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
- Ivan-propio/claude-skillstheir own version, first seen Nov 16, 2026
- notedit/happy-coding-agenttheir own version, first seen Oct 8, 2026
- KellyDigitalArmy/ClaudeCodetheir own version, first seen May 5, 2026
- notedit/happy-skillstheir own version, first seen Mar 3, 2026
- abdullah1854/ClaudeSuperSkillstheir own version, first seen Dec 25, 2025
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- notedit/happy-skills★ 340same name
- notedit/happy-coding-agent★ 339same name
- abdullah1854/ClaudeSuperSkills★ 1same name
- Ivan-propio/claude-skills★ 0same name
- KellyDigitalArmy/ClaudeCode★ 0same 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 repository7 other files it gives its agents.
- ai-llm-skills-guideSkill
- claude-code-skillsSkill
- dev-tools-skills-guideSkill
- marketing-skills-guideSkill
- awesome-skills-overviewSkill
- agent-platformsSkill
- security-skills-guideSkill
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
- Distinctive: line 10
Use this skill when:
- Very specific: line 62
Use progressive disclosure: Put detailed references in references/ folder.
- Distinctive: line 63
Include scripts for automation: Use helper scripts for deterministic operations.
- Distinctive: line 65
Test across platforms: Verify skills work with Claude Code, Codex, etc.
- Distinctive: line 73
Bundled resources: Only load as needed
“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.
Files
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 filesSKILL.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
- Keep descriptions exhaustive: The frontmatter description helps agents decide when to trigger the skill.
- Focus on execution: The body should contain clear, actionable steps.
- Use progressive disclosure: Put detailed references in
references/folder. - Include scripts for automation: Use helper scripts for deterministic operations.
- Keep SKILL.md under 500 lines: For optimal performance.
- Test across platforms: Verify skills work with Claude Code, Codex, etc.
Token Efficiency
Skills employ progressive disclosure architecture:
- Metadata loading (~100 tokens): Agent scans available skills
- Full instructions (<5k tokens): Load when skill is activated
- Bundled resources: Only load as needed
Platform-Specific Paths
| Platform | Project Path | Global 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.mdThe README.md contains the complete categorized resource list with all links.
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
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.

