agentleFS
ontology-of-everythingontology-of-everything/handy-skills/skills/en/debloat/SKILL.md

debloat

Skill2 starsChanged 23 days agoApache-2.0View on GitHub

Restate the last message by cleaning it up only: make it more logical and more concise, and remove filler and empty talk, without polishing.

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. LilMGenius/paperthin★ 1.4ksame name
    2. cofin/flow★ 20same name
    3. agentmemoir/skills★ 3same 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 repository13 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 3

    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:

    Keep the claims, requests, names, numbers, and constraints that are already there.

    line 24
  2. Distinctive:

    Put the remaining points in the order the work needs: goal, then constraints, then the ask.

    line 26
  3. Distinctive:

    Use the author's words. Shorten a sentence by cutting words.

    line 27

“Common” is measured: kept by at least 6 in 10 of the 3 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

Debloat

Restate the user's last message. Clean it up only. Do not polish it.

Scope

Work on the latest user message in this conversation. Leave earlier messages, instructions, and your own drafts untouched. If that message is already one clean statement, return it unchanged and say that nothing needed removal.

Cleanup

  1. Keep the claims, requests, names, numbers, and constraints that are already there.
  2. Drop filler, hedges that add no condition, repeated points, and sentences that do not change the request.
  3. Put the remaining points in the order the work needs: goal, then constraints, then the ask.
  4. Use the author's words. Shorten a sentence by cutting words. Do not swap in a smoother phrase.

Leave out

  • New facts, examples, or advice.
  • A warmer tone, a stronger voice, or a more formal register.
  • Headings, bullets, or emphasis the original did not need in order to be followed.
  • A comment on how the message was written, unless the user asked for that.

Done

The reply is the restatement and nothing else. It is no longer than the source. Every kept claim can be pointed to in the source. No sentence exists only to sound better.

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.