Creating Agent Skills Packages

What it does

When your agent uses it

• Writing a new SKILL.md that must work in several coding agents
• Checking whether a skill name or description meets the format limits
• Deciding where to install a skill for Codex CLI, GitHub Copilot or Amp
• Rewriting a vague skill description so agents activate it at the right time

Example prompts

• “Create an Agent Skills package called code-review with valid frontmatter and a body outline.”
• “Is Data_Analysis a valid skill name, and if not, what should it be?”
• “Where should I put this skill so GitHub Copilot picks it up?”
• “Rewrite the description 'Helps with PDFs' so it says what the skill does and when to use it.”

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1Metadata (~100 tokens): name + description load at startup
2. 2Activation (<5000 tokens): Full SKILL.md loads when selected
3. 3On-demand: Supporting files load when referenced

What it can do on your machine

Read from SKILL.md and the folder at commit 5f993e6. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are yaml, markdown, python and bash).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  Links to these hosts (documentation or services it may open):

  • agentskills.io

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Creating Agent Skills Packages loads about 1.5k tokens when it runs. Until then it costs about 58 tokens; SKILL.md has 293 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~58

When it runs · the whole SKILL.md, loaded when a task matches

~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from pr-pm/prpm at commit 5f993e6, republished under its MIT licence (© pr-pm). 293 words, ~1,458 tokens.

name

creating-agent-skills

description

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

my-skill/                 # Must match frontmatter `name`
├── SKILL.md              # Required - main definition
├── scripts/              # Optional - executable code
├── references/           # Optional - additional docs
└── assets/               # Optional - static resources

---
name: skill-name
description: What it does and when to use it
---

---
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
---

✅ Valid: pdf-processing, code-review, data-analysis
❌ Invalid: PDF-Processing (uppercase), -pdf (leading hyphen), pdf--processing (consecutive hyphens)

# ❌ 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.

---
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.

#!/usr/bin/env python3
# scripts/extract.py
import sys
# Self-contained with clear dependencies

---
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-skill

# Codex → Copilot
mv .agents/skills/my-skill .github/skills/my-skill

# Copilot → Codex/Amp
mv .github/skills/my-skill .agents/skills/my-skill

© pr-pm, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/creating-agent-skills of pr-pm/prpm.

Open the folder on GitHubat commit 5f993e6

Used in 1 other repository

We found 1 copy of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in pr-pm/prpm, which our catalogue first saw on October 7, 2026.

• AgentWorkforce/relay.agents/skills/creating-agent-skills-skill