ClawCoach Core
ReviewAudited by ClawScan on May 10, 2026.
Overview
The skill’s coaching purpose is coherent, but it handles personal health and nutrition logs while making a strong “no data leaves your machine” privacy claim that conflicts with its required Anthropic LLM backend key.
Install only if you are comfortable with a health-coaching skill storing your profile and meal logs under ~/.clawcoach/. Before entering sensitive health details or food photos, verify whether your data is sent to Anthropic/OpenClaw’s LLM backend and review the companion setup and food-analysis skills.
Findings (4)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A user may believe their diet and profile data never leaves their computer, even though the coaching response may involve an external model provider.
The skill reads personal health and nutrition data for coaching, but the privacy claim does not clearly reconcile that data use with an Anthropic-backed LLM service.
No data is sent to any external service. No data leaves your machine. The ANTHROPIC_API_KEY is used by OpenClaw's LLM backend for generating coaching responses
Clarify the actual model/provider data flow and avoid using the skill for sensitive health information unless the user is comfortable with how prompts are processed.
Private health and eating-history information may remain on the device and be reused in later coaching sessions.
The skill persistently stores and later reuses personal profile and nutrition data across interactions.
`~/.clawcoach/profile.json` — your name, age, calorie targets, dietary preferences, coach persona choice - `~/.clawcoach/food-log.json` — your logged meals and macros
Use the skill only if you are comfortable storing this data locally; periodically review or delete ~/.clawcoach/ if you no longer want the information retained.
Food photos, food descriptions, or setup details may be handled by other skills whose permissions and data handling were not reviewed here.
The core skill relies on other named skills for onboarding and food/photo analysis, but those companion skills are not included in the reviewed artifacts.
If it does NOT exist: activate the `clawcoach-setup` skill... Delegate to the `clawcoach-food` skill for photo analysis.
Review and install only trusted companion skills, especially any skill that analyzes food photos or writes to the same profile and log files.
The user must provide or have access to an Anthropic API credential for the skill’s LLM-backed coaching environment.
The skill declares a required provider API key, although the artifacts show no code that directly reads or transmits the key.
metadata:
openclaw: {"requires": {"env": ["ANTHROPIC_API_KEY"]}}Keep the API key scoped and protected, and verify the OpenClaw/Anthropic data handling policy before using the skill with sensitive personal information.