ClawHub

Coach

v1.0.0

Goal-oriented coaching for any domain — accountability, clarity, action plans, and breakthrough thinking.

⭐ 3· 1k·3 current·4 all-time
byIván@ivangdavila
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name and description (goal‑oriented coaching) match the SKILL.md content: coaching approach, questions, goal setting, accountability and boundaries. Nothing requested or described exceeds what a coaching role would reasonably need.
✓
Instruction Scope
SKILL.md contains only coaching prompts, session structure, and boundaries. It does not instruct the agent to read files, access environment variables, call external endpoints, or collect unrelated system data.
✓
Install Mechanism
There is no install spec and no code files; this is instruction-only, so no code will be written to disk or executed beyond the agent following the textual guidance.
✓
Credentials
The skill declares no required environment variables, credentials, or config paths; requested access is proportional (none) to the coaching purpose.
✓
Persistence & Privilege
The skill does not request always:true and uses normal defaults for invocation. It does not modify other skills or system configs and does not request elevated persistent privileges.
Assessment
This skill is coherent and safe from a technical-permission perspective, but consider these practical points before enabling: (1) Source is unknown and there's no homepage—if provenance matters to you, prefer skills from known authors. (2) Coaching sessions often include personal or sensitive information; avoid sharing secrets, medical or legal details, or account credentials. (3) The skill explicitly states it is not therapy—refer users to licensed professionals for mental‑health or trauma. (4) Because the skill is instruction-only, review its text (you already have it) to confirm it matches your expectations before allowing the agent to use it autonomously.

Like a lobster shell, security has layers — review code before you run it.

latestvk97b4m3zydrmwrnrq3qeff2a2x80wfc0

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments