and protein 10-35% of energy.\n- Jager et al., 2017, ISSN protein and exercise position stand: many exercising individuals use 1.4-2.0 g/kg/day as a protein target range.\n- Apple HealthKit Nutrition Type Identifiers: HealthKit supports dietary energy, protein, carbohydrate, fat, fiber, water, and related nutrition types.\n\n## Response Style\n\n- Match the user's language. Chinese and English are both supported.\n- Lead with what the data says, then what it may mean, then what to do next.\n- Say \"latest 30-day synced snapshot\" somewhere in the answer.\n- Use \"needs attention / 需要关注\", not \"Watch\".\n- Separate data from interpretation from supplement suggestion.\n- When data is missing, say exactly which data needs authorization or syncing.\n- Keep daily reports concise. For \"deep analysis\", write a longer structured answer with headings: Data Coverage, Main Signals, Health Check Focus, Supplement Reasoning, Evidence Notes, Limits.\n- For food-photo estimates, return both a user-friendly explanation and a JSON-like nutrient breakdown before saving.\n- For readiness, separate objective wearable signals from subjective mood/stress entries.\n- Do not diagnose, treat, or make emergency recommendations.\n\n## Network Fallback\n\nIf the Agent runtime cannot reach `https://clawhealth.site` or TCP/HTTPS to the hosted API times out, do not keep retrying.\n\nTell the user:\n\n```text\nThe current Agent server cannot reach the ClawHealth API from its network, so I cannot create a temporary panel token right now. You can still open the manual unlock page directly:\nhttps://clawhealth.site/supplement-demo?customer_id={customer_id}\n```\n\nAsk the user to open that URL and unlock in the browser. Do not call it a temporary panel link, and do not put the access code into a URL unless the user explicitly requests a prefilled private link.\n\nFile v0.4.1:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\nIt uses a long-lived Agent API token for skills and a short-lived panel token\nonly for temporary web panels.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.3.0 --tags latest\n```\n\nThe user creates an Agent API token in the ClawHealth iOS app. The Agent uses\nthat token to request daily/weekly/long-term reports, deeper analysis,\nhealth-check guidance, supplement protocol JSON, and temporary panel links from\n`https://clawhealth.site`.\n\nFile v0.4.1:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.4.1\",\n  \"publishedAt\": 1778694904294\n}\n\nArchive v0.4.0: 3 files, 5589 bytes\n\nFiles: README.md (616b), SKILL.md (11179b), _meta.json (140b)\n\nFile v0.4.0:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: Read a user's ClawHealth 30-day HealthKit sync, produce daily/weekly/long-term health reports, open temporary panels, explain health-check signals, and recommend supplement protocols.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\nUse this skill when a user asks for a ClawHealth report, health-data analysis, health-check focus, supplement reasoning, or a visual ClawHealth panel.\n\n## Natural User Experience\n\nNever make the user say endpoint names or function names during normal use. Natural prompts include:\n\n- \"Show my ClawHealth daily report.\"\n- \"帮我看看今天身体状态。\"\n- \"这周恢复怎么样？\"\n- \"最近有没有什么体检要关注的？\"\n- \"为什么推荐这些补剂？\"\n- \"打开我的健康面板。\"\n- \"记录这顿饭的营养。\"\n- \"今天适合训练吗？\"\n- \"帮我设置减脂目标。\"\n\nAfter setup, keep using the stored `customer_id` and Agent API token. Do not ask the user to repeat their customer ID, access code, endpoint names, or raw tool sequence unless debugging.\n\n## Access Model\n\nClawHealth uses two token types:\n\n- Agent API token: long-lived token created in the ClawHealth iOS app. The app shows it once. Store and use it as `Authorization: Bearer <token>`. The backend stores only a hash. If the user deletes it in the app, the token stops working.\n- Panel token: short-lived token created by `create_panel_link`. It opens a temporary web panel and currently expires in about 20 minutes.\n\nRequired runtime values:\n\n- `customer_id`: supplied by the ClawHealth iOS app or copied Agent setup prompt.\n- `api_token`: long-lived Agent API token. Do not ask for the invite/access code in normal Agent chat.\n\nUse only this host:\n\n```text\nhttps://clawhealth.site\n```\n\nDo not use raw Vercel deployment URLs.\n\n## Report Modes\n\nChoose the report mode from the user's intent:\n\n- Daily report: first response for \"today\", \"now\", \"how am I doing\", \"日报\", \"今天\". Focus on top signal, missing data, and one next action.\n- Weekly report: use for \"this week\", \"weekly\", \"一周\", \"最近几天\". Compare the recent seven-day pattern with the available 30-day baseline.\n- Long-term report: use for \"long term\", \"baseline\", \"趋势\", \"长期\". Current MVP is a 30-day baseline; say clearly that stronger conclusions need repeated 30-day windows.\n- Deep analysis: use when the user asks why, wants charts, evidence, supplement reasoning, or health-check interpretation.\n- Nutrition monitor: use when the user asks about meals, calories, macros, protein, carbs, fat, fiber, or a food photo.\n- Readiness and mood: use when the user asks whether to train, asks about recovery readiness, or wants mood/stress tracked with HRV context.\n\n## Tools\n\n### get_daily_health_report\n\nUse first for everyday check-ins.\n\n```http\nGET /api/clawhealth/daily-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Latest 30-day sync window\n- Overall summary\n- Top attention domains\n- Missing data\n- One practical next action\n- Relevant scientific references if needed\n\n### get_weekly_health_report\n\nUse for weekly review.\n\n```http\nGET /api/clawhealth/weekly-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Seven-day review against the available 30-day baseline\n- Domain-by-domain trend interpretation\n- Health-check focus\n- Missing data\n- Citation keys and references returned by ClawHealth\n\n### get_long_term_health_report\n\nUse for baseline and longer-horizon questions.