agentleFS
Sign inStart free
lov-altlov-alt/skill-distill/SKILL.md

skill-distill

Skill4 starsChanged 4 months agoMITView on GitHub

Audit skill descriptions for routing quality. Use when the user asks to check, lint, audit, or improve AI agent skill descriptions, wants to find overlapping or confusingly similar skills, or needs to benchmark skill routing accuracy. Use for directories containing SKILL.md or similar markdown skill definition files. Not for general code review, not for reviewing pull requests, not for linting regular source code.

  • Installs packages

6 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions6 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 6

    1. fielding/skill-distill★ 4same name
    2. ridges0315/skill-distill★ 4same name
    3. izerume/skill-distill★ 2same name
    4. AbdouMoumen/claude-skills-plugin★ 1same name
    5. fielding/skills★ 1same name
    6. scott2b/claude-skills★ 1same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run the skill-distill CLI to analyze AI agent skill descriptions for routing quality issues.

    line 8

“Common” is measured: kept by at least 6 in 10 of the 6 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 Distill

Run the skill-distill CLI to analyze AI agent skill descriptions for routing quality issues.

Prerequisites

  • Python 3.10+
  • skill-distill installed: pip install skill-distill

Commands

Lint — check description quality with scoring

skill-distill lint <path>           # list issues
skill-distill lint <path> --score   # show 0-100 quality score per skill
skill-distill lint <path> -f json   # JSON output for CI/scripts

Diff — find overlapping skills

skill-distill diff <path-to-skills-directory>

Compares all skills pairwise to find descriptions that an agent would struggle to tell apart.

Optimize — get improvement suggestions

skill-distill optimize <path-to-skill-file> --dry-run

Suggests specific changes to make descriptions more distinguishable.

Benchmark — measure routing accuracy

skill-distill bench <benchmark-yaml> --skills <skills-directory>

Health — audit registry

skill-distill health <skills-directory>

Reports parseable/unparseable counts, skills missing descriptions, and overall status.

Example workflow

  1. skill-distill health ./skills/ — audit the registry
  2. skill-distill lint ./skills/ --score — score all skills
  3. skill-distill diff ./skills/ — find overlapping pairs
  4. skill-distill optimize ./skills/problem-skill.md --apply — fix issues
  5. skill-distill bench suite.yaml --skills ./skills/ — verify improvement

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