create-agent-skills

Create Claude Code agent skills with valid YAML frontmatter and gerund-based naming.

5|Updated Mar 27, 2026
One-click install
npx skills add https://github.com/barkleesanders/claude-code-starter --skill create-agent-skills-barkleesanders
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: create-agent-skills
Source: https://github.com/barkleesanders/claude-code-starter/tree/main/skills/create-agent-skills
Command: npx skills add https://github.com/barkleesanders/claude-code-starter --skill create-agent-skills-barkleesanders

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill eliminates the risk of creating inconsistent, non-compliant agent skills that fail to integrate with Claude Code or get discovered by users, ensuring all custom skills follow official structural and content guidelines for reliable performance.

Core Features & Use Cases

  • Audit Checklist: Built-in validation to confirm skills meet all requirements for valid structure, frontmatter formatting, and content quality.
  • Guideline Enforcement: Clear rules for required YAML frontmatter fields, gerund-based naming conventions, and progressive disclosure to keep skill files maintainable.
  • Anti-Pattern Avoidance: Explicit guidance to skip common mistakes like using XML tags, writing vague descriptions, deep nesting, and including too many configuration options.
  • Use Case: A developer building a custom skill for automated code review can use this Skill to ensure their skill's name follows the required gerund format, its description includes relevant trigger keywords, and its content is split into manageable reference files to avoid context overload.

Quick Start

Use the create-agent-skills skill to build a new skill for processing PDF documents that passes all built-in audit checks and follows official Claude Code skill guidelines.

Frequently Asked Questions about create-agent-skills

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I structure agent skills for Claude Code to ensure they are discovered correctly?

To structure agent skills for Claude Code correctly, use valid YAML frontmatter, gerund-based naming conventions, and progressive disclosure to split content into manageable reference files, ensuring reliable integration and discovery within the agent ecosystem.

What are common anti-patterns to avoid during Claude Code skill creation?

Common anti-patterns in Claude Code skill creation include using XML tags, writing vague descriptions, deep nesting, and including too many configuration options; avoiding these mistakes keeps skill files maintainable and prevents integration failures.

What is progressive disclosure when building custom agent skills?

Progressive disclosure is a structural guideline for building custom agent skills that splits content into manageable reference files to avoid context overload, keeping skill files maintainable and ensuring correct integration with Claude Code.

How do I audit an existing custom skill to verify it meets Claude Code guidelines?

You can audit an existing custom skill using a built-in validation checklist to confirm it meets requirements for valid YAML frontmatter formatting, gerund-based naming conventions, and content quality, ensuring it passes Claude Code skill guidelines.

Does my prompt engineering workflow require specific YAML frontmatter fields for Claude Code skill creation?

Yes, Claude Code skill creation requires specific YAML frontmatter fields and clear rules for gerund-based naming conventions to ensure the custom skill integrates properly and is discovered by users in the agent ecosystem.