agentleFS
desbmadesbma/agent-skills/.agents/skills/audit-skill-run/SKILL.md

audit-skill-run

Skill1 starsChanged 20 days agoMITView on GitHub

Audit recent runs of a skill from their session transcripts, and propose improvements to the skill.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    If the runs went well, say so, and propose nothing: Do not suggest minor improvements for their own sake.

    line 23

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Audit skill run

Audit how the most recent runs of the skill named in the arguments went, from their session transcripts: usually those of the same day or hour. Notes after the skill name say what the user saw or what to focus on.

For each run, assess, among anything else that cost it:

  • the wrong turns it took, and what led to each;
  • whether its time was well spent;
  • where its tokens went, and which were wasted;
  • whether the skill's instructions were ambiguous, conflicting or misleading, and where the agent had to improvise.

You may use subagents.

Report your findings, and propose improvements to the skill's prose or helper scripts. Each proposal opens with the issues it fixes and roughly what the run would have saved in turns, time and tokens; the change comes after. Before proposing to change a passage, read its VCS history, so the change does not undo what an earlier one fixed.

If the runs went well, say so, and propose nothing. Do not suggest minor improvements for their own sake. A minor issue is acceptable when it comes from an exceptional case and fixing it would degrade more common ones.

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.