How do I install the Skills Audit skill?

Run npx skillmds@latest add minghinmatthewlam/skills-audit in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Skills Audit safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Skills Audit?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Skills Audit free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Skills Audit?

minghinmatthewlam (@minghinmatthewlam) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Skills Audit by minghinmatthewlam — Agent Skill

Name: Skills Audit
Author: minghinmatthewlam

Skills Audit

Audit agent skills for triggering quality, correctness, context efficiency, redundancy, structure, failure guidance, and coverage gaps. Use when the user asks to review, improve, compare, simplify, or evaluate skills in global, repo-local, Claude, Codex, or custom skill paths.

minghinmatthewlam f8494c2 6 files · 18.2 KB Updated Sep 17, 2026

File contents

Audit Skills

Perform a read-only, evidence-backed audit of the requested skills. Default to decision-relevant findings, not an exhaustive ceremony.

Discover

Inspect the paths in scope, including when relevant:

~/.agents/skills/, ~/.claude/skills/, and ~/.claude/commands/;
repo-local .agents/skills/ and .claude/skills/;
custom paths named by the user.

Deduplicate synced or linked copies and identify the source of truth. Note agent system, folder resources, frontmatter, and broken links or scripts.

Evaluate

Read references/checklist.md and apply only relevant checks. Use references/categories.md when classification helps reveal mixed responsibilities or a repository-level coverage gap; do not force classification when it adds no decision value.

Prioritize:

incorrect, stale, conflicting, or unsafe instructions;
duplicated guidance likely to drift;
always-loaded detail better routed through references or scripts;
weak trigger descriptions;
missing real-world failure guidance;
rigid procedures that prevent capable agents from adapting;
missing skills only when repository evidence shows repeated value.

Numeric scores are optional comparison aids, not required output. Never penalize a short behavioral skill for lacking unnecessary resources.

Report

Use concisely. Include every material finding, ordered by impact, with exact file evidence and the smallest useful change. Group clean or low-priority skills rather than producing filler.

Distinguish observed evidence from inference. Do not impose a fixed findings count.

Apply Mode

Audit first. If the user asks for changes, edit only the approved scope, preserve useful non-obvious guidance through progressive disclosure, validate the changed skills, and report proof.

Gotchas

Do not audit installed mirrors as independent skills when they share one source.
Do not optimize for line count at the cost of deleting real failure knowledge.
Do not treat a large command reference as always-loaded context when it is properly routed.
Do not recommend generic new skills without repository evidence that they would recur.

---name: skills-auditdescription: Audit agent skills for triggering quality, correctness, context efficiency, redundancy, structure, failure guidance, and coverage gaps. Use when the user asks to review, improve, compare, simplify, or evaluate skills in global, repo-local, Claude, Codex, or custom skill paths.---# Audit SkillsPerform a read-only, evidence-backed audit of the requested skills. Default to decision-relevant findings, not an exhaustive ceremony.## DiscoverInspect the paths in scope, including when relevant:- `~/.agents/skills/`, `~/.claude/skills/`, and `~/.claude/commands/`;- repo-local `.agents/skills/` and `.claude/skills/`;- custom paths named by the user.Deduplicate synced or linked copies and identify the source of truth. Note agent system, folder resources, frontmatter, and broken links or scripts.## EvaluateRead `references/checklist.md` and apply only relevant checks. Use `references/categories.md` when classification helps reveal mixed responsibilities or a repository-level coverage gap; do not force classification when it adds no decision value.Prioritize:- incorrect, stale, conflicting, or unsafe instructions;- duplicated guidance likely to drift;- always-loaded detail better routed through references or scripts;- weak trigger descriptions;- missing real-world failure guidance;- rigid procedures that prevent capable agents from adapting;- missing skills only when repository evidence shows repeated value.Numeric scores are optional comparison aids, not required output. Never penalize a short behavioral skill for lacking unnecessary resources.## ReportUse `concisely`. Include every material finding, ordered by impact, with exact file evidence and the smallest useful change. Group clean or low-priority skills rather than producing filler.Distinguish observed evidence from inference. Do not impose a fixed findings count.## Apply ModeAudit first. If the user asks for changes, edit only the approved scope, preserve useful non-obvious guidance through progressive disclosure, validate the changed skills, and report proof.## Gotchas- Do not audit installed mirrors as independent skills when they share one source.- Do not optimize for line count at the cost of deleting real failure knowledge.- Do not treat a large command reference as always-loaded context when it is properly routed.- Do not recommend generic new skills without repository evidence that they would recur.

Frequently asked questions