agentleFS
Sign inStart free
redicherediche/skills/simplify-agent-instructions/SKILL.md

simplify-agent-instructions

Skill3 starsChanged 36 days agoMITView on GitHub

Reviews agent instructions and suggests clearer language using practical ASD-STE100 principles. Use when simplifying AGENTS.md, CLAUDE.md, .ai/ files, editor rules, or other codebase instructions for agents.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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 practical ASD-STE100 principles, not strict compliance:

    line 10
  2. Distinctive:

    Use short sentences with one instruction per sentence.

    line 11
  3. Distinctive:

    Use active voice and imperative verbs.

    line 12
  4. Distinctive:

    Prefer familiar words and consistent terms.

    line 13
  5. Distinctive:

    Remove repetition only when scope and meaning remain unchanged.

    line 15

≈ “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

Simplify Agent Instructions

Find agent instructions throughout the codebase, including nested files, rule directories, and referenced instruction sources. For Laravel projects using Laravel Boost, prioritize .ai/ source instructions over generated files such as AGENTS.md or CLAUDE.md.

Use practical ASD-STE100 principles, not strict compliance:

  • Use short sentences with one instruction per sentence.
  • Use active voice and imperative verbs.
  • Prefer familiar words and consistent terms.
  • Replace vague references with explicit names.
  • Remove repetition only when scope and meaning remain unchanged.

Preserve requirements, prohibitions, exceptions, conditions, instruction priority, and technical terms. Keep code, commands, paths, and identifiers unchanged. Flag ambiguity instead of guessing.

Report suggestions only. For each suggestion, include:

  • File path and line number.
  • Original text.
  • Suggested replacement.
  • Brief reason.

Skip changes that do not improve clarity. Identify source files when generated instructions duplicate them.

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