Where should I store my Claude Code skills?

Skills should be organized in a directory structure following the pattern 'skills/[skill-name]/SKILL.md', allowing Claude to discover the skill and its supporting files.

What is a Claude Code skill?

A Claude Code skill is a specialized capability that enhances Claude's behavior during specific tasks through domain-specific guidance, best practices, and implementation patterns.

What is the purpose of the allowed-tools field?

The allowed-tools field restricts which tools (like Read, Write, or Bash) a specific skill can access, improving security and keeping the AI focused on the task at hand.

How does a skill differ from a command?

Skills are invoked autonomously by Claude based on conversation context and triggers, whereas commands are explicitly executed by the user using a /command-name syntax.

Claude Skill Development Guide

Name: Claude Skill Development Guide
Author: shawn-sandy

byshawn-sandy

•

Learning & Documentation

Provides a standardized framework and best practices for creating custom Claude Code skills.

About

This skill serves as a comprehensive reference for developers looking to extend Claude's capabilities through custom skill development. It offers clear guidance on file structures, frontmatter configuration, and the critical distinction between skills, commands, and agents, ensuring that developers can build robust, autonomous extensions for their AI-powered workflows.

Key Features

Practical examples of frontmatter and SKILL.md configuration
Automated skill structure templates and boilerplate
Architectural comparison of skills, commands, and agents
1 GitHub stars
Detailed guidance on writing effective trigger descriptions
Security best practices for tool permission management

Use Cases

Standardizing documentation for internal team skill development
Learning how to create a new Claude Code skill from scratch
Optimizing skill invocation triggers for better autonomous behavior

About

Key Features

Practical examples of frontmatter and SKILL.md configuration
Automated skill structure templates and boilerplate
Architectural comparison of skills, commands, and agents
1 GitHub stars
Detailed guidance on writing effective trigger descriptions
Security best practices for tool permission management

Use Cases

Standardizing documentation for internal team skill development
Learning how to create a new Claude Code skill from scratch
Optimizing skill invocation triggers for better autonomous behavior