返回顶部
h

health-training-frontdoor

Narrow first-class front door for live Fitbit/training retrieval via stable JSON actions.

作者: admin | 来源: ClawHub
源自
ClawHub
版本
V 1.0.0
安全检测
已通过
64
下载量
0
收藏
概述
安装方式
版本历史

health-training-frontdoor

# Health/Training Front Door Use this when OpenClaw needs **live Fitbit/health/training data** in a stable, low-ambiguity way. This is a thin, typed front door over the canonical Fitbit connector tooling. ## Why this exists `fitbit_tools.py` is the canonical operational backend, but it still requires low-level CLI composition. This front door provides a narrow action contract so agents can call one stable interface instead of assembling raw shell commands every time. ## Contract Run: - `node skills/health-training-frontdoor/scripts/request.js '{...json...}'` Input JSON: ```json { "action": "latest_recovery" } ``` Supported actions: - `auth_status` - `latest_recovery` - `quality_flags` - `training_status` - `training_window` - `unified_latest` Optional fields: - `days` (integer) - `ensureFresh` (boolean) - `source` (for `unified_latest`, default `best`) ## Default behavior by action - `latest_recovery`: fetches latest days of `hrv_rmssd,resting_hr,sleep_minutes,sleep_score,data_quality`; defaults `days=3`, `ensureFresh=true` - `quality_flags`: defaults `days=7` - `training_status`: defaults `days=14`, `ensureFresh=true` - `training_window`: defaults `days=14`, `ensureFresh=true` - `unified_latest`: defaults `days=14`, `source=best` ## Notes - Output is compact JSON. - This surface is read-only. - Interpretation/coaching remains outside this skill. ## Training Programming Reference All programming decisions must be grounded in **Practical Programming for Strength Training** (Rippetoe & Baker, 3rd Ed.). **Always load before giving any programming advice:** 1. `reference/practical-programming/INDEX.md` — who Joao is, relevant chapters, reading guide 2. `memory/training-continuity.md` — current lifts, recent sessions, health signals For any programming question, read the relevant sections of `reference/practical-programming/book.md` directly. The book is the authority. ## Backend mapping This front door maps directly to: - `fitbit-connector/scripts/fitbit_tools.py` Do not use this to bypass auth or write-capable operations.

标签

skill ai

通过对话安装

该技能支持在以下平台通过对话安装:

OpenClaw WorkBuddy QClaw Kimi Claude

方式一:安装 SkillHub 和技能

帮我安装 SkillHub 和 health-training-frontdoor-1775942739 技能

方式二:设置 SkillHub 为优先技能安装源

设置 SkillHub 为我的优先技能安装源,然后帮我安装 health-training-frontdoor-1775942739 技能

通过命令行安装

skillhub install health-training-frontdoor-1775942739

下载 Zip 包

⬇ 下载 health-training-frontdoor v1.0.0

文件大小: 3.18 KB | 发布时间: 2026-4-12 10:11

v1.0.0 最新 2026-4-12 10:11
health-training-frontdoor v1.0.0

- Introduced a typed front door for live Fitbit/health/training data retrieval using stable JSON actions.
- Provides a simplified, read-only API over the canonical Fitbit connector, reducing the need for raw CLI command assembly.
- Supports stable actions: `auth_status`, `latest_recovery`, `quality_flags`, `training_status`, `training_window`, and `unified_latest` with clear default behaviors and optional fields.
- Ensures all programming advice is grounded in "Practical Programming for Strength Training" and references user-specific context before making recommendations.
- Guarantees compact JSON outputs and direct mapping to backend tools, without bypassing authentication or allowing data writes.

Archiver·手机版·闲社网·闲社论坛·羊毛社区· 多链控股集团有限公司 · 苏ICP备2025199260号-1

Powered by Discuz! X5.0   © 2024-2025 闲社网·线报更新论坛·羊毛分享社区·http://xianshe.com

p2p_official_large
返回顶部