creating-agent-skills
Skill124 starsChanged 8 months agoMITView on GitHub
Use when creating Agent Skills packages (SKILL.md format) for Codex CLI, GitHub Copilot, or Amp - provides the agentskills.io specification with frontmatter constraints, directory structure, and validation rules
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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
- Distinctive: line 94
When to activate it (keywords agents search for)
- Distinctive: line 197
Use the validation tool:
- Distinctive: line 238
No content changes required.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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.
Files
Creating Agent Skills
Overview
Agent Skills is an open standard for portable AI agent capabilities. One SKILL.md file works across Codex CLI, GitHub Copilot, and Amp.
Official Spec: https://agentskills.io/specification
Installation Directories
| Tool | Location |
| Codex CLI | .agents/skills/{skill-name}/SKILL.md |
| GitHub Copilot | .github/skills/{skill-name}/SKILL.md |
| Amp | .agents/skills/{skill-name}/SKILL.md |
Directory Structure
my-skill/ # Must match frontmatter `name`
├── SKILL.md # Required - main definition
├── scripts/ # Optional - executable code
├── references/ # Optional - additional docs
└── assets/ # Optional - static resourcesFrontmatter Specification
Required Fields
---
name: skill-name
description: What it does and when to use it
---| Field | Constraints |
name | 1-64 chars, lowercase alphanumeric + hyphens, no leading/trailing/consecutive hyphens, must match parent directory |
description | 1-1024 chars, explains functionality AND use cases |
Optional Fields
---
name: pdf-processing
description: Extracts and processes PDF content. Use for document analysis and text extraction.
license: MIT
compatibility: Requires pdftotext, poppler-utils
allowed-tools: Bash(pdftotext:*) Read Write
metadata:
category: document-processing
version: 1.0.0
---| Field | Constraints |
license | Short reference (e.g., MIT, Apache-2.0) |
compatibility | 1-500 chars, environment requirements |
allowed-tools | Space-delimited pre-approved tools (experimental) |
metadata | Arbitrary string key-value pairs |
Name Validation
✅ Valid: pdf-processing, code-review, data-analysis
❌ Invalid: PDF-Processing (uppercase), -pdf (leading hyphen), pdf--processing (consecutive hyphens)Pattern: ^[a-z0-9]+(-[a-z0-9]+)*$
Description Best Practices
# ❌ BAD - Too vague
description: Helps with PDFs
# ❌ BAD - Missing use cases
description: Extracts text from PDFs
# ✅ GOOD - Functionality + use cases
description: Extracts and processes PDF content. Use for document analysis, text extraction, and form data parsing.Include:
- What the skill does
- When to activate it (keywords agents search for)
- Specific use cases
Body Content
Markdown instructions after frontmatter. No format restrictions, but recommended sections:
---
name: code-review
description: Reviews code for best practices and security issues. Use when analyzing PRs or conducting audits.
---
## Overview
Brief description of capabilities.
## Process
1. Step-by-step workflow
2. With clear actions
## Guidelines
- Bullet points for rules
- Best practices
## Examples
Code samples showing usage.Progressive Disclosure
Skills use tiered loading to optimize context:
- Metadata (~100 tokens):
name+descriptionload at startup - Activation (<5000 tokens): Full
SKILL.mdloads when selected - On-demand: Supporting files load when referenced
Keep SKILL.md under 500 lines for efficient context usage.
Supporting Files
scripts/
Executable code agents can invoke:
#!/usr/bin/env python3
# scripts/extract.py
import sys
# Self-contained with clear dependenciesreferences/
Additional documentation:
REFERENCE.md- Technical detailsFORMS.md- Templates- Domain-specific files
assets/
Static resources: templates, diagrams, lookup tables.
Reference with relative paths: scripts/extract.py, references/REFERENCE.md
Complete Example
---
name: typescript-expert
description: Expert TypeScript assistance with strict typing and modern patterns. Use for TypeScript projects requiring type safety, generics, or advanced type manipulation.
license: MIT
compatibility: Requires Node.js 18+, TypeScript 5+
---
You are an expert TypeScript developer.
