بنقرة واحدة
health-data-summary
综合查询健康数据 — Digital Health Twin 快照、Safety 告警、长期趋势、Orchestrator 多专家分析。当用户想了解自己的整体健康状况、趋势变化、安全风险时使用。
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
القائمة
综合查询健康数据 — Digital Health Twin 快照、Safety 告警、长期趋势、Orchestrator 多专家分析。当用户想了解自己的整体健康状况、趋势变化、安全风险时使用。
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
管理首页行动卡片 — 创建、查询、完成、归档。当用户想把某条建议固化到首页、查看当前行动计划、标记完成,使用这个 skill。
Assess chronic disease risk — cardiovascular (modified Framingham), metabolic syndrome (IDF criteria), and 90-day trend analysis. Integrates wearable data (Garmin), labs, vitals, and genetic markers for personalized risk scoring with confidence intervals.
Family health management - medical reports, medications, review calendar, family daily health check. Use when user asks about family members' health, medical exams, medications, checkup schedules, or wants to manage health for parents/spouse/children.
Query and analyze user genetic test data (基因检测). Cross-reference genetics with medical reports, Garmin wearable data, and current health status for personalized nutrition, exercise, drug sensitivity, disease risk, and sleep advice.
Get AI health analysis, daily recommendations, health trend predictions, and health scores. Use when the user asks for health advice, trend analysis, risk assessment, or wellness recommendations.
Query health data from the Health Management System - steps, heart rate, HRV, SpO2, sleep, weight, blood pressure, workouts, diet, and checkin status. Use when the user asks about their health metrics, fitness data, or daily stats.
| name | health-data-summary |
| description | 综合查询健康数据 — Digital Health Twin 快照、Safety 告警、长期趋势、Orchestrator 多专家分析。当用户想了解自己的整体健康状况、趋势变化、安全风险时使用。 |
| version | 1.0.0 |
| metadata | {"agent":{"requires":{"env":["HEALTH_API_URL","HEALTH_API_TOKEN"],"bins":["curl"]},"primaryEnv":"HEALTH_API_TOKEN","emoji":"📊"}} |
综合查询用户的健康数据和 AI 分析结果。整合了 Digital Health Twin、Safety Guardian、Orchestrator 多专家系统。
Authorization: Bearer ${HEALTH_API_TOKEN}| 用户说 | 你应该调用的接口 |
|---|---|
| "我的健康状况怎么样" | Twin + Safety + Orchestrator |
| "我有什么安全风险" | Safety |
| "我过去半年的变化" | Personal Outcome |
| "分析我的 HRV 趋势" | Orchestrator |
| "我该注意什么" | Safety + Orchestrator |
curl -s -H "Authorization: Bearer ${HEALTH_API_TOKEN}" "${HEALTH_API_URL}/twin/me"
返回用户当前的完整健康状态(13 个维度):
physiological: HRV, 心率, 睡眠, 压力, 电量, 步数, SpO2body_composition: 体重, BMI, 体脂, TDEE, BMRlabs: 血压, 胆固醇, 血糖, 化验异常项cgm: CGM 血糖读数, TIR, 变异系数medication: 在服药物, 依从率supplement: 补剂打卡状态genetic: 基因变异(药物敏感/风险/保护)environment: 天气, AQI, PM2.5behavioral: 饮食, 饮水, 训练负荷, ACWRmental: 情绪, 精力, 压力 7 日均值chronic: 鼻炎今日状态goals: 当前目标freshness: 各数据源的新鲜度典型用法:先调 Twin 了解全貌,再根据具体问题深入分析。
curl -s -H "Authorization: Bearer ${HEALTH_API_TOKEN}" "${HEALTH_API_URL}/safety/me"
返回基于 47 条确定性规则的安全告警:
每条告警包含 severity(info/low/medium/high/critical)、action(建议动作)、data_citation(数据溯源)。
curl -s -X POST \
-H "Authorization: Bearer ${HEALTH_API_TOKEN}" \
-H "Content-Type: application/json" \
"${HEALTH_API_URL}/orchestrator/chat" \
-d '{"query": "综合分析我的健康状态并给出今日建议"}'
调度最多 10 个专家协作分析:
返回每个专家的结构化 finding + LLM 合成的自然语言回答。
curl -s -H "Authorization: Bearer ${HEALTH_API_TOKEN}" \
"${HEALTH_API_URL}/personal-outcome/me/timeline?range=6m&granularity=month"
6m / 1y / 2yweek / month返回:
points[]: 每月/每周的 HRV, 静息心率, 睡眠, 体重, 血压均值events[]: 干预事件(开始补剂/体检/里程碑)summary.metrics: 每个指标的 first→last 变化和趋势方向curl -s -X POST \
-H "Authorization: Bearer ${HEALTH_API_TOKEN}" \
-H "Content-Type: application/json" \
"${HEALTH_API_URL}/safety/explain" \
-d '{
"rule_id": "labs.liver_enzyme_pattern",
"data_citation": {"alt": {"value": 54}, "ast": {"value": 67}},
"message": "肝酶组合升高"
}'
对单条安全告警请求 LLM 个性化解读,结合用户真实健康数据给出具体建议。
curl -s -H "Authorization: Bearer ${HEALTH_API_TOKEN}" "${HEALTH_API_URL}/safety/rules"
返回全部 47 条规则的名称列表(透明度用)。
curl -s -H "Authorization: Bearer ${HEALTH_API_TOKEN}" "${HEALTH_API_URL}/safety/audit?limit=10"
查看最近的 agent 决策历史(谁做了什么分析、多少告警、用了多少毫秒)。
/twin/me → 获取全貌/safety/me → 获取安全风险/personal-outcome/me/timeline?range=6m → 获取趋势/orchestrator/chat query="我今天能高强度训练吗"