agentleFS
JuneYaoooJuneYaooo/mediwise-health-suite/health-monitor/SKILL.md

health-monitor

Skill29 starsChanged 4 months agoMITView on GitHub

智能健康监测与告警。基于阈值检测、趋势分析和多级告警系统, 按需或在设备同步后检查家庭成员的已记录健康指标。支持全家健康 dashboard 一屏总览。 Intelligent health monitoring and alerting. Uses threshold detection, trend analysis, and multi-level alert records to check recorded family health metrics on demand or after wearable imports. Supports a family dashboard. 关键词:健康监测、异常告警、指标预警、趋势分析、健康报告、心率异常、血压异常、血氧低、告警管理、全家概览、健康dashboard。

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. WhispersOfJ/arrfleet-toolkit★ 1same name
    2. Presidio-Federal/ai-studio-netops★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository6 other files it gives its agents.

The file

Files
SKILL.md

MediWise · 健康记录提醒 Skill

按已配置阈值检查健康指标并生成多级记录提醒,支持全家 dashboard 一屏总览。所有级别都只表示规则优先级,不是病情严重程度或临床判断;本 Skill 不提供诊断、治疗或用药指导。

告警级别

级别含义处理方式
info信息记录仅记录
warning普通提醒创建普通优先级提醒记录
urgent高优先级创建高优先级提醒记录
emergency最高优先级创建最高优先级提醒记录

默认规则阈值

这些数值是可修改的内置提醒规则,不代表诊断标准或医疗建议。用户可根据自己的记录需求调整或关闭;如需医学阈值,应由专业医疗人员确定。

指标warningurgentemergency
心率(高)>100 bpm>120 bpm>150 bpm
心率(低)<55 bpm<45 bpm<35 bpm
血氧(低)<95%<90%<85%
收缩压(高)>140 mmHg>160 mmHg>180 mmHg
舒张压(高)>90 mmHg>100 mmHg>110 mmHg
体温(高)>37.3°C>38.5°C>39.5°C
血糖空腹(高)>6.1 mmol/L>7.8 mmol/L>11.1 mmol/L

支持按年龄自动调整,支持用户自定义覆盖。

核心工作流

当前公开版本只用于个人本地档案。身份隔离由安装时的个人模式和 action 适配层处理,不向普通用户暴露或索取 owner_id。

0. 全家健康 Dashboard(首选入口)

用户说「看看全家健康」「今天家人状态怎样」「健康概览」时,优先调用此接口。 返回所有成员的风险级别、未解决告警数、最新关键指标和趋势警告。

# 全家健康一屏总览
python3 {baseDir}/scripts/dashboard.py show

1. 阈值管理

# 查看阈值配置(含默认+自定义)
python3 {baseDir}/scripts/threshold.py list --member-id <id>

# 自定义阈值
python3 {baseDir}/scripts/threshold.py set --member-id <id> --type heart_rate --level warning --direction above --value 110

# 恢复默认
python3 {baseDir}/scripts/threshold.py reset --member-id <id> --type heart_rate

2. 异常检测

# 检查单个成员
python3 {baseDir}/scripts/check.py run --member-id <id>

# 检查所有成员
python3 {baseDir}/scripts/check.py run-all

# 检查最近指定时间窗口
python3 {baseDir}/scripts/check.py run --member-id <id> --window 24h

3. 趋势分析

# 单指标趋势
python3 {baseDir}/scripts/trend.py analyze --member-id <id> --type heart_rate --days 7

# 全指标摘要
python3 {baseDir}/scripts/trend.py report --member-id <id>

4. 告警管理

# 查看未解决告警
python3 {baseDir}/scripts/alert.py list --member-id <id>

# 按级别筛选
python3 {baseDir}/scripts/alert.py list --member-id <id> --level urgent

# 标记已解决
python3 {baseDir}/scripts/alert.py resolve --alert-id <id>

# 告警历史
python3 {baseDir}/scripts/alert.py history --member-id <id> --limit 20

检测触发与提醒边界

  • wearable-sync 成功导入数据后可以自动触发一次检查。
  • 用户也可以主动请求检查、查看 dashboard 或查询提醒历史。
  • health-monitor 只写入本地告警和 reminder 记录,不包含后台守护进程、IM Bot、Webhook、短信或电话推送能力。
  • 如当前个人 Agent 自身提供任务调度或通知能力,应使用该平台受支持的配置方式,并保持同一数据目录仅供当前本地用户使用;必须完成任务注册、持久化和一次触发测试后,才能告诉用户会到点主动通知。不要在 Skill 文档中拼接 shell、Webhook 或账号标识。

反模式

  • 不要把优先级写成病情分级 — warning/urgent/emergency 只是项目内部记录优先级
  • 不要声称已发送外部通知 — 项目只创建本地记录,除非当前 Agent 平台确实完成了通知动作
  • 趋势分析需要足够数据 — 少于 3 天数据时趋势不可靠

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.