\n\n```http\nGET /api/clawhealth/long-term-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Current 30-day baseline quality\n- Persistent focus candidates\n- Next-cycle recommendation\n- Limits of the data\n\n### analyze_health_data\n\nUse when the user asks for deeper evidence, charts, or domain-by-domain interpretation.\n\n```http\nGET /api/clawhealth/health-check?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nUse only evidence returned by ClawHealth. Distinguish `attention`, `needs_data`, and `ok`.\n\n### decide_healthcare_check\n\nUse `clinical_check_guidance` from `analyze_health_data`. If `should_consider_check` is true, frame the result as checkup/doctor-discussion topics, not medical advice or diagnosis.\n\nHealth Check response pattern:\n\n1. \"This is not a diagnosis.\"\n2. Mention which domains need attention.\n3. Convert them into checkup questions or metrics to ask about.\n4. Mention missing data that blocks stronger analysis.\n5. Encourage professional care for symptoms, abnormal clinical readings, or urgent concerns.\n\n### recommend_supplement_protocol\n\n```http\nGET /api/clawhealth/supplement-protocol?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain why each supplement candidate appears using returned evidence only. Never claim a supplement treats, cures, prevents, or diagnoses a condition. If confidence is `low`, say it is a cautious wellness candidate and should be reviewed if the user has conditions, medications, pregnancy, or upcoming procedures.\n\n### create_panel_link\n\nUse when the user asks to see a visual panel.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn the temporary `panel_url`. Tell the user it expires in about 20 minutes.\n\n### update_basic_profile\n\nUse when the user gives age, sex, height, weight, goal, or activity level. This enables calorie and macro targets.\n\n```http\nPOST /api/clawhealth/profile\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"age\": 29,\n  \"sex\": \"male\",\n  \"height_cm\": 178,\n  \"weight_kg\": 74,\n  \"goal\": \"fat_loss\",\n  \"activity_level\": \"moderate\"\n}\n```\n\nReturn the saved profile and explain that targets use Mifflin-St Jeor plus activity and goal adjustment. It is an estimate, not measured metabolism.\n\n### record_meal_nutrition\n\nUse after the user provides a food photo, meal description, or Agent-estimated nutrition JSON.\n\nWorkflow:\n\n1. Estimate calories, protein, carbohydrate, fat, and fiber from the image/description.\n2. Be explicit that image-based nutrition is an estimate.\n3. Save the estimate to ClawHealth.\n4. Return daily totals and remaining targets.\n\n```http\nPOST /api/clawhealth/nutrition\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"meal_name\": \"lunch bowl\",\n  \"calories_kcal\": 650,\n  \"protein_g\": 38,\n  \"carbohydrate_g\": 72,\n  \"fat_g\": 21,\n  \"fiber_g\": 9,\n  \"confidence\": \"medium\",\n  \"raw_agent_json\": {}\n}\n```\n\nThe current MVP stores nutrition in ClawHealth. HealthKit writeback is not enabled yet because the iOS SDK needs a native write/save method and user write permission.\n\n### get_nutrition_summary\n\nUse when the user asks about calories, macros, remaining limits, or recent meals.\n\n```http\nGET /api/clawhealth/nutrition?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\n### record_mood\n\nUse when the user states mood, stress, energy, soreness, or subjective recovery.\n\n```http\nPOST /api/clawhealth/mood\nAuthorization: Bearer {api_token}\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"mood_score\": 3,\n  \"energy_score\": 4,\n  \"stress_score\": 2,\n  \"note\": \"slept late but feels okay\"\n}\n```\n\n### get_readiness_check\n\nUse when the user asks whether to train, whether recovery is good, or how mood relates to HRV.\n\n```http\nGET /api/clawhealth/readiness?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain the readiness score as a transparent MVP heuristic from recovery, sleep, training, mood, and stress. Do not present it as a validated medical or performance diagnosis.\n\n### submit_feedback\n\nUse when the user wants to report a bug, improve a recommendation, or leave demo feedback.\n\n```http\nPOST /api/clawhealth/feedback\nContent-Type: application/json\n\n{\n  \"customer_id\": \"{customer_id}\",\n  \"feedback\": \"text\",\n  \"context\": {}\n}\n```\n\n## Evidence and Literature Rules\n\nClawHealth API responses include `scientific_references`. Use those first. You may cite them in normal language, but do not invent citations.\n\nCurrent reference library:\n\n- Watson et al., 2015, AASM/SRS sleep-duration consensus, J Clin Sleep Med: adults should generally sleep 7+ hours regularly; use as sleep context, not diagnosis.\n- WHO, 2020 physical activity guidelines: adults should do regular activity, including 150-300 minutes moderate aerobic activity weekly where appropriate.\n- Zhang et al., 2016, CMAJ resting-heart-rate meta-analysis: higher resting heart rate is associated with higher population-level mortality risk; individual clinical context is required.\n- Maki et al., 2024, HRV/autonomic review: HRV is a non-invasive autonomic marker, but baseline and context matter.\n- Hjort et al., 2024, CGM variability review: glucose variability in people without diabetes is emerging and should be interpreted cautiously.\n- Mah and Pitre, 2021, magnesium insomnia systematic review: magnesium sleep evidence is limited and population-specific.\n- Hidese et al., 2019, L-theanine RCT: small trial evidence suggests possible stress/sleep-quality effects; do not overstate.\n- Mifflin et al., 1990, AJCN resting energy expenditure equation: use for estimated calorie target only.\n- Institute of Medicine / National Academies AMDR reference tables: adult macro ranges are commonly cited as carbohydrate 45-65%, fat 20-35%, and protein 10-35% of energy.\n- Jager et al., 2017, ISSN protein and exercise position stand: many exercising individuals use 1.4-2.0 g/kg/day as a protein target range.\n- Apple HealthKit Nutrition Type Identifiers: HealthKit supports dietary energy, protein, carbohydrate, fat, fiber, water, and related nutrition types.\n\n## Response Style\n\n- Match the user's language. Chinese and English are both supported.\n- Lead with what the data says, then what it may mean, then what to do next.