skill-development

Guide creation and organization of Claude Code plugin skills with SKILL.md.

6|Updated Feb 25, 2026
One-click install
npx skills add https://github.com/archibate/archibate-skills --skill skill-development-archibate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-development
Source: https://github.com/archibate/archibate-skills/tree/main/skills/skill-development
Command: npx skills add https://github.com/archibate/archibate-skills --skill skill-development-archibate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Provide structured, repeatable guidance for creating, organizing, and validating Claude Code plugin skills so that plugins expose reliable, discoverable, and context-efficient capabilities to Claude agents. Reduce confusion about frontmatter requirements, writing style, and where to place scripts, references, and assets to enable progressive disclosure and maintainable skills.

Core Features & Use Cases

  • Authoring guidance: Specify YAML frontmatter requirements, recommended trigger phrases, and imperative writing style to ensure correct skill discovery and activation.
  • Structure & resources: Recommend layouts for SKILL.md, references, examples, and scripts and explain when to move details into references or assets for efficient context loading.
  • Validation & testing: Provide a checklist for validating frontmatter, trigger quality, resource existence, and progressive disclosure, useful when packaging or reviewing plugin skills.

Quick Start

Ask Claude to generate a concise SKILL.md with third-person frontmatter, imperative instructions, and pointers to any supporting references, examples, or scripts for the new plugin skill.

Frequently Asked Questions about skill-development

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

FAQPage Schema
How do I write YAML frontmatter for a Claude Code plugin skill?

YAML frontmatter for Claude Code skills requires third-person metadata fields and recommended trigger phrases to ensure correct skill discovery and activation by agents. Following these frontmatter requirements guarantees reliable plugin integration.

What is progressive disclosure in skill development and when should I use it?

Progressive disclosure is an organizational design that moves detailed instructions into separate reference files, loading context efficiently only when needed. Use it to maintain maintainable skills and reduce token consumption during agent execution.

How to structure a SKILL.md file with references, examples, and scripts?

Structure SKILL.md by writing concise imperative instructions at the top level, then organizing supporting references, examples, and scripts into dedicated subdirectories. This layout enables progressive disclosure and efficient context loading for Claude agents.

What's the best way to validate trigger phrases for Claude Code skills?

Validate trigger phrases by running a checklist that tests frontmatter accuracy, trigger quality, resource existence, and progressive disclosure behavior. This validation process ensures plugin-distributed skills activate reliably during agent interactions.

Why does my Claude Code skill fail to activate despite correct frontmatter?

Skill activation failures often stem from poor trigger phrase quality, missing referenced resource files, or non-imperative writing style in SKILL.md. Validate your progressive disclosure design and ensure all referenced scripts and examples exist.

Do I need to use imperative writing style for Claude Code plugin development?

Yes, imperative writing style is required for Claude Code plugin development to ensure clear, direct instructions for agent execution. This style standardizes skill behavior and improves the reliability of automated task completion.