More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    skill library health

    2

    Audit and resolve routing collisions, purpose overlap, and version drift across your entire AI agent skill library.

    Free

    10 uses5.0 (1 review)
    skill library health

    skill library health

    Example session with this skill installed

    audit my skills library at ~/.claude/skills/synced

    • Read your context and instructions
    • Compiled the library health

    HEALTH REPORT: Grade C (72/100).

    Findings

    • H1: Collision between 'git-commit' and 'git-helper' on phrase "commit changes".
    • H7: Version drift in 'react-tool' (v18) vs 'ui-core' (v19).

    Fix Sequence

    1. Add negative boundary to 'git-helper' (Resolves H1, H4).
    2. Sync React versions (Resolves H7).

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Skill Library Health Report

    Audits the set, not the skill.

    Every skill review tool reads one file. None of them can see the problems that only exist in a collection — two skills claiming the same trigger phrase, four doing one job, a skill no wording will ever reach, siblings running different versions of the same framework. Each file, read alone, looks fine.

    This reads all of them at once and reports what they do to each other.

    MIT licensed. Free, complete, and not a sample of anything else.


    Run it in ten seconds

    python3 scripts/library_health.py
    

    No arguments scans a bundled six-skill sample library and prints the full report, labelled as a demonstration. Nothing to configure, no keys, no network.

    Run it on your own library

    python3 scripts/library_health.py ~/.claude/skills/synced
    python3 scripts/library_health.py ~/.claude/skills/synced --json
    

    Point it at any folder containing skill folders. Nested trees are walked, so a plugins directory or a mixed layout works. Python 3, standard library only.


    What it checks

    IDCheckQuestion
    H0Unreadable skill fileDid anything fail to load and get left out?
    H1Trigger collisionDo two skills claim the same phrase?
    H2Purpose overlapDo several describe the same job?
    H3Unreachable skillIs there anything for a request to match?
    H4Missing boundaryDoes a skill with close neighbours say what it is not for?
    H5Description budgetIs the routing surface over the limit, or barely used?
    H6Stale or stubIs the skill too thin to do what it claims?
    H7Version driftDo siblings cite different versions of one framework?

    Full trigger rules, severity logic and the blind spot of every check are in references/health-checks.md.

    What the score means

    100 points, minus a deduction per problem — and the report prints the subtraction, not just the total:

      HOW THAT SCORE WAS REACHED
       100 starting points
          -8  6 colliding phrase(s)
         -20  35 closely related pair(s)
         -10  1 description over the 1024-character limit
    

    A score you cannot reconstruct is a score you should ignore. Every weighting is a constant at the top of scripts/library_health.py — disagree with a number and change it deliberately.

    A 90+ · B 75+ · C 60+ · D 40+ · E below 40.

    What it refuses to do

    • It will not grade a library of one. Four of the checks compare skills against each other and have nothing to compare, so no grade is issued and the report says why. An A awarded on an empty comparison is worse than no grade.
    • A check that could not run is not reported as passed. Those come back N/A, listed separately from PASSED.
    • It does not invent findings. A clean library scores 100 with "no deductions".
    • It never hides a dropped input. A SKILL.md that fails to open is named in the report and counted in H0, because every other figure was computed without it.
    • Similarity is a candidate for your judgement, never a verdict. Two skills that share vocabulary because they are one workflow split in two will show as an overlap. That is a finding to dismiss, not a defect to fix.

    What it is not

    Not a per-skill quality audit. Not a security scan. Not a judgement of whether any skill is well written, correct, or does what it claims. A library of excellent skills can score badly here, and a library of weak ones can score well.

    Reads only

    Executes nothing it scans. Writes nothing into your library. Makes no network call. The demonstration materialises its sample into a temporary folder and deletes it after the run — a tool that installed six fake skills to demo itself would be adding the problem it reports.


    Two ways to use it

    As a script — clone and run, as above.

    As a skill — copy this folder into your skills directory. SKILL.md routes requests like "audit my skills library" or "why does the wrong skill keep firing" straight to it. A single-file build is in skill-library-health-STANDALONE.md for destinations that take one file only.


    Verified

    CheckResult
    monna-verifyCLEAN · 30/30 · 0 blockers · 0 fails · 0 AI-language hits
    Adversarial cold-run suite7 of 7 scenarios pass — cold run, score arithmetic reconstructed by hand, one-skill library, trigger collision, clean library, no-write/no-temp-residue, missing-library error
    Box renderingevery row exactly 80 columns across 1-, 3-, 6- and 125-skill libraries
    Real-world run125-skill library: grade E, 38/100, 6 colliding phrases, 35 close pairs

    From the same author

    one deliberately does not:

    • Skill Security Auditor — eight checks on what a single skill could reach: injection surface, credential exposure, exfiltration paths, unbounded execution.
    • Trade Post-Mortem Engine — behavioural fault classes in a closed trade log.
    • Pre-Trade Risk Auditor — what a trade plan commits before it is sent.

    This tool is not a trial of those. It answers a question they do not.

    Contributing

    Issues and pull requests welcome, particularly:

    • additional check ideas with a stated blind spot
    • false positives on real libraries, with the library shape that produced them
    • weighting disagreements backed by a library where the current number reads wrong

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skill Creator Skills.

    Requires Python 3. Audits inter-skill relationships only, not internal code quality, safety, or individual skill logic. Needs a folder containing SKILL.md files.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    5.0
    1 review
    5
    1
    4
    0
    3
    0
    2
    0
    1
    0

    This skill has been used 10 times.

    Trust & safety

    Security scan

    Security scan passed 2 months ago

    • Free with an Agensi account

    Software
    Python

    Permissions

    Terminal / Shell
    Listed2 months ago

    What's inside

    Frequently Asked Questions

    Standard audit tools look at individual files, but this tool analyzes how your skills interact. It identifies 'routing collisions' where two skills fight over the same trigger and 'purpose overlap' where multiple skills redundantly perform the same task.

    This is a local-first Python tool designed to run via CLI or as an integrated skill. It requires Python 3 (standard library only) and works with any agent framework that organizes skills into folders, such as Claude Desktop or similar modular AI environments.

    No, the tool operates on a 'Read-Only' basis to ensure the integrity of your library. It executes nothing it scans, makes no network calls, and writes no changes to your files, providing a safe diagnostic report without altering your code.

    You will receive the full Python source code for the auditor, a standalone skill markdown file for easy integration, and a comprehensive reference guide detailing the logic behind each of the eight health checks.

    The auditor is designed to evaluate a collection; it requires at least two skills to function. If run against a single skill, the report will explain that there are no siblings to compare against rather than giving a false 'A' grade.

    The report provides a transparency breakdown showing exactly how points were deducted (e.g., -8 for collisions, -20 for overlaps). You can easily adjust the scoring weights at the top of the script if you want to prioritize certain checks over others for your specific workflow.

    New in Agents & Orchestration

    Free