agentleFS
romeohcromeohc/afkit/skills/clean/SKILL.md

clean

Skill0 starsChanged 38 days agoMITView on GitHub

Read-only cleanup of a given path. Spawn agents, propose named PRs, implement only the one they name.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use expressive, friendly and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • bergsideSkill

    expressive

    Vibrant, personality-driven design with bold colors, playful graphics, and dynamic layouts that balance creativity with structure.

    Also in 4 projects that use this

  • bergsideSkill

    friendly

    Approachable, intuitive design with rounded elements, ample whitespace, and soft pastel color palettes.

    Also in 4 projects that use this

  • +10 more from bergside

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 2

    Distinctive

    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 they gave no path, ask for one and stop.

    line 25
  2. Distinctive:

    If they reply with a name from the list, implement that PR only.

    line 33

“Common” is measured: kept by at least 6 in 10 of the 18 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

Clean

They give a path. You stay read-only. Spawn several agents on that path. Report. Do not edit until they answer with a PR name from your list.

Engineer

Question hard. Should this exist at all? What should we never build? What should we delete? Saying no is the default until it earns its place. Point at less.

Then: cut what does not change the result, including what looks useful but is not. Simplify what remains. Same result with less is the win, or better.

Settle the data shape before writing logic. One rule in one place, not scattered checks. If a new need belongs in the core, redesign for it. Do not bolt on. Flatten anything a reader must chase through many files.

Trace to the real cause. Do not hide a problem.

Stay inside the given path. Do not touch outside it.

Do

If they gave no path, ask for one and stop.

Split the path. Spawn several read-only agents in parallel. Each owns a slice. They hunt deletions and simplifications. You keep summaries, not their raw dumps.

Synthesize. Drop noise. Keep only what would change the code.

Reply: what you found, then named PRs. One short name per PR, what it does, one PR or several. Then stop.

If they reply with a name from the list, implement that PR only. If they keep talking, stay read-only and refine the list.

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.