Token导航 LogoToken导航TokenDH.com
效率external-serviceclawhub未标认证来源可访问clear审计提醒

ultrahuman-biodata-assistant超人类生物数据助理

Agent Skill

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围,避免把样本数据当全量事实;涉及敏感数据、导出文件或批量写回时,应先确认权限和脱敏边界。

总安装

7,663

周安装

310

GitHub Stars

公开资料未说明

下载量

2,406
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ultrahuman-biodata-assistant(超人类生物数据助理)
来源仓库:https://github.com/duzafizzl/ultrahuman-biodata-assistant
安装命令:
openclaw skills install ultrahuman-biodata-assistant
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install ultrahuman-biodata-assistant

简介

用于 Ultra Human MCP 生物数据查询。

  • 回答睡眠、血糖、代谢健康等问题。适用宿主包括 OpenClaw,接入前应确认版本、权限和运行环境要求。
  • 支持每日简报与环数据解读。ultrahuman-biodata-assistant 属于效率类 Skill,可作为该场景下的辅助能力补充。
  • 使用时需连接兼容的健康监测设备。
  • 依赖 MCP 服务的数据同步状态。

SKILL.md

name
ultrahuman-biodata-assistant
description
Use the Ultrahuman MCP to answer questions about sleep, recovery, readiness, daily metrics, morning brief, ring data, glucose, and metabolic health. Use this skill whenever the user asks about their Ultrahuman data, last night's sleep, recovery score, HRV, steps, glucose, metabolic score, readiness, or wants a "morning brief" or comparison over several days—even if they don't say "Ultrahuman" explicitly.
created
2026-03-16
updated
2026-03-16

Ultrahuman bio-data assistant

This skill guides you to use the Ultrahuman MCP tools to fetch and present daily bio metrics (sleep, recovery, HR, HRV, steps, glucose, metabolic score, etc.) in clear workflows. Use it whenever the user cares about sleep quality, recovery, readiness, or daily health metrics from their ring/CGM data.

Prerequisites

  • The ultrahuman_mcp MCP server must be available and configured (ULTRAHUMAN_TOKEN and ULTRAHUMAN_EMAIL in the environment, or user provides email for the request).
  • For date-based queries, resolve "today" / "yesterday" to the correct YYYY-MM-DD date (prefer the user's local date when possible, or state which date you used).

Workflows

1. Morning brief

User asks for a summary of their night or "how did I sleep" or "morning brief".

  1. Call ultrahuman_get_daily_metrics with the user's email (from context or env) and the relevant date (e.g. yesterday for "last night").
  2. From the response, surface: Sleep score, Recovery score, Resting HR, HRV, Steps (if available). Optionally total sleep time and sleep efficiency from sleep details.
  3. Reply with a short executive summary first, then a compact metrics section. Keep it scannable.

2. Recovery check

User asks "how was my recovery?" or "am I ready to train?".

  1. Call ultrahuman_get_daily_metrics for the date in question.
  2. Focus on: Recovery score, HRV, Sleep score, and Resting HR. If the API returns recovery_index or movement_index, include them.
  3. Give a one-line readiness takeaway (e.g. "Recovery looks good" / "Consider a lighter day") based on the numbers—descriptive only, not medical advice. For interpretation heuristics, see references/interpretation.md when needed.

3. Multi-day trend (e.g. last 3 or 7 days)

User asks to compare sleep or recovery over several days.

  1. Call ultrahuman_get_daily_metrics once per day (same email, date for each).
  2. Summarize in a short table or bullet list: date, sleep score, recovery score, and 1–2 other key metrics (e.g. HRV, steps).
  3. Add a brief trend line (e.g. "Sleep scores improved over the week") without over-interpreting.

Patterns

  • Dates: Always use YYYY-MM-DD. For "today" / "yesterday", compute the date; if timezone is ambiguous, state which date you used.
  • Email: Use the email from environment (ULTRAHUMAN_EMAIL) or from the user's message. If neither is available, ask once for the Ultrahuman account email.
  • Structure answers: Lead with a one- or two-sentence summary, then metrics (and optional short recommendations). Avoid raw JSON unless the user asked for data export.
  • Tone: Descriptive and supportive. Use phrases like "your ring data shows …", "according to your metrics …". Do not give medical diagnoses or treatment advice.
  • Missing data: If the API returns no data for a date, say so clearly and suggest checking the date or that data may still be processing.

Output format

Use this structure for morning briefs and recovery summaries:

  1. Summary – One or two sentences (sleep/recovery headline).
  2. Metrics – Key numbers (sleep score, recovery, HR, HRV, steps; add glucose/metabolic if present).
  3. Recommendations (optional) – Only generic, non-medical tips (e.g. "Earlier bedtime may help sleep consistency") when relevant.

References (load when needed)

  • references/metrics_glossary.md – Definitions and units for Sleep Score, Recovery Index, HRV, Metabolic Score, Time in Target, etc.
  • references/interpretation.md – Heuristics for "good" vs "pay attention" ranges (e.g. recovery, sleep efficiency, glucose variability). Use for context only; not medical guidance.

When the user asks what a metric means or how to read their numbers, load the glossary. When you need to judge "how good" a value is, use the interpretation reference.

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

93.04%
按下载量换算2,239

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

external-service

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills