Agent Development

anthropics/claude-plugins-officialOfficial

If you're building autonomous agents for Claude Code plugins, this walks you through the complete structure: YAML frontmatter with name, description, model, color, and tools, plus the system prompt that defines behavior. The description field is critical since it determines when Claude triggers your agent, so you get specific guidance on writing triggering conditions with prose examples. Includes validation rules (identifiers must be 3-50 chars, lowercase with hyphens), best practices for system prompts (second person, step-by-step processes, quality standards), and the distinction between agents (autonomous multi-step work) versus commands (user-initiated actions). Useful whether you're writing agents manually or using AI-assisted generation.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 6
skills.sh installs: 7.9K
GitHub stars: 46.7K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/claude-plugins-official --skill agent-development --agent claude-code

Installs into .claude/skills of the current project.

Files

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

---
name: agent-identifier
description: Use this agent when [triggering conditions]. Typical triggers include [scenario 1 in prose], [scenario 2 in prose], and [scenario 3 in prose]. See "When to invoke" in the agent body for worked scenarios.
model: inherit
color: blue
tools: ["Read", "Write", "Grep"]
---

You are [agent role description]...

## When to invoke

[Two to four representative scenarios written as prose, e.g.:]
- **[Scenario name].** [What the situation looks like and what the agent should do.]
- **[Scenario name].** [Same.]

SKILL.md on GitHub