agentleFS
Sign inStart free
cellrishi-codecellrishi-code/claude-skills-atlas/skills/claude/skill-author/SKILL.md

skill-author

Skill6 starsChanged 42 days agoMITView on GitHub

Design or improve a reusable Claude Agent Skill with precise activation criteria, focused instructions, examples, verification, and safe boundaries. Use when creating or refactoring a SKILL.md.

23 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 5

    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:

    Create skills that are reusable, testable, and easy for another contributor to understand.

    line 8
  2. Distinctive:

    Write an activation description that states when it should be used.

    line 13
  3. Distinctive:

    Keep instructions focused on behavior, not background exposition.

    line 14
  4. Distinctive:

    Add examples when they clarify invocation or expected output.

    line 17
  5. Distinctive:

    Test against representative tasks.

    line 20

“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

Skill Author

Create skills that are reusable, testable, and easy for another contributor to understand.

Process

  1. Define one clear job for the skill.
  2. Write an activation description that states when it should be used.
  3. Keep instructions focused on behavior, not background exposition.
  4. Separate required steps from optional guidance.
  5. Include failure conditions and safety boundaries.
  6. Add examples when they clarify invocation or expected output.
  7. Define verification that can expose common failures.
  8. Move large reference material outside the main skill.
  9. Test against representative tasks.
  10. Revise based on observed failures.

Quality checklist

  • Is the purpose specific?
  • Is the trigger description useful?
  • Are assumptions explicit?
  • Is the output format clear?
  • Can the skill be tested?
  • Does it avoid unnecessary permissions or destructive actions?
  • Does it duplicate an existing Atlas resource?

Output

Return:

  • Skill purpose
  • Activation description
  • Instructions
  • Examples
  • Verification plan
  • Known limitations

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