skill-refiner

Audit and fix all skills in the workspace for compliance with skill-creator requirements. Use when asked to "refine skills", "audit skills", "check skill qua...

This package is functionally what it says (it discovers and audits SKILL.md files), but its runtime instructions recommend destructive fixes (deleting README.md, moving directories, renaming skills) that could remove or relocate many user files. Before installing or allowing autonomous invocation: 1) Inspect scripts locally and run them yourself in read-only mode (bash scripts/find_skills.sh and python3 scripts/audit_skill.py) to review the audit output. 2) Make a full backup of your workspace. 3) Do not grant the skill permission to run shell commands autonomously unless you trust it; prefer manual application of fixes after reviewing each change. 4) If you want automation, consider forking the skill and removing or changing the destructive 'fix' steps (or add a dry-run flag and explicit user confirmation for any delete/move operations).

Type: OpenClaw Skill Name: skill-refiner Version: 1.0.0 The skill-refiner bundle is designed to audit and fix OpenClaw skills for compliance. While its core scripts (`audit_skill.py`, `find_skills.sh`) are purely analytical, the `SKILL.md` contains explicit instructions for the AI agent to perform high-risk file system operations, including deleting files (e.g., `README.md`, `CHANGELOG.md`), moving skill directories to a new location (`~/.openclaw/workspace/skills/`), and renaming directories. These actions, though aligned with the stated purpose of 'fixing' skills, represent significant capabilities for modifying the workspace. There is no clear evidence of malicious intent (e.g., data exfiltration, backdoor installation), but the broad file system access and modification instructions make it a powerful administrative tool that could lead to unintended data loss or system changes if misused or if the agent's interpretation is flawed, classifying it as suspicious due to these risky capabilities.