agentleFS
Sign inStart free
m2ai-mcp-serversm2ai-mcp-servers/claude-skills/skills/skill-audit/SKILL.md

skill-audit

Skill0 starsChanged 7 months agoMITView on GitHub

Audit your Claude Code skills directory, CLAUDE.md, and recent session patterns to surface candidates for new skills -- gaps, redundancies, and formalization opportunities.

58 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use root-cause, write-a-skill and 8 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Ingramradical235Skill

    root-cause

    Structured root cause analysis using WHERE (MECE decomposition) then WHY (causal structure diagrams) pipeline. Includes coin-flip detection, logical-leap detection, and vicious cycle intervention. Use when buffer enters YELLOW/RED, when metrics stall, or when Actions execute but don't produce results.

    Also in 3 projects that use this

  • simo97Skill

    write-a-skill

    Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    reflect

    Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.

    Also in 5 projects that use this

  • sunnyclinches44Skill

    explain

    Explains code using real-world analogies and ASCII diagrams

    Also in 4 projects that use this

  • eherrerosjSkill

    humanize

    Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive 'Signs of AI writing' guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases. Triggers on: 'humanize', 'make this sound human', 'remove AI writing', 'de-AI', 'sound more natural', 'less robotic', 'too AI-sounding', or when reviewing text that reads like AI output.

    Also in 3 projects that use this

  • MicrosoftSkill

    report

    Turn an exploration (threads, findings, charts) into a single Markdown report — note, blog post, executive summary, KPI dashboard, slide brief, or multi-section analytical report, with embedded charts.

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 52 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use when the user says "audit my skills", "what skills am I missing", "skill audit", "skill backlog", "what should be a skill", or asks …

    line 12
  2. Distinctive:

    Do NOT auto-create skills.

    line 71

“Common” is measured: kept by at least 6 in 10 of the 52 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Skill Backlog Audit

Scans your existing skill library, CLAUDE.md instructions, and workflow patterns to identify what should be formalized into a skill but hasn't been yet.

Trigger

Use when the user says "audit my skills", "what skills am I missing", "skill audit", "skill backlog", "what should be a skill", or asks about gaps in their skill library.

Phase 1: Inventory

Scan these sources and build a full inventory:

  1. Skills directory (~/.claude/skills/) -- list every skill, its description, trigger patterns, and category
  2. Plugins (~/.claude/plugins/installed_plugins.json) -- list installed plugins and their capabilities
  3. CLAUDE.md files -- read ~/.claude/CLAUDE.md and the current project's CLAUDE.md for repeated instruction patterns that could be skills
  4. Hooks (~/.claude/settings.json, ~/.claude/settings.local.json) -- check for hook-based behaviors that might work better as skills

Build a table:

#Skill/PluginCategoryTrigger CoverageLast Modified

Phase 2: Gap Analysis

Analyze the inventory for:

Missing Skills

  • Repeated multi-step workflows in CLAUDE.md that aren't skills yet
  • Patterns the user does frequently (check conversation history if available) that have no skill
  • Common Claude Code operations with no skill coverage (deployment, testing, refactoring patterns)

Redundant Skills

  • Skills with overlapping trigger patterns (risk of wrong skill firing)
  • Skills that cover the same domain from different angles (candidates for merging)

Underspecified Skills

  • Skills missing description fields (won't trigger reliably for agents)
  • Skills with vague triggers ("use when needed")
  • Skills without verification/output phases

Phase 3: Recommendations

Produce a ranked list of recommendations:

PRIORITY | ACTION     | TARGET              | RATIONALE
---------|------------|---------------------|----------
1        | CREATE     | <skill name>        | <why>
2        | MERGE      | <skill A> + <B>     | <why>
3        | IMPROVE    | <existing skill>    | <what's weak>

Limit to top 10 recommendations. For each CREATE recommendation, include:

  • Suggested skill name
  • One-line description
  • Trigger patterns
  • Estimated complexity (trivial / weekend / multi-sprint)

Phase 4: Output

Present findings as:

  1. Summary stats: total skills, total plugins, coverage gaps found, redundancies found
  2. Recommendations table (from Phase 3)
  3. Quick wins: any recommendations that could be implemented in under 30 minutes

Do NOT auto-create skills. This is an audit -- the user decides what to act on.

Source Attribution

Technique: Skill Backlog Audit prompt pattern Source: Nate's Newsletter (natesnewsletter@substack.com), 2026-03-30 Post: "Your Best AI Work Vanishes Every Session. 4 Prompts That Make It Permanent"

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free