skill-tidy
Skill0 starsChanged 29 days agoMITView on GitHub
Tidies a working skill that grew long, repetitive or stale while keeping its behaviour, proven by the same eval results at fewer tokens. Not for wrong output (skill-improve).
- Installs packages
1 other project uses a version of this.
Adopted by
Most recently taken up by
- innoai-tech/skillstheir own version, first seen May 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- innoai-tech/skills★ 0same 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.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- skill-benchSkill
- skill-checkSkill
- skill-competeSkill
- skill-createSkill
- skill-descriptionSkill
- skill-evalSkill
- skill-factsSkill
- skill-improveSkill
- skill-learnSkill
- skill-packageSkill
- skill-planSkill
- skill-pluginSkill
- skill-publishSkill
- skill-releaseSkill
- skill-repoSkill
- skillSkill
- skill-tokensSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 22
If the skill has no evals, write a few for what it does now first (the format is in skill-eval): without them there is nothing to prove the …
≈ “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.
Files
Tidy a skill
Cutting is easy; proving nothing broke is the job. Change how the skill is written, never what it does.
The engine runs as npx -y @thenavidm/skill-builder@latest. Where skill-builder is installed (npm install -g @thenavidm/skill-builder), run skill-builder instead: it's the same engine, without the download.
1. Save it and measure it
Copy the whole skill folder to .agents/skill/history/<name>/<date-and-time>/ and confirm the copy matches: it's the baseline and the way back. Then take the before numbers:
npx -y @thenavidm/skill-builder@latest check <skill>
npx -y @thenavidm/skill-builder@latest tokens <skill>
npx -y @thenavidm/skill-builder@latest eval <skill> --runs 3If the skill has no evals, write a few for what it does now first (the format is in skill-eval): without them there is nothing to prove the tidy against.
2. Find what to change
| Problem | Change |
| The same rule in several places | Keep it once, where it's needed |
| Two rules that contradict | Ask which wins; keep that one |
| Generic advice the model follows anyway | Remove it |
| A rule without its reason | Add the reason in a sentence, or remove the rule if nobody knows why it's there |
| Detail only some cases need | Move it into a reference, linked from the step that needs it |
| Links to files that moved | Fix or remove them |
| A long description | What it does, when, one boundary, about 300 characters |
3. One approval
Show the changes grouped by kind, with what each saves, and get a yes for the set. Apply them.
4. Prove nothing changed
Run the same three commands. eval must give the same results as before (within the usual spread between runs), check must be as clean or cleaner, and tokens shows what was saved. If any eval result got worse, find the change that caused it, undo that one change, and run again. Two tries; after that, put the saved version back and report what you found.
Report the before and after numbers side by side and where the old version is kept.
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
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.