Agent Development
Agent Development for Claude Code Plugins
Overview
Agents are autonomous subprocesses that handle complex, multi-step tasks independently. Understanding agent structure, triggering conditions, and system prompt design enables creating powerful autonomous capabilities.
Key concepts:
- Agents are FOR autonomous work, commands are FOR user-initiated actions
- Markdown file format with YAML frontmatter
- Triggering via description field with examples
- System prompt defines agent behavior
- Model and color customization
Agent File Structure
Complete Format
More from claude-code-community-ireland/claude-code-resources
design-ui
This skill should be used when the user asks to "design a UI", "create a landing page", "build a dashboard", "generate a website design", "make a product page", or needs guidance on UI design patterns, accessibility standards, design tokens, or eliminating generic AI-generated design patterns (vibe-code).
12security-review
Security review checklist covering OWASP Top 10, authentication, authorization, input validation, secrets management, and common vulnerability patterns. Reference when reviewing code for security.
7design-patterns
Reference library of proven UI design patterns, component templates, and sector-specific conventions for high-quality design generation.
6architecture-decision-record
ADR format and methodology for documenting significant technical decisions with context, alternatives considered, and consequences. Use when making or documenting architectural decisions.
5pr-description
Pull request authoring standards — structured descriptions, linking issues, providing test evidence, and writing good summaries. Reference when creating or describing pull requests.
4refactoring-patterns
Safe refactoring techniques — extract method, rename, move, inline, and structural patterns. Includes code smell identification and transformation recipes. Use when refactoring code or improving structure.
4