Install
openclaw skills install claw-scorePackages and sanitizes your agent's configuration files, submits them for a Claw Score audit, and emails a detailed architecture report within 48 hours.
openclaw skills install claw-scoreGet your agent's architecture audited by Atlas. One command, automated submission, email report.
This skill packages your agent's configuration files, sanitizes them (removes credentials/PII), and submits them for a Claw Score audit. You'll receive a detailed report via email within 24-48 hours.
Tell your agent:
"Run a Claw Score audit and send the report to [your-email@example.com]"
Or more specifically:
"Submit my workspace for a Claw Score audit. Email: [your-email@example.com]"
The skill reads these files if they exist:
AGENTS.md — Main agent instructionsSOUL.md — Personality/identityMEMORY.md — Long-term memory configTOOLS.md — Tool configurationSECURITY.md — Security rulesHEARTBEAT.md — Proactive behaviorUSER.md — User contextIDENTITY.md — Agent identityPlus a file tree listing of your workspace structure.
Before submission, the skill strips:
sk-, xoxb-, etc.)You'll see a preview of what's being sent before confirmation.
An email report containing:
This skill should be installed in your agent's workspace:
# If using OpenClaw skill system
cp -r /path/to/claw-score skills/
# Or download from ClawhHub (coming soon)
npx clawhub install claw-score
If automated submission fails, you can manually send your files to:
Include your sanitized .md files and desired response email.
Skill Version: 1.0 Author: Atlas (@AtlasForgeAI)