\n- Say \"latest 30-day synced snapshot\" somewhere in the answer.\n- Use \"needs attention / 需要关注\", not \"Watch\".\n- Separate data from interpretation from supplement suggestion.\n- When data is missing, say exactly which data needs authorization or syncing.\n- Keep daily reports concise. For \"deep analysis\", write a longer structured answer with headings: Data Coverage, Main Signals, Health Check Focus, Supplement Reasoning, Evidence Notes, Limits.\n- For food-photo estimates, return both a user-friendly explanation and a JSON-like nutrient breakdown before saving.\n- For readiness, separate objective wearable signals from subjective mood/stress entries.\n- Do not diagnose, treat, or make emergency recommendations.\n\n## Network Fallback\n\nIf the Agent runtime cannot reach `https://clawhealth.site` or TCP/HTTPS to the hosted API times out, do not keep retrying.\n\nTell the user:\n\n```text\nThe current Agent server cannot reach the ClawHealth API from its network. You can still open the browser panel directly:\nhttps://clawhealth.site/supplement-demo?customer_id={customer_id}\n```\n\nAsk the user to open that URL and enter their ClawHealth invite/access code in the panel. Do not put the access code into a URL unless the user explicitly requests a prefilled private link.\n\nFile v0.4.0:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\nIt uses a long-lived Agent API token for skills and a short-lived panel token\nonly for temporary web panels.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.3.0 --tags latest\n```\n\nThe user creates an Agent API token in the ClawHealth iOS app. The Agent uses\nthat token to request daily/weekly/long-term reports, deeper analysis,\nhealth-check guidance, supplement protocol JSON, and temporary panel links from\n`https://clawhealth.site`.\n\nFile v0.4.0:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.4.0\",\n  \"publishedAt\": 1778197397741\n}\n\nArchive v0.3.0: 3 files, 4156 bytes\n\nFiles: README.md (616b), SKILL.md (7414b), _meta.json (140b)\n\nFile v0.3.0:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: Read a user's ClawHealth 30-day HealthKit sync, produce daily/weekly/long-term health reports, open temporary panels, explain health-check signals, and recommend supplement protocols.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\nUse this skill when a user asks for a ClawHealth report, health-data analysis, health-check focus, supplement reasoning, or a visual ClawHealth panel.\n\n## Natural User Experience\n\nNever make the user say endpoint names or function names during normal use. Natural prompts include:\n\n- \"Show my ClawHealth daily report.\"\n- \"帮我看看今天身体状态。\"\n- \"这周恢复怎么样？\"\n- \"最近有没有什么体检要关注的？\"\n- \"为什么推荐这些补剂？\"\n- \"打开我的健康面板。\"\n\nAfter setup, keep using the stored `customer_id` and Agent API token. Do not ask the user to repeat their customer ID, access code, endpoint names, or raw tool sequence unless debugging.\n\n## Access Model\n\nClawHealth uses two token types:\n\n- Agent API token: long-lived token created in the ClawHealth iOS app. The app shows it once. Store and use it as `Authorization: Bearer <token>`. The backend stores only a hash. If the user deletes it in the app, the token stops working.\n- Panel token: short-lived token created by `create_panel_link`. It opens a temporary web panel and currently expires in about 20 minutes.\n\nRequired runtime values:\n\n- `customer_id`: supplied by the ClawHealth iOS app or copied Agent setup prompt.\n- `api_token`: long-lived Agent API token. Do not ask for the invite/access code in normal Agent chat.\n\nUse only this host:\n\n```text\nhttps://clawhealth.site\n```\n\nDo not use raw Vercel deployment URLs.\n\n## Report Modes\n\nChoose the report mode from the user's intent:\n\n- Daily report: first response for \"today\", \"now\", \"how am I doing\", \"日报\", \"今天\". Focus on top signal, missing data, and one next action.\n- Weekly report: use for \"this week\", \"weekly\", \"一周\", \"最近几天\". Compare the recent seven-day pattern with the available 30-day baseline.\n- Long-term report: use for \"long term\", \"baseline\", \"趋势\", \"长期\". Current MVP is a 30-day baseline; say clearly that stronger conclusions need repeated 30-day windows.\n- Deep analysis: use when the user asks why, wants charts, evidence, supplement reasoning, or health-check interpretation.\n\n## Tools\n\n### get_daily_health_report\n\nUse first for everyday check-ins.\n\n```http\nGET /api/clawhealth/daily-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Latest 30-day sync window\n- Overall summary\n- Top attention domains\n- Missing data\n- One practical next action\n- Relevant scientific references if needed\n\n### get_weekly_health_report\n\nUse for weekly review.\n\n```http\nGET /api/clawhealth/weekly-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Seven-day review against the available 30-day baseline\n- Domain-by-domain trend interpretation\n- Health-check focus\n- Missing data\n- Citation keys and references returned by ClawHealth\n\n### get_long_term_health_report\n\nUse for baseline and longer-horizon questions.\n\n```http\nGET /api/clawhealth/long-term-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn:\n\n- Current 30-day baseline quality\n- Persistent focus candidates\n- Next-cycle recommendation\n- Limits of the data\n\n### analyze_health_data\n\nUse when the user asks for deeper evidence, charts, or domain-by-domain interpretation.\n\n```http\nGET /api/clawhealth/health-check?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nUse only evidence returned by ClawHealth. Distinguish `attention`, `needs_data`, and `ok`.\n\n### decide_healthcare_check\n\nUse `clinical_check_guidance` from `analyze_health_data`. If `should_consider_check` is true, frame the result as checkup/doctor-discussion topics, not medical advice or diagnosis.\n\nHealth Check response pattern:\n\n1. \"This is not a diagnosis.\"\n2. Mention which domains need attention.\n3. Convert them into checkup questions or metrics to ask about.\n4. Mention missing data that blocks stronger analysis.