skill-evaluatorlisted

Audit an existing SKILL.md for rule adherence — does the text actually land when Claude runs it? Use when the user wants a behavioral review of a shipped skill. Outputs: failure classification by fix layer (skill text / rubric / brief / fixture) and targeted rule-text diffs. Trigger ON: "audit this skill", "stress-test my skill", "does this skill actually work", "find gaps in this skill", "what's broken in this skill", "validate rule adherence", "review this skill end-to-end", or uploading a SKILL.md for behavior review. Do NOT trigger on: "build a skill", "create a skill from scratch", "benchmark this skill", "evaluate skill quality", "compare versions", "optimize trigger phrases", or "measure variance" — those are all `skill-creator`. If the request mixes both, start with `skill-creator` and chain here. Hard boundary: `skill-creator` builds, benchmarks, measures variance, and optimizes triggering; this skill does NONE of those — it asks "does the text land?".
sorawit-w/agent-skills · ★ 1 · AI & Automation · score 77

Install: claude install-skill sorawit-w/agent-skills

# Skill Evaluator Audit a target skill to see whether its instructions actually land when Claude runs it. This skill does NOT benchmark skill-vs-no-skill (that's `skill-creator`'s job). This skill checks rule adherence under realistic prompts, classifies where failures come from, and proposes targeted fixes. ## Scope **Good fit — v1 supports:** - Workflow skills (sequences of steps, shutdown rituals, review passes) - Rule-shaped skills (policies, conventions, constraints, checklists) - Guideline skills (style guides, voice guides, design rules) **Out of scope for v1 (say so explicitly if asked):** - Creative-synthesis skills (brand voice, canvas design, algorithmic art) — rule-adherence framing does not apply cleanly to "is this output beautiful" - Skills whose value is measured by end-user outcomes over time (engagement, retention) If the user asks to evaluate a creative-synthesis skill, say the harness is not validated for that skill type and ask if they want to proceed anyway with a best-effort run. Do not silently pretend it works. ## Differentiation from skill-creator | skill-creator | skill-evaluator | |--|--| | Authors new skills | Audits existing skills | | Benchmarks skill-vs-baseline (A/B) | Measures rule adherence under realistic prompts | | Asks "does the skill help?" | Asks "does the skill's text actually land?" | | Outputs: a skill | Outputs: findings + rule-text diffs | You can chain them: evaluator finds a gap → creator's conventions guide the rule-t