← 返回 Skills 市场
effeceee

Whoop Guru

作者 effeceee · GitHub ↗ · v8.4.12 · MIT-0
cross-platform ✓ 安全检测通过
314
总下载
0
收藏
1
当前安装
45
版本数
在 OpenClaw 中安装
/install whoop-guru
功能描述
WHOOP AI Fitness Coach - WHOOP手环数据获取、健康分析、恢复预测、AI教练、个性化训练计划
安全使用建议
This skill appears to be what it says: a WHOOP data integrator + LLM coach. Before installing or running it: 1) Review scripts (scripts/*.py, *.sh) yourself—they run subprocesses and read/write local files. 2) Be aware that your WHOOP health data and any tokens will be stored on disk (~/.clawdbot/whoop-tokens.json and data/config/llm_config.json) and will be sent to whatever LLM endpoint you configure; only use trusted LLM services if you are comfortable sharing health data. 3) Use dedicated user account or sandbox if you want isolation; inspect and control any crontab entries before adding them. 4) Remove or revoke WHOOP tokens and delete local config files if you uninstall the skill. 5) If you need a deeper review, ask for the specific files that interact with network endpoints (lib/ whoop-fetcher, lib/llm.py, scripts/whoop_auth.py, scripts/whoop_data.py) so they can be audited for unexpected external endpoints or hardcoded hosts.
功能分析
Type: OpenClaw Skill Name: whoop-guru Version: 8.4.12 The WHOOP Guru skill is a comprehensive health management system that integrates the WHOOP API with LLM-driven coaching and ML-based recovery predictions. It handles sensitive credentials, including OAuth tokens and LLM API keys, but stores them in appropriate local directories (~/.clawdbot/ and data/config/) and uses them only for authorized communication with official endpoints (e.g., api.prod.whoop.com). The extensive use of shell scripts and subprocess calls in files like lib/whoop-fetcher.sh and lib/checkin_auto.py is aligned with the system's complex architecture and lacks any indicators of malicious intent or unauthorized data exfiltration.
能力标签
requires-oauth-token
能力评估
Purpose & Capability
Name/description match what is implemented: many scripts and Python modules fetch WHOOP data, process it, generate reports/charts, and call an LLM-based coach. Required binaries/packages and OAuth token storage locations are consistent with the described functionality.
Instruction Scope
SKILL.md instructs running local scripts, an OAuth login flow, and storing tokens at ~/.clawdbot/whoop-tokens.json and data/config/llm_config.json. The runtime instructions do not request unrelated system files or unrelated credentials, but they do send user WHOOP health data to whichever LLM endpoint the user configures—this is expected for an LLM coach but important to note because it transmits sensitive health data to an external service selected by the user.
Install Mechanism
No install spec; code is provided as files and is instruction-driven. There are no remote download/install steps in the manifest, so nothing in the registry would write arbitrary external code during install.
Credentials
No surprising environment variables or unrelated credentials are required. WHOOP OAuth credentials (via CLI args or optional ~/.clawdbot/whoop-credentials.env) and an optional LLM API key are proportional to the skill's purpose. The skill persists OAuth tokens and LLM keys locally, which is expected but contains sensitive data that should be protected.
Persistence & Privilege
always is false and the skill does not request forced/always-on inclusion. It stores tokens/config under user paths (~/.clawdbot and data/config) and schedules are left to the user (crontab examples). It does not request or modify other skills' configs.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install whoop-guru
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /whoop-guru 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v8.4.12