\n5. Encourage professional care for symptoms, abnormal clinical readings, or urgent concerns.\n\n### recommend_supplement_protocol\n\n```http\nGET /api/clawhealth/supplement-protocol?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain why each supplement candidate appears using returned evidence only. Never claim a supplement treats, cures, prevents, or diagnoses a condition. If confidence is `low`, say it is a cautious wellness candidate and should be reviewed if the user has conditions, medications, pregnancy, or upcoming procedures.\n\n### create_panel_link\n\nUse when the user asks to see a visual panel.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn the temporary `panel_url`. Tell the user it expires in about 20 minutes.\n\n## Evidence and Literature Rules\n\nClawHealth API responses include `scientific_references`. Use those first. You may cite them in normal language, but do not invent citations.\n\nCurrent reference library:\n\n- Watson et al., 2015, AASM/SRS sleep-duration consensus, J Clin Sleep Med: adults should generally sleep 7+ hours regularly; use as sleep context, not diagnosis.\n- WHO, 2020 physical activity guidelines: adults should do regular activity, including 150-300 minutes moderate aerobic activity weekly where appropriate.\n- Zhang et al., 2016, CMAJ resting-heart-rate meta-analysis: higher resting heart rate is associated with higher population-level mortality risk; individual clinical context is required.\n- Maki et al., 2024, HRV/autonomic review: HRV is a non-invasive autonomic marker, but baseline and context matter.\n- Hjort et al., 2024, CGM variability review: glucose variability in people without diabetes is emerging and should be interpreted cautiously.\n- Mah and Pitre, 2021, magnesium insomnia systematic review: magnesium sleep evidence is limited and population-specific.\n- Hidese et al., 2019, L-theanine RCT: small trial evidence suggests possible stress/sleep-quality effects; do not overstate.\n\n## Response Style\n\n- Match the user's language. Chinese and English are both supported.\n- Lead with what the data says, then what it may mean, then what to do next.\n- Say \"latest 30-day synced snapshot\" somewhere in the answer.\n- Use \"needs attention / 需要关注\", not \"Watch\".\n- Separate data from interpretation from supplement suggestion.\n- When data is missing, say exactly which data needs authorization or syncing.\n- Keep daily reports concise. For \"deep analysis\", write a longer structured answer with headings: Data Coverage, Main Signals, Health Check Focus, Supplement Reasoning, Evidence Notes, Limits.\n- Do not diagnose, treat, or make emergency recommendations.\n\n## Network Fallback\n\nIf the Agent runtime cannot reach `https://clawhealth.site` or TCP/HTTPS to the hosted API times out, do not keep retrying.\n\nTell the user:\n\n```text\nThe current Agent server cannot reach the ClawHealth API from its network. You can still open the browser panel directly:\nhttps://clawhealth.site/supplement-demo?customer_id={customer_id}\n```\n\nAsk the user to open that URL and enter their ClawHealth invite/access code in the panel. Do not put the access code into a URL unless the user explicitly requests a prefilled private link.\n\nFile v0.3.0:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\nIt uses a long-lived Agent API token for skills and a short-lived panel token\nonly for temporary web panels.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.3.0 --tags latest\n```\n\nThe user creates an Agent API token in the ClawHealth iOS app. The Agent uses\nthat token to request daily/weekly/long-term reports, deeper analysis,\nhealth-check guidance, supplement protocol JSON, and temporary panel links from\n`https://clawhealth.site`.\n\nFile v0.3.0:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.3.0\",\n  \"publishedAt\": 1778195853995\n}\n\nArchive v0.2.1: 3 files, 2945 bytes\n\nFiles: README.md (594b), SKILL.md (5170b), _meta.json (140b)\n\nFile v0.2.1:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: Read a user's ClawHealth 30-day HealthKit sync, produce daily health reports, open temporary panels, explain checkup signals, and recommend supplement protocols.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\nUse this skill when a user asks for a ClawHealth daily report, health-data analysis, checkup focus, supplement reasoning, or a visual ClawHealth panel.\n\n## User-facing behavior\n\nDo not ask the user to say function names, endpoint names, or raw implementation steps. Normal user prompts should sound like:\n\n- \"Show my ClawHealth daily report.\"\n- \"Check my recovery today.\"\n- \"Do I need to pay attention to anything from my recent health data?\"\n- \"Why is ClawHealth recommending this supplement?\"\n- \"Open my health panel.\"\n\nThe user should not have to say `create_panel_link`, `analyze_health_data`, or `recommend_supplement_protocol`.\n\nAfter setup, the user should also not have to repeat their `customer_id` in\nevery request. The Agent may receive `customer_id` and the Agent API token from\nthe ClawHealth app's copied setup prompt, then keep using those values for\nlater daily reports.\n\n## Authentication model\n\nClawHealth uses two token types:\n\n- Agent API token: long-lived token created in the ClawHealth iOS app. The app shows it once. Store and use it as `Authorization: Bearer <token>`. The backend stores only a hash. If the user deletes it in the app, it stops working.\n- Panel token: short-lived token created by `create_panel_link`. It opens a temporary web panel and currently expires in 20 minutes.\n\nRequired runtime values:\n\n- `customer_id`: supplied by the ClawHealth iOS app or copied Agent prompt.\n- `api_token`: long-lived Agent API token. Do not ask for the user's access code in normal Agent chat.\n\n## Skill host\n\nUse only:\n\n```text\nhttps://clawhealth.site\n```\n\nDo not use raw Vercel deployment URLs such as `https://clawhealth-...-voicetypes-projects.vercel.app`; those can be protected by Vercel authentication.\n\n## Tools\n\n### get_daily_health_report\n\nUse first for everyday check-ins.