skill-auditor
Audit an Agent Skill or a repository of skills for trigger quality, scope overlap, instruction conflicts, progressive-disclosure cost, broken references/dependencies, eval blind spots, false-green paths, semantic-version and public-contract compatibility, host-support overclaims, package hygiene, supply-chain risks, migration/deprecation gaps, and drift between registry, docs, tests, and shipped archives. Use when the user asks to audit, review, roast, harden, compare, or quality-check a skill or skill library itself. Do not use to create/edit the skill (use skill-creator), to empirically benchmark model behavior with-vs-without it (use skill-evaluator), to audit ordinary software (use repo-roaster), or to issue a production release verdict.
Pinned to revision 6626bb65beb0, so it is the text this page describes rather than whatever the author pushed since.
Files
- skills/skill-auditor/SKILL.md
- skills/skill-auditor/CHANGELOG.md
- skills/skill-auditor/LICENSE
- skills/skill-auditor/README.md
- skills/skill-auditor/VERSION
- skills/skill-auditor/agents/openai.yaml
- skills/skill-auditor/assets/icon.svg
- skills/skill-auditor/evals/cases.json
- skills/skill-auditor/evals/real-host.json
- skills/skill-auditor/references/audit-model.md
- skills/skill-auditor/references/eval-and-portability.md
- skills/skill-auditor/references/evaluation.md
- skills/skill-auditor/references/migrations-and-regression-bisection.md
- skills/skill-auditor/references/output-contract.md
- skills/skill-auditor/references/routing-and-overlap.md
- skills/skill-auditor/references/untrusted-input.md
- skills/skill-auditor/references/version-and-contract-compatibility.md
- skills/skill-auditor/scripts/kernel.py
- skills/skill-auditor/scripts/run_evals.py
Every link opens the file at its source, pinned to the revision this page describes.