Subagent System

What problem does it solve?

This Skill guides you in creating and managing specialized Claude Code subagents, allowing you to delegate task-specific workflows to pre-configured AI personalities. It solves the problem of maintaining context, leveraging specialized expertise, and applying flexible permissions for complex, multi-faceted tasks.

Core Features & Use Cases

• Specialized AI Personalities: Define subagents with custom system prompts, specific tools, and separate context windows.
• Automatic & Explicit Delegation: Claude can proactively delegate tasks based on descriptions, or you can explicitly invoke subagents by name.
• Use Case: When you have a complex task like "review code for security issues and then fix failing tests," you can delegate the security review to a code-reviewer subagent and the test fixing to a test-runner subagent, ensuring each part of the task is handled by a specialist.

Quick Start

Open the interactive subagents interface

/agents

Or create a project-scoped subagent manually

mkdir -p .claude/agents

Then create a Markdown file like .claude/agents/test-runner.md

---

name: test-runner

description: Use proactively to run tests and fix failures

---

You are a test automation expert...