What files are mandatory for a new skill?

Every skill requires a SKILL.md file containing YAML frontmatter with 'name' and 'description' fields, plus the Markdown body instructions.

What is a Claude Code Skill?

A Skill is a modular package that extends Claude's capabilities by providing specialized knowledge, workflows, and tools tailored for specific domains or tasks.

Why is token efficiency important in skill creation?

Skills share the context window with the system prompt and conversation history; keeping skills concise ensures Claude has more room to process the actual user request.

What is the Progressive Disclosure design principle?

It is a strategy to manage context by loading information in stages: metadata first, then the SKILL.md body, and finally specific bundled resources only when needed.

When should I use scripts versus text instructions?

Use scripts in the /scripts folder for tasks requiring deterministic reliability or complex logic that would be token-expensive for Claude to rewrite repeatedly.

Claude Skill Creator

Name: Claude Skill Creator
Author: kjgarza

bykjgarza

Developer Tools

Guides developers through the end-to-end process of building, optimizing, and packaging high-quality Claude Code skills.

About

The Claude Skill Creator provides a structured framework for extending Claude's capabilities with specialized knowledge, custom workflows, and tool integrations. It helps developers adhere to core design principles like progressive disclosure and token efficiency, ensuring skills are modular, deterministic, and easy for AI agents to utilize. By following its standardized patterns for organizing scripts, references, and assets, you can transform Claude from a general-purpose model into a specialized agent equipped with company-specific logic and procedural guardrails.

Key Features

Step-by-step workflows for planning, initializing, and packaging new skills
Standardized SKILL.md generation with required YAML metadata
0 GitHub stars
Strategic frameworks for setting appropriate 'Degrees of Freedom' for AI tasks
Guidance on organizing scripts, references, and assets for maximum modularity
Best practices for progressive disclosure and context window optimization

Use Cases

Standardizing internal development workflows into reusable Claude skills
Optimizing complex AI prompts to reduce token usage and improve reliability
Building domain-specific agents with custom scripts and reference documentation

About

Key Features

Step-by-step workflows for planning, initializing, and packaging new skills
Standardized SKILL.md generation with required YAML metadata
0 GitHub stars
Strategic frameworks for setting appropriate 'Degrees of Freedom' for AI tasks
Guidance on organizing scripts, references, and assets for maximum modularity
Best practices for progressive disclosure and context window optimization

Use Cases

Standardizing internal development workflows into reusable Claude skills
Optimizing complex AI prompts to reduce token usage and improve reliability
Building domain-specific agents with custom scripts and reference documentation