agentleFS
gmh5225gmh5225/awesome-skills/.claude/skills/skill-creation/SKILL.md

skill-creation-guide

Skill97 starsChanged 10 months agoMITView on GitHub

Guide for creating Agent Skills: structure, best practices, and SKILL.md format for Claude Code, Codex, Gemini CLI, and other AI agents.

5 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, 4 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 4 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when:

    line 10
  2. Very specific:

    Use progressive disclosure: Put detailed references in references/ folder.

    line 62
  3. Distinctive:

    Include scripts for automation: Use helper scripts for deterministic operations.

    line 63
  4. Distinctive:

    Test across platforms: Verify skills work with Claude Code, Codex, etc.

    line 65
  5. Distinctive:

    Bundled resources: Only load as needed

    line 73

“Common” is measured: kept by at least 6 in 10 of the 4 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 Creation Guide

Scope

Use this skill when:

  • Creating new Agent Skills
  • Understanding SKILL.md format and conventions
  • Learning best practices for skill authoring

Skill Structure

skill-name/
├── SKILL.md          # Required: Instructions and metadata
├── scripts/          # Optional: Helper scripts
├── templates/        # Optional: Document templates
└── resources/        # Optional: Reference files

SKILL.md Format

Required Frontmatter

---
name: my-skill-name
description: A clear description of what this skill does and when to use it.
---

Body Structure

# Skill Name

Detailed description of the skill's purpose.

## When to Use This Skill

- Use case 1
- Use case 2

## Instructions

[Detailed instructions for the agent]

## Examples

[Real-world examples]

Best Practices

  1. Keep descriptions exhaustive: The frontmatter description helps agents decide when to trigger the skill.
  2. Focus on execution: The body should contain clear, actionable steps.
  3. Use progressive disclosure: Put detailed references in references/ folder.
  4. Include scripts for automation: Use helper scripts for deterministic operations.
  5. Keep SKILL.md under 500 lines: For optimal performance.
  6. Test across platforms: Verify skills work with Claude Code, Codex, etc.

Token Efficiency

Skills employ progressive disclosure architecture:

  1. Metadata loading (~100 tokens): Agent scans available skills
  2. Full instructions (<5k tokens): Load when skill is activated
  3. Bundled resources: Only load as needed

Platform-Specific Paths

PlatformProject PathGlobal Path
Claude Code.claude/skills/~/.claude/skills/
Codex.codex/skills/~/.codex/skills/
Cursor.cursor/skills/~/.cursor/skills/
Gemini CLI.gemini/skills/~/.gemini/skills/
GitHub Copilot.github/skills/~/.copilot/skills/

Quality Checklist

  • Clear, actionable instructions
  • Includes real-world examples
  • Written for AI agents, not end users
  • Documents prerequisites and dependencies
  • Includes error handling guidance
  • Tested on target platform(s)

Full Resource List

For more detailed skill creation resources, complete link lists, or the latest information, use WebFetch to retrieve the full README.md:

https://raw.githubusercontent.com/gmh5225/awesome-skills/refs/heads/main/README.md

The README.md contains the complete categorized resource list with all links.

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.