\n\n```http\nGET /api/clawhealth/daily-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn a concise report: top focus, missing data, daily next action, and the 30-day sync window. Do not diagnose.\n\n### analyze_health_data\n\nUse when the user asks for deeper evidence, charts, or domain-by-domain interpretation.\n\n```http\nGET /api/clawhealth/health-check?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nUse only evidence returned by ClawHealth. Distinguish `watch`, `needs_data`, and `ok`.\n\n### decide_healthcare_check\n\nUse the `clinical_check_guidance` object from `analyze_health_data`. If `should_consider_check` is true, frame the result as check-in topics, not medical advice.\n\n### recommend_supplement_protocol\n\n```http\nGET /api/clawhealth/supplement-protocol?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain why each supplement candidate appears using returned evidence only. Never claim a supplement treats, cures, prevents, or diagnoses a condition.\n\n### create_panel_link\n\nUse when the user asks to see a visual panel.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn the temporary `panel_url`. Tell the user it expires in about 20 minutes.\n\n## Network fallback\n\nIf the Agent runtime cannot reach `https://clawhealth.site` or TCP/HTTPS to the hosted API times out, do not keep retrying.\n\nTell the user:\n\n```text\nThe current Agent server cannot reach the ClawHealth API from its network. You can still open the browser panel directly:\nhttps://clawhealth.site/supplement-demo?customer_id={customer_id}\n```\n\nAsk the user to open that URL and enter their ClawHealth access code in the panel. Do not put the access code into a URL unless the user explicitly requests a prefilled private link.\n\n## Response rules\n\n- Always mention that analysis uses the latest 30-day synced snapshot.\n- Lead with the daily report when the user asks broadly how they are doing.\n- Keep the user's experience natural; hide function names unless debugging.\n- Do not ask for access code in normal Agent chat. Ask the user to create or refresh the Agent API token in the ClawHealth app if authentication fails.\n- Do not respond with \"please enter your ClawHealth access code\" when a stored Agent API token should be available. Only ask the user to return to the app and create a new Agent API token if auth fails.\n- Do not make the user copy-paste raw endpoint names or function names during normal use.\n- Never diagnose, treat, or make emergency recommendations.\n- If data is missing, say what needs to be synced or authorized.\n\n## Example natural flow\n\n1. User: \"How am I doing today?\"\n2. Call `get_daily_health_report`.\n3. If there are watch domains, optionally call `analyze_health_data` for evidence.\n4. If the user asks about supplements, call `recommend_supplement_protocol`.\n5. If the user asks to see the page, call `create_panel_link`.\n6. Reply with a concise report, key evidence, any checkup focus, supplement reasoning, and a temporary panel link if requested.\n\nFile v0.2.1:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\nIt uses a long-lived Agent API token for skills and a short-lived panel token\nonly for temporary web panels.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.2.0 --tags latest\n```\n\nThe user creates an Agent API token in the ClawHealth iOS app. The Agent uses\nthat token to request daily reports, deeper analysis, checkup guidance,\nsupplement protocol JSON, and temporary panel links from\n`https://clawhealth.site`.\n\nFile v0.2.1:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.2.1\",\n  \"publishedAt\": 1778192275559\n}\n\nArchive v0.2.0: 3 files, 2945 bytes\n\nFiles: README.md (604b), SKILL.md (5192b), _meta.json (140b)\n\nFile v0.2.0:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: Read a user's ClawHealth 30-day HealthKit sync, produce daily health reports, open temporary panels, explain checkup signals, and recommend supplement protocols.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\nUse this skill when a user asks for a ClawHealth daily report, health-data analysis, checkup focus, supplement reasoning, or a visual ClawHealth panel.\n\n## User-facing behavior\n\nDo not ask the user to say function names, endpoint names, or raw implementation steps. Normal user prompts should sound like:\n\n- \"Show my ClawHealth daily report.\"\n- \"Check my recovery today.\"\n- \"Do I need to pay attention to anything from my recent health data?\"\n- \"Why is ClawHealth recommending this supplement?\"\n- \"Open my health panel.\"\n\nThe user should not have to say `create_panel_link`, `analyze_health_data`, or `recommend_supplement_protocol`.\n\nAfter setup, the user should also not have to repeat their `customer_id` in\nevery request. The Agent may receive `customer_id` and the Agent API token from\nthe ClawHealth app's copied setup prompt, then keep using those values for\nlater daily reports.\n\n## Authentication model\n\nClawHealth uses two token types:\n\n- Agent API token: long-lived token created in the ClawHealth iOS app. The app shows it once. Store and use it as `Authorization: Bearer <token>`. The backend stores only a hash. If the user deletes it in the app, it stops working.\n- Panel token: short-lived token created by `create_panel_link`. It opens a temporary web panel and currently expires in 20 minutes.\n\nRequired runtime values:\n\n- `customer_id`: supplied by the ClawHealth iOS app or copied Agent prompt.\n- `api_token`: long-lived Agent API token. Do not ask for the user's access code in normal Agent chat.\n\n## Skill host\n\nUse only:\n\n```text\nhttps://clawhealth-psi.vercel.app\n```\n\nDo not use raw Vercel deployment URLs such as `https://clawhealth-...-voicetypes-projects.vercel.app`; those can be protected by Vercel authentication.\n\n## Tools\n\n### get_daily_health_report\n\nUse first for everyday check-ins.\n\n```http\nGET /api/clawhealth/daily-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn a concise report: top focus, missing data, daily next action, and the 30-day sync window. Do not diagnose.\n\n### analyze_health_data\n\nUse when the user asks for deeper evidence, charts, or domain-by-domain interpretation.