Help us improve
Share bugs, ideas, or general feedback.
From agent-skills
Use when creating, packaging, or distributing Agent Skills. Covers the SKILL.md specification, frontmatter schema, naming conventions, marketplace publishing, and the skills-ref validator. USE FOR: creating SKILL.md files, packaging reusable agent capabilities, marketplace publishing, frontmatter schema validation DO NOT USE FOR: project-level agent guidance (use agents-md), agent runtime configuration (use adl or cagent)
npx claudepluginhub tyler-r-kendrick/agent-skills --plugin agent-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/agent-skills:agent-skillsThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Agent Skills is an open standard from Anthropic for packaging reusable capabilities that AI agents can discover and load dynamically. A skill is a directory containing a `SKILL.md` file with YAML frontmatter metadata and Markdown instructions. Adopted by Claude, VS Code Copilot, OpenAI Codex, Cursor, and 25+ platforms.
Creates, updates, or validates SKILL.md agent skills including frontmatter authoring, bundled resource planning, and three-phase discoverability validation.
Reference for Agent Skills Open Standard. Guides authoring portable skills for Claude Code, Cursor, VS Code, and 20+ AI agents. Covers frontmatter schema, naming rules, directory structure, validation.
Scaffolds new Claude Code skills with proper structure, progressive disclosure, and bundled resource conventions.
Share bugs, ideas, or general feedback.
Agent Skills is an open standard from Anthropic for packaging reusable capabilities that AI agents can discover and load dynamically. A skill is a directory containing a SKILL.md file with YAML frontmatter metadata and Markdown instructions. Adopted by Claude, VS Code Copilot, OpenAI Codex, Cursor, and 25+ platforms.
my-skill/
SKILL.md # Required — metadata + instructions
scripts/ # Optional — executable scripts
references/ # Optional — reference documents
assets/ # Optional — supporting files
---
name: my-skill
description: "Use when working with My Framework to follow best practices."
license: MIT
metadata:
displayName: "My Skill"
category: frameworks
author: your-name
compatibility:
- claude
- copilot
allowed-tools:
- Bash
- Read
- Edit
---
# My Skill
## Overview
Instructions for the agent when this skill is activated...
## Best Practices
- Concrete guidance the agent should follow
- Code examples demonstrating correct usage
| Field | Type | Rules |
|---|---|---|
name | string | Must match directory name. Lowercase, hyphens, digits only. Max 64 chars. |
description | string | What the skill does and when to trigger it. |
| Field | Type | Description |
|---|---|---|
license | string | SPDX identifier (e.g., MIT, Apache-2.0) |
metadata | object | Arbitrary key-value pairs (category, author, tags) |
compatibility | list | Target platforms |
allowed-tools | list | Tools the skill may use |
The description field is critical for discovery — agents use it to decide when to activate the skill:
# Install the validator
pip install skills-ref
# Validate a skill
agentskills validate path/to/my-skill
# Read properties as JSON
agentskills read-properties path/to/my-skill
# Generate agent prompt XML
agentskills to-prompt path/to/my-skill
Skills can be published to marketplace repositories:
# Add skills from a marketplace
npx skills add owner/repo
# List available skills
npx skills list owner/repo
The marketplace catalog is defined in .claude-plugin/marketplace.json.
agentskills validate before publishing.