Skill Evaluator

Evaluate Clawdbot skills for quality, reliability, and publish-readiness using a multi-framework rubric (ISO 25010, OpenSSF, Shneiderman, agent-specific heuristics). Use when asked to review, audit, evaluate, score, or assess a skill before publishing, or when checking skill quality. Runs automated structural checks and guides manual assessment across 25 criteria.

This skill appears internally consistent and appropriate for reviewing other skills. Before running: 1) Inspect scripts/eval-skill.py yourself (it only reads files and parses YAML/AST; it does not spawn subprocesses or network calls). 2) Ensure you run it on the intended skill directory (don't point it at system or private repos containing secrets). 3) Install Python 3.6+ and PyYAML (pip install pyyaml) if you plan to run the automated checks. 4) Remember the automated script covers only structural/heuristic checks — manual judgment is required for many rubric items. 5) SKILL.md recommends an optional external tool (SkillLens via npm) — that is not required by this skill; treat external tool recommendations as separate dependencies and review them before use.

Type: OpenClaw Skill Name: skill-evaluator Version: 1.0.0 The OpenClaw skill 'skill-evaluator' is designed to assess the quality and security of other skills. Its `SKILL.md` provides clear, task-oriented instructions for the AI agent to execute a local Python script (`scripts/eval-skill.py`) on a specified skill directory. The Python script performs static analysis and content checks, including looking for hardcoded credentials and undocumented environment variables within the *target skill* being evaluated, which is a legitimate security function for an evaluator. There is no evidence of prompt injection, data exfiltration, malicious execution, or persistence mechanisms targeting the agent's environment or unrelated data.