\n\n```http\nGET /api/clawhealth/health-check?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nUse only evidence returned by ClawHealth. Distinguish `watch`, `needs_data`, and `ok`.\n\n### decide_healthcare_check\n\nUse the `clinical_check_guidance` object from `analyze_health_data`. If `should_consider_check` is true, frame the result as check-in topics, not medical advice.\n\n### recommend_supplement_protocol\n\n```http\nGET /api/clawhealth/supplement-protocol?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nExplain why each supplement candidate appears using returned evidence only. Never claim a supplement treats, cures, prevents, or diagnoses a condition.\n\n### create_panel_link\n\nUse when the user asks to see a visual panel.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}\nAuthorization: Bearer {api_token}\n```\n\nReturn the temporary `panel_url`. Tell the user it expires in about 20 minutes.\n\n## Network fallback\n\nIf the Agent runtime cannot reach `https://clawhealth-psi.vercel.app` or TCP/HTTPS to Vercel times out, do not keep retrying.\n\nTell the user:\n\n```text\nThe current Agent server cannot reach the ClawHealth API from its network. You can still open the browser panel directly:\nhttps://clawhealth-psi.vercel.app/supplement-demo?customer_id={customer_id}\n```\n\nAsk the user to open that URL and enter their ClawHealth access code in the panel. Do not put the access code into a URL unless the user explicitly requests a prefilled private link.\n\n## Response rules\n\n- Always mention that analysis uses the latest 30-day synced snapshot.\n- Lead with the daily report when the user asks broadly how they are doing.\n- Keep the user's experience natural; hide function names unless debugging.\n- Do not ask for access code in normal Agent chat. Ask the user to create or refresh the Agent API token in the ClawHealth app if authentication fails.\n- Do not respond with \"please enter your ClawHealth access code\" when a stored Agent API token should be available. Only ask the user to return to the app and create a new Agent API token if auth fails.\n- Do not make the user copy-paste raw endpoint names or function names during normal use.\n- Never diagnose, treat, or make emergency recommendations.\n- If data is missing, say what needs to be synced or authorized.\n\n## Example natural flow\n\n1. User: \"How am I doing today?\"\n2. Call `get_daily_health_report`.\n3. If there are watch domains, optionally call `analyze_health_data` for evidence.\n4. If the user asks about supplements, call `recommend_supplement_protocol`.\n5. If the user asks to see the page, call `create_panel_link`.\n6. Reply with a concise report, key evidence, any checkup focus, supplement reasoning, and a temporary panel link if requested.\n\nFile v0.2.0:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\nIt uses a long-lived Agent API token for skills and a short-lived panel token\nonly for temporary web panels.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.2.0 --tags latest\n```\n\nThe user creates an Agent API token in the ClawHealth iOS app. The Agent uses\nthat token to request daily reports, deeper analysis, checkup guidance,\nsupplement protocol JSON, and temporary panel links from\n`https://clawhealth-psi.vercel.app`.\n\nFile v0.2.0:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.2.0\",\n  \"publishedAt\": 1778190894876\n}\n\nArchive v0.1.1: 3 files, 2312 bytes\n\nFiles: README.md (424b), SKILL.md (3580b), _meta.json (140b)\n\nFile v0.1.1:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: Query a user's ClawHealth 30-day HealthKit sync, create temporary health panels, explain checkup signals, and recommend supplement protocols using ClawHealth hosted Skills.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\nUse this skill when a user wants their Agent to read ClawHealth health data, open a temporary panel, understand recent health signals, decide whether a checkup focus is worth considering, or review supplement candidates.\n\n## Required user inputs\n\n- `customer_id`: prefilled by the ClawHealth iOS app or copied prompt.\n- `access_code`: ask the user for this at runtime. Do not invent it. The user gets it from the ClawHealth iOS app.\n\n## Skill host\n\nUse only the production alias:\n\n```text\nhttps://clawhealth-psi.vercel.app\n```\n\nDo not use raw Vercel deployment URLs such as `https://clawhealth-...-voicetypes-projects.vercel.app`; those can be protected by Vercel authentication.\n\n## Tools\n\n### create_panel_link\n\nCall first when the Agent runtime can make outbound HTTPS requests. It returns a temporary panel link and a `panel_token`.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}&access_code={access_code}\n```\n\nUse the returned `panel_url` when the user asks to see the data visually. The panel token currently expires in 20 minutes.\n\n### network fallback\n\nIf the Agent runtime cannot reach `https://clawhealth-psi.vercel.app` or `create_panel_link` times out, do not keep retrying. Tell the user the ClawHealth API is not reachable from the current Agent environment and provide this browser-only panel URL:\n\n```text\nhttps://clawhealth-psi.vercel.app/supplement-demo?customer_id={customer_id}\n```\n\nAsk the user to open that URL and enter their ClawHealth access code in the panel. Do not put the `access_code` into the URL unless the user explicitly asks for a prefilled private link.\n\n### analyze_health_data\n\n```http\nGET /api/clawhealth/health-check?customer_id={customer_id}&panel_token={panel_token}\n```\n\nReturn only evidence-backed observations from the response. Do not diagnose.\n\n### decide_healthcare_check\n\nUse the `clinical_check_guidance` object from `analyze_health_data`. If `should_consider_check` is true, summarize the suggested focus areas as check-in topics, not medical advice.\n\n### recommend_supplement_protocol\n\n```http\nGET /api/clawhealth/supplement-protocol?customer_id={customer_id}&panel_token={panel_token}\n```\n\nExplain why each supplement candidate appears, using `rules_triggered`, `checks`, and candidate `evidence`. If no protocol is generated, say which data is missing or which rules did not trigger.