## Guidelines
- Always use strict type checking
- Prefer `unknown` over `any`
- Use type guards for runtime checking
- Leverage template literal types
## Best Practices
- Export types from dedicated `.types.ts` files
- Use `readonly` for immutable data
- Prefer interfaces for objects, types for unions
## Examples
### Type Guard
```typescript
function isUser(obj: unknown): obj is User {
return (
typeof obj === 'object' &&
obj !== null &&
'id' in obj &&
'name' in obj
);
}
## Validation
Use the validation tool:
```bash
skills-ref validate ./my-skillChecks:
- YAML frontmatter validity
- Name format compliance
- Required fields presence
- Directory name matches
namefield
Quick Checklist
Frontmatter:
nameis 1-64 chars, lowercase alphanumeric + hyphensnamematches parent directory namedescriptionis 1-1024 charsdescriptionincludes functionality AND use cases
Content:
- Under 500 lines for efficient loading
- Clear instructions agents can follow
- Examples for complex operations
Structure:
- Directory named exactly as
namefield SKILL.mdat directory root- Supporting files in appropriate subdirectories
Cross-Tool Compatibility
The SKILL.md format is identical across implementations. To port:
# Codex → Copilot
mv .agents/skills/my-skill .github/skills/my-skill
# Copilot → Codex/Amp
mv .github/skills/my-skill .agents/skills/my-skillNo content changes required.
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- AgentWorkforce/relay★ 1.1k92% same
Wrote their own version · 2
- mazrean/agent-skills★ 2same name
- ravid7000/skills★ 1same 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 repository64 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- beanstalk-deployCursor rule
- .cursor/rules/core-principles.mdcCursor rule
- .cursor/rules/creating-agents-md.mdcCursor rule
- .cursor/rules/creating-claude-agents.mdCursor rule
- .cursor/rules/creating-claude-commands.mdCursor rule
- .cursor/rules/creating-claude-hooks.mdCursor rule
- .cursor/rules/creating-continue-packages.mdCursor rule
- .cursor/rules/creating-copilot-packages.mdCursor rule
- .cursor/rules/creating-cursor-commands.mdCursor rule
- .cursor/rules/creating-cursor-rules.mdcCursor rule
- .cursor/rules/creating-kiro-agents.mdcCursor rule
- .cursor/rules/creating-kiro-packages.mdCursor rule
- .cursor/rules/creating-skills.mdcCursor rule
- .cursor/rules/creating-windsurf-packages.mdCursor rule
- .cursor/rules/elastic-beanstalk-deployment.mdCursor rule
- .cursor/rules/format-conversion.mdcCursor rule
- .cursor/rules/github-actions-testing.mdcCursor rule
- .cursor/rules/karen-repo-reviewer.mdcCursor rule
- .cursor/rules/prpm-json-best-practices.mdcCursor rule
- .cursor/rules/self-improve-cursor.mdcCursor rule
- .cursor/rules/testing-patterns.mdcCursor rule
- .cursor/rules/typescript-type-safety.mdcCursor rule
- .cursor/rules/typescript-type-specialist.mdcCursor rule
- adding-new-ai-formatSkill
- agent-builderSkill
- aws-beanstalk-expertSkill
- beanstalk-deploySkill
- claude-hook-writerSkill
- creating-agents-mdSkill
- creating-claude-agentsSkill
- creating-claude-commandsSkill
- creating-claude-hooksSkill
- creating-claude-rulesSkill
- creating-continue-packagesSkill
- creating-copilot-packagesSkill
- creating-cursor-commandsSkill
- creating-cursor-rules-skillSkill
- creating-kiro-agentsSkill
- creating-kiro-packagesSkill
- creating-opencode-agentsSkill
- creating-opencode-pluginsSkill
- creating-skillsSkill
- creating-windsurf-packagesSkill
- creating-zed-extensionsSkill
- documentation-standardsSkill
- elastic-beanstalk-deploymentSkill
- github-actions-testingSkill
- human-writingSkill
- integrating-stripe-webhooksSkill
- karen-repo-reviewerSkill
- npm-trusted-publishingSkill
- osgrepSkill
- postgres-migrationsSkill
- prpm-developmentSkill
- prpm-json-best-practicesSkill
- pulumi-troubleshootingSkill
- self-improvingSkill
- slash-command-builderSkill
- The first 60 shown.
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.

