Whoop Guru

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

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.

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.