\n\n## Response rules\n\n- Always mention the data window is the latest 30-day synced snapshot.\n- Distinguish `needs_data`, `watch`, and `ok`.\n- Never claim a supplement treats, cures, or diagnoses a condition.\n- When giving a panel link, use the temporary `panel_url`.\n- If access fails, ask the user to confirm the access code in the ClawHealth app or create a new panel link from the app.\n- If the ClawHealth host times out from the Agent runtime, use the network fallback URL and explain that the browser panel can still work even when the Agent server cannot fetch the API.\n\n## Example agent flow\n\n1. User says: \"Use ClawHealth for customer_id claw_demo_claw_001_xxxxxxxx.\"\n2. Ask: \"Please enter your ClawHealth access code.\"\n3. Call `create_panel_link`.\n4. Call `analyze_health_data`.\n5. Call `recommend_supplement_protocol`.\n6. Reply with a concise health brief, any checkup focus, supplement logic, and the temporary panel link.\n\nFile v0.1.1:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.1.0 --tags latest\n```\n\nThe Agent asks for the user's access code, creates a temporary panel link, then reads health analysis and supplement protocol JSON from `https://clawhealth-psi.vercel.app`.\n\nFile v0.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.1.1\",\n  \"publishedAt\": 1778189939780\n}\n\nArchive v0.1.0: 3 files, 1948 bytes\n\nFiles: README.md (424b), SKILL.md (2615b), _meta.json (140b)\n\nFile v0.1.0:SKILL.md\n\n---\nname: clawhealth-data-skill\ndescription: Query a user's ClawHealth 30-day HealthKit sync, create temporary health panels, explain checkup signals, and recommend supplement protocols using ClawHealth hosted Skills.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\nUse this skill when a user wants their Agent to read ClawHealth health data, open a temporary panel, understand recent health signals, decide whether a checkup focus is worth considering, or review supplement candidates.\n\n## Required user inputs\n\n- `customer_id`: prefilled by the ClawHealth iOS app or copied prompt.\n- `access_code`: ask the user for this at runtime. Do not invent it. The user gets it from the ClawHealth iOS app.\n\n## Skill host\n\nDefault host:\n\n```text\nhttps://clawhealth-psi.vercel.app\n```\n\n## Tools\n\n### create_panel_link\n\nCall first. It returns a temporary panel link and a `panel_token`.\n\n```http\nGET /api/clawhealth/panel-token?customer_id={customer_id}&access_code={access_code}\n```\n\nUse the returned `panel_url` when the user asks to see the data visually. The panel token currently expires in 20 minutes.\n\n### analyze_health_data\n\n```http\nGET /api/clawhealth/health-check?customer_id={customer_id}&panel_token={panel_token}\n```\n\nReturn only evidence-backed observations from the response. Do not diagnose.\n\n### decide_healthcare_check\n\nUse the `clinical_check_guidance` object from `analyze_health_data`. If `should_consider_check` is true, summarize the suggested focus areas as check-in topics, not medical advice.\n\n### recommend_supplement_protocol\n\n```http\nGET /api/clawhealth/supplement-protocol?customer_id={customer_id}&panel_token={panel_token}\n```\n\nExplain why each supplement candidate appears, using `rules_triggered`, `checks`, and candidate `evidence`. If no protocol is generated, say which data is missing or which rules did not trigger.\n\n## Response rules\n\n- Always mention the data window is the latest 30-day synced snapshot.\n- Distinguish `needs_data`, `watch`, and `ok`.\n- Never claim a supplement treats, cures, or diagnoses a condition.\n- When giving a panel link, use the temporary `panel_url`.\n- If access fails, ask the user to confirm the access code in the ClawHealth app or create a new panel link from the app.\n\n## Example agent flow\n\n1. User says: \"Use ClawHealth for customer_id claw_demo_claw_001_xxxxxxxx.\"\n2. Ask: \"Please enter your ClawHealth access code.\"\n3. Call `create_panel_link`.\n4. Call `analyze_health_data`.\n5. Call `recommend_supplement_protocol`.\n6. Reply with a concise health brief, any checkup focus, supplement logic, and the temporary panel link.\n\nFile v0.1.0:README.md\n\n# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.1.0 --tags latest\n```\n\nThe Agent asks for the user's access code, creates a temporary panel link, then reads health analysis and supplement protocol JSON from `https://clawhealth-psi.vercel.app`.\n\nFile v0.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.1.0\",\n  \"publishedAt\": 1778189631751\n}","readmeExcerpt":"Skill: ClawHealth Data Skill Owner: hengruizzzz Summary: ClawHealth is an agent-native precision health service that connects wearable data, nutrition, goals, readiness, reports, anomaly context, and temporary visu... Tags: latest:0.5.1 Version history: v0.5.1 | 2026-06-01T00:20:07.858Z | auto clawhealth-data-skill v0.5.1 - Updated SKILL.md to add a new section on the \"First 7 Days Experience\" with usage and guidance","codeSnippets":[],"executableExamples":[{"language":"text","snippet":"https://clawhealth.site"},{"language":"text","snippet":"https://clawhealth.site"},{"language":"text","snippet":"https://clawhealth.site"},{"language":"http","snippet":"GET /api/clawhealth/daily-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}"},{"language":"http","snippet":"GET /api/clawhealth/weekly-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}"},{"language":"http","snippet":"GET /api/clawhealth/long-term-report?customer_id={customer_id}\nAuthorization: Bearer {api_token}"}],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: clawhealth-data-skill\ndescription: ClawHealth is an agent-native precision health service that connects wearable data, nutrition, goals, readiness, reports, anomaly context, and temporary visual panels to the user's own Agent. 小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务，把可穿戴数据、营养记录、目标、准备度、报告、异常上下文和临时可视化面板连接到用户自己的 Agent。Visit https://clawhealth.site to request access.\nmetadata:\n  openclaw:\n    emoji: \"❤️\"\n---\n\n# ClawHealth Data Skill\n\n## What ClawHealth Does\n\n**English.