← ClaudeAtlas

skill-quality-auditorlisted

Evaluate, score, and remediate agent skill collections using a 9-dimension quality framework (Knowledge Delta, Mindset, Anti-Patterns, Specification Compliance, Progressive Disclosure, Freedom Calibration, Pattern Recognition, Practical Usability, Eval Validation). Performs duplication detection, generates remediation plans with T-shirt sizing, enforces CI quality gates, validates artifact conventions, tracks score trends, and provides a native eval runner with LLM-as-judge (BYOK, provider-agnostic). Use when evaluating skill quality, auditing SKILL.md files, scoring agent skills, generating remediation plans, detecting duplicate skills, validating skill format, enforcing quality gates, optimizing for A-grade publication, comparing audit baselines, batch skill assessments, or checking skill registry compliance. Triggers: 'check my skills', 'skill audit', 'improve my SKILL.md', 'quality check', 'A-grade scoring', 'quality gates', 'eval validation', 'audit all skills', 'remediation plan', 'skill judge', 'dimens
pantheon-org/skill-quality-auditor · ★ 2 · AI & Automation · score 68
Install: claude install-skill pantheon-org/skill-quality-auditor
# Skill Quality Auditor Evaluate, maintain, and improve skill quality with 9-dimension framework scoring. ## Quick Start ```bash # Single skill skill-auditor evaluate <domain>/<skill-name> --json --store # Batch with grade gate skill-auditor batch <skill1> <skill2> --fail-below B --store ``` ## When to Use - Evaluate skills before merge or publication using 9-dimension scoring - Generate remediation plans, detect duplication (High at 20%, Critical at 35%), or enforce CI quality gates - Validate eval scenario coverage and artifact conventions ## When Not to Use - Write the skill first — do not audit an unfinished draft - Avoid using this as a substitute for peer review of logic or domain accuracy ## Prerequisites - MUST have the skill directory with `SKILL.md` and at least one eval scenario. - MUST run `--store` at least once before `remediate` or `trend` can produce output. ## Workflow 1. Run `skill-auditor evaluate <skill> --json --store` 2. Check artifacts and eval coverage using deterministic criteria 3. Generate a remediation plan with T-shirt sizing and score delta estimates 4. Re-run the auditor to verify improvement; if below target, focus on the lowest-scoring dimension ## Anti-Patterns **NEVER** skip baseline comparison in recurring audits. **WHY:** Score regressions go undetected without a prior stored audit. **BAD:** `skill-auditor evaluate my-skill` with no prior `--store` run. **GOOD:** `skill-auditor evaluate my-skill --store` after a prior stored