v8.4.12: revert metadata to 8.4.7 clean state
v8.4.11
whoop-guru v8.4.11 - 增加环境变量声明:metadata中明确WHOOP_CLIENT_ID为primaryEnv,其余必需环境变量在env数组中声明。 - 新增数据日志模板文件:`data/logs/checkins_default.json` 和 `data/logs/running_default.json`。 - 更新和调整健康建议数据文件(`data/processed/health_advisor.json`)。 - 文档(CLAWHUB.md、SKILL.md)同步更新以反映配置要求和最新结构说明。
v8.4.10
whoop-guru v8.4.10 - 移除冗余/历史打卡日志和部分模拟目标数据,精简 data/logs/ 与 data/profiles/ 下文件 - 更新、维护文档 (SKILL.md, CLAWHUB.md, _meta.json) 保持信息同步和简洁 - 精简 data/processed/health_advisor.json 数据文件 - 无功能性变更,主要聚焦于数据、文档和结构优化
v8.4.9
修复ClawHub安全审查问题:credentials声明+硬编码路径
v8.4.8
v8.4.8 重点修复推送延迟与数据同步问题 - 推送脚本(morning/evening/checkin)执行前自动刷新 WHOOP 数据,保持推送为最新实时数据 - 新增:推送内容直接读取 whoop_data.py summary 生成的最新数据(latest.json) - 修复:recovery.start 字段为空导致 date=None 问题(改为使用 created_at 字段) - 修复:hrv 或 skin_temp 结果为 None 时 round() 报错 - 修复:push-cron 任务 30s 超时,openclaw.json 增加 agents.defaults.timeoutSeconds=120 - 新增测试数据和用户目标文件,增强数据覆盖
v8.4.7
v8.4.7: 新增自动打卡检测(whooop workouts api);增强反馈学习系统;统一北京时间;65测试100%通过
v8.4.6
v8.4.6: 修复测试套件7个失败;修复中文日期/时间解析;新增quick_checkin;重写enhanced_reports;更新TOOLS.md;全部41测试通过
v8.4.5
v8.4.5 introduces marathon-focused features and enhanced tracking: - 新增马拉松训练目标管理(GoalsManager扩展) - 跑步打卡追踪功能(ProgressTracker扩展) - 集成马拉松训练分析器(MarathonAnalyzer)和指令处理(MarathonCommands) - 每日报告现支持马拉松专属内容 - 初始化32项单元测试,提高稳定性
v8.3.7
v8.3.7 is a minor update. - Updated meta information in _meta.json to reflect latest release. - No feature or documentation changes in code or SKILL.md.
v8.3.6
- 移除对 WHOOP_REFRSH_TOKEN 环境变量的支持,凭证配置方式澄清为仅 CLI 参数或配置文件,不再通过环境变量设置。 - 修订环境变量说明,删除 WHOOP_CLIENT_ID 和 WHOOP_CLIENT_SECRET,明确它们仅通过 CLI 或 credentials 文件设置。 - 文档中进一步统一和澄清凭证(whoop-tokens.json 和 whoop-credentials.env)相关内容,避免混淆。
v8.3.5
- 统一和修正 WHOOP OAuth 凭证的环境变量说明,明确可通过环境变量或 CLI 参数配置 - 在环境变量表中新增 WHOOP_CLIENT_ID、WHOOP_CLIENT_SECRET、WHOOP_REFRESH_TOKEN 等项 - 修改凭证配置说明,强调支持环境变量与参数两种方式 - 文档其余内容结构未改动
v8.3.4
- 修复:WHOOP OAuth 凭证文件说明,支持 whoop-tokens.json 和 whoop-credentials.env 两种格式 - 文档:在配置说明部分增加 whoop-credentials.env 手动配置示例 - 其他说明保持一致,无功能变化
v8.3.2
v8.3.2 is a documentation and metadata update. - 更新 CLAWHUB.md 和 _meta.json 内容 - 无功能、接口或实现更改 - 用于修正和同步项目文档与技能元数据
v8.3.1
Version 8.3.1 - Documentation update: Version bumped to v8.3.0 in SKILL.md introduction. - No functional or code changes; updates limited to documentation files (CLAWHUB.md, SKILL.md).
v8.3.0
Version 8.3.0 - 重要变更:精简环境变量与配置方式,澄清 OAuth 配置方式。 - 移除 WHOOP OAuth 环境变量(Client ID/Secret),强调通过 CLI 参数设置。 - 明确 WHOOP OAuth 凭证存储/加载机制,相关说明更新至配置章节。 - 保持所有功能模块和调用方式不变,其余内容无实质性更改。
v8.2.9
环境变量支持已添加,便于自定义 Skill 运行目录和存储。 - 新增环境变量:WHOOP_CLIENT_ID、WHOOP_CLIENT_SECRET 等,灵活指定存储与配置路径 - 文档增加“环境变量”说明表,列出可选与必需变量 - 原有功能、配置及推送机制未变
v8.2.8
WHOOP Guru v8.2.8 - 新增:系统要求章节,详细说明依赖的 Python 包及命令 - 新增:推送机制说明,明确需要在 OpenClaw 配置 cron 定时任务 - 修复:澄清数据流向和本地隐私存储位置说明 - 清理:移除无用的打卡推送日志文件 (checkin_push.json)
v8.2.7
whoop-guru v8.2.7 - 新增 data/logs/checkin_push.json 用于打卡推送日志记录 - 更新配置说明,进一步明确数据流向与本地凭证存储策略,强调安全性 - 优化文档表述和术语,使说明对普通用户和技术用户更直观 - 轻微调整 CLAWHUB.md 和 _meta.json 保持内容一致性
v8.2.6
v8.2.6 主要改进配置一致性与文档规范 - 统一 SKILL.md 和 _meta.json 的配置说明 - 新增 homepage 字段 - 移除 WHOOP_REFRESH_TOKEN(OAuth 自动获取) - 所有凭证说明文本实现一致化
v8.2.5
### v8.2.5 - 更新了 CLAWHUB.md - 更新了 _meta.json - 无新功能或重大修复,仅文档和元数据维护
元数据
Slug whoop-guru
版本 8.4.12
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 45
常见问题

Whoop Guru 是什么?

WHOOP AI Fitness Coach - WHOOP手环数据获取、健康分析、恢复预测、AI教练、个性化训练计划. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 314 次。

如何安装 Whoop Guru?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install whoop-guru」即可一键安装,无需额外配置。

Whoop Guru 是免费的吗?

是的,Whoop Guru 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

Whoop Guru 支持哪些平台?

Whoop Guru 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 Whoop Guru?

由 effeceee(@effeceee)开发并维护,当前版本 v8.4.12。

💬 留言讨论