** ClawHealth is an agent-native precision health service. It lets a user's own Agent call structured health services instead of guessing from screenshots or generic advice. The current hosted service connects recent Apple Health / HealthKit data, nutrition records, personal goals, readiness signals, anomaly context, temporary visual panels, and feedback workflows. Users can request access and learn more at:\n\n```text\nhttps://clawhealth.site\n```\n\nAfter a user joins the test program, they use the ClawHealth iOS app to sync the latest 30 days of authorized health data and create an Agent Token. This skill then helps the Agent answer questions such as \"How am I doing today?\", \"What should I pay attention to this week?\", \"Am I ready to train hard?\", \"What did this meal do to my nutrition target?\", and \"Open my health panel.\"\n\n**中文。** 小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务。它不是让 Agent 凭截图或通用模板猜测，而是把用户授权的健康数据、营养记录、个人目标、恢复准备度、异常上下文、临时可视化面板和反馈流程，整理成 Agent 可以调用的结构化服务。欢迎前往官网注册体验：\n\n```text\nhttps://clawhealth.site\n```\n\n用户加入测试后，可以通过 ClawHealth iOS App 同步最近 30 天已授权的 Apple Health / HealthKit 数据，并创建 Agent Token。之后用户可以直接向自己的 Agent 提问，例如「我今天整体状态怎么样？」「这周需要关注什么？」「今天适合高强度训练吗？」「这顿饭对我的营养目标有什么影响？」「打开我的健康面板」。\n\nUse this skill when a user asks for a ClawHealth report, health-data analysis, readiness, nutrition, anomaly context, or a visual ClawHealth panel.\n\n## Natural User Experience\n\nNever make the user say endpoint names or function names during normal use. Natural prompts include:\n\n- \"Show my ClawHealth daily report.\"\n- \"帮我看看今天身体状态。\"\n- \"这周恢复怎么样？\"\n- \"打开我的健康面板。\"\n- \"记录这顿饭的营养。\"\n- \"今天适合训练吗？\"\n- \"帮我设置减脂目标。\"\n\nAfter setup, keep using the stored `customer_id` and Agent API token. Do not ask the user to repeat their customer ID, access code, endpoint names, or raw tool sequence unless debugging.\n\n## Setup Order\n\nUse this sequence for a new user:\n\n1. Ask the user to open the ClawHealth iOS app and finish beta login.\n2. The iOS app should request HealthKit permission during first setup and complete the first rolling 30-day sync.\n3. Ask the user to create an Agent Token in the app.\n4. Ask the user to copy the Agent setup prompt from the app. If the prompt includes the one-time token, store it securely as `Authorization: Bearer <token>` and do not repeat it in normal chat.\n5. Call `send_agent_heartbeat` with the current channel, then call `get_daily_health_report` for the first pattern check.\n6. If the Agent has a WeChat bridge, proactive reminders can be sent through that bridge. If not, return reminders in the curren"},{"path":"README.md","content":"# ClawHealth Data Skill\n\nThis ClawHub skill lets a user's Agent query the hosted ClawHealth Skills API.\nClawHealth is an agent-native precision health service: it connects recent\nApple Health / HealthKit data, nutrition records, personal goals, readiness\nsignals, anomaly context, temporary visual panels,\nand feedback workflows to the user's own Agent.\n\n小爪健康 / ClawHealth 是面向 Agent 的个人精准健康服务。它把用户授权的\nApple Health / HealthKit 数据、营养记录、个人目标、恢复准备度、\n异常上下文、临时可视化面板和反馈流程，整理成 Agent 可以调用的结构化服务。\n\nRequest access / 注册体验:\n\n```text\nhttps://clawhealth.site\n```\n\nThe skill uses a long-lived Agent API token for normal Agent calls and a\nshort-lived panel token only for temporary web panels.\n\nInstall/publish target:\n\n```bash\nclawhub publish . --slug clawhealth-data-skill --name \"ClawHealth Data Skill\" --version 0.5.1 --tags latest\n```\n\nThe user creates an Agent API token in the ClawHealth iOS app. The Agent uses\nthat token to request daily/weekly/long-term reports, deeper analysis,\nreadiness checks, nutrition summaries, mood tracking, and temporary panel links from\n`https://clawhealth.site`."},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn72es9rgqt0f58tqcy43afnjn81dbvn\",\n  \"slug\": \"clawhealth-data-skill\",\n  \"version\": \"0.5.1\",\n  \"publishedAt\": 1780273207858\n}"},{"path":"skill-card.md","content":"## Description:\n\nClawHealth lets an agent query hosted ClawHealth services for synced wearable data, nutrition records, goals, readiness signals, anomaly context, temporary panels, and feedback workflows.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[hengruizzzz](https://clawhub.ai/user/hengruizzzz)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nExternal users and their agents use this skill after ClawHealth iOS setup to request health reports, readiness checks, nutrition summaries, mood tracking, anomaly context, and temporary visual panel links.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: The skill uses synced health, nutrition, profile, and mood data with a hosted service and a long-lived Agent API token.\n\nMitigation: Install only when the user intends to use ClawHealth with that data, protect the Agent API token like a password, and revoke it in the iOS app if exposed.\n\nRisk: Temporary panel links may expose a user's health panel while the link is active.\n\nMitigation: Do not share temporary panel links, and treat them as private until they expire.\n\n## Reference(s):\n\n- [ClawHealth site](https://clawhealth.site)\n- [ClawHub skill page](https://clawhub.ai/hengruizzzz/skills/clawhealth-data-skill)\n\n## Skill Output:\n\n**Output Type(s):** [Text, Markdown, API calls, Configuration, Guidance]\n\n**Output Format:** [Markdown prose with HTTP examples, temporary links, and structured nutrition summaries]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Responses may include health reports, readiness guidance, nutrition estimates, setup steps, and temporary panel URLs.]\n\n## Skill Version(s):\n\n0.5.1 (source: server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":null,"editorialQuality":{"score":100,"threshold":65,"status":"thin","wordCount":1418,"uniquenessScore":43,"reasons":["uniqueness-below-45"]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T08:54:47.872Z","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":"2026-10-11T08:54:47.872Z","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":"2026-10-11T11:28:21.897Z","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"}]}}}