agentleFS
Sign inStart free
getedgehqgetedgehq/skills/agent-skills-gap/SKILL.md

agent-skills-gap

Skill5 starsChanged 11 days agoApache-2.0View on GitHub

Analyze Claude or Codex session logs or pasted prompts to identify evidenced strengths, weak task categories, a surprising weakness, and up to seven relevant skills, then create a private JSON result and shareable card. Use when asked for an AI skills gap test, agent résumé, missing expertise, or a share card about what an agent is good or bad at.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    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 only the session logs, transcripts, or prompts the user authorized.

    line 12
  2. Distinctive:

    Never copy prompts, paths, filenames, private project names, or transcript excerpts into the share card or public summary.

    line 35
  3. Distinctive:

    Do not upload or publish anything without a separate explicit action.

    line 38

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “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

Agent Skills Gap Test

Give the user a defensible result, not a personality quiz.

Run

  1. Use only the session logs, transcripts, or prompts the user authorized.
  2. Locate this skill directory and run its deterministic analyzer:
node /absolute/path/to/this-skill/cli.js --out ./out <input-file> [more-input-files]

For pasted material, save it as a temporary .txt input inside the task workspace first. Do not put private prompt text in a shell argument.

  1. Read out/skills-gap.json. Report:
    • strongest measured category;
    • every category rating;
    • the surprising weakness;
    • the recommended skills count and names.
  2. Point the user to out/skills-gap-card.svg as the shareable artifact.

Evidence rules

  • Fewer than two relevant entries means Not measured, never Weak.
  • A task appearing often is not proof of quality. Weakness requires explicit friction evidence.
  • Say the result describes the supplied sample, not the model's intelligence.
  • Recommendations mean “relevant to this observed gap,” not “confirmed missing from the machine.”
  • Never copy prompts, paths, filenames, private project names, or transcript excerpts into the share card or public summary.
  • Cap recommendations at seven.
  • Do not upload or publish anything without a separate explicit action.

Output contract

skills-gap.json uses schema agent-skills-gap/0.1. The SVG contains only generic category labels, ratings, the number of analyzed entries, and recommended-skill count. Raw input stays local.

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