agentleFS
HashLipsHashLips/agent-skills/skills/agent-skill-creator/SKILL.md

agent-skill-creator

Skill29 starsChanged 7 months agoMITView on GitHub

Creates coherent Agent Skills with consistent format, minimal main SKILL.md files, and reference-driven documentation. Use when creating new skills, standardizing existing skills, defining skill structure, or improving skill maintainability and context efficiency.

6 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

9 rules. 0 are common, 6 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 6 edited versions we read keep these.

  • 6

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Keep main SKILL.md operational.

    line 11
  2. Very specific:

    Keep SKILL.md concise and action-oriented.

    line 16
  3. Distinctive:

    Use consistent naming, layout, and discoverability patterns.

    line 18
  4. Distinctive:

    Avoid duplicated guidance across files.

    line 19
  5. Very specific:

    Write frontmatter (name, description).

    line 24
  6. Distinctive:

    Add assets only if execution quality materially improves.

    line 27
  7. Distinctive:

    Run quality checklist before finalizing.

    line 28
  8. Distinctive:

    Do not duplicate large guidance across main and reference files.

    line 38
  9. Distinctive:

    Before delivery, format produced Markdown with the local MD design system skill.

    line 39

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

Agent Skill Creator

Summary

  • Build coherent, reusable Agent Skills with low context cost.
  • Keep main SKILL.md operational; move depth into references.
  • Standardize structure and naming across repository skills.

Core Goals

  • Keep SKILL.md concise and action-oriented.
  • Store long-form guidance in references/.
  • Use consistent naming, layout, and discoverability patterns.
  • Avoid duplicated guidance across files.

Authoring Workflow

  1. Define skill intent and trigger scenarios.
  2. Write frontmatter (name, description).
  3. Draft minimal operational SKILL.md.
  4. Move depth into references.
  5. Add assets only if execution quality materially improves.
  6. Run quality checklist before finalizing.
  7. Apply final formatting pass using the available MD Design System skill.

Non-Negotiable Rules

  • Frontmatter is required.
  • name is lowercase kebab-case.
  • description states what the skill does and when to use it.
  • description pattern: <what it does>. Use when <trigger scenarios>.
  • Reference links are one-level deep and description-first.
  • Do not duplicate large guidance across main and reference files.
  • Before delivery, format produced Markdown with the local MD design system skill.

Reference Index

  • Authoring model and structure strategy: references/blueprint.md
  • Default file layout and naming: references/file-layout.md
  • Final quality gate checklist: references/quality-checklist.md
  • Final Markdown formatting contract: available MD Design System skill

When To Use This Skill

  • Creating a new skill from scratch.
  • Refactoring existing skills for consistency.
  • Reducing token overhead in skill packages.
  • Standardizing team skill authoring patterns.

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.