subagent-creator

Create Claude Code sub-agents with YAML frontmatter and system prompts.

434|168|Updated Dec 1, 2025
One-click install
npx skills add https://github.com/greatSumini/cc-system --skill subagent-creator-greatsumini
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: subagent-creator
Source: https://github.com/greatSumini/cc-system/tree/main/.claude/skills/subagent-creator
Command: npx skills add https://github.com/greatSumini/cc-system --skill subagent-creator-greatsumini

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill enables creating specialized Claude Code sub-agents with custom system prompts, tool configurations, and optional skill loading for domain-specific workflows.

Core Features & Use Cases

  • Structured sub-agent files: YAML frontmatter defining name, description, tools, model, and permissions.
  • Scope configuration: Choose between project (.claude/agents/) or user (~/.claude/agents/) storage.
  • System prompt guidance: Provide clear role, responsibilities, and output format for delegation.

Quick Start

Create a new sub-agent file under the appropriate directory with the required frontmatter and system prompt.

Frequently Asked Questions about subagent-creator

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

FAQPage Schema
How do I create specialized sub-agents with custom prompts and tools?

Create a sub-agent by defining a Markdown file with YAML frontmatter specifying name, description, system prompt, tools, and model configuration, then store it in either `.claude/agents/` (project scope) or `~/.claude/agents/` (user scope) for delegation workflows.

What's the difference between project-scoped and user-scoped sub-agent storage?

Project-scoped agents (`.claude/agents/`) apply only within a specific project, while user-scoped agents (`~/.claude/agents/`) are available across all projects, letting you choose between workflow isolation and reusability.

Can I use sub-agents for code review, debugging, and security auditing?

Yes, sub-agents support domain-specific workflows including code review, debugging, data science, and security auditing by tailoring system prompts, tool permissions, and model configuration to each task.

Do sub-agents support skill loading and tool configuration?

Sub-agents support custom tool configurations and optional skill loading, enabling you to restrict capabilities per agent and compose specialized workflows with precise permission scoping.

What frontmatter fields are required for a valid sub-agent file?

Required frontmatter includes name, description, system prompt role and responsibilities, tools array, model selection, and permissions, validated through structured YAML schema during sub-agent creation.

How do I delegate tasks across projects using multiple sub-agents?

Define sub-agents with distinct system prompts and tool sets, store them at project or user scope, then reference them for auto-delegation to handle specialized tasks without context switching.