agent-creator

Generate custom Task subagent definitions in the ~/.claude/agents/ directory.

Updated Aug 27, 2026
One-click install
npx skills add https://github.com/HTRamsey/claude-config --skill agent-creator-htramsey
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-creator
Source: https://github.com/HTRamsey/claude-config/tree/main/skills/agent-creator
Command: npx skills add https://github.com/HTRamsey/claude-config --skill agent-creator-htramsey

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps you design and generate custom Task subagents for Claude's Task tool system, enabling focused automation with clearly defined scope and boundaries.

Core Features & Use Cases

  • Agent anatomy: Shows how agents live as markdown files in ~/.claude/agents/ with a defined structure.
  • Frontmatter-driven configuration: Customize name, description, tools, and model to control routing and capabilities.
  • Creation workflow: Generate templates, edit backstories, define processing steps, and set escalation rules for robust automation.

Quick Start

Initialize a new agent using the template: ~/.claude/skills/agent-creator/scripts/init_agent.py my-agent --model haiku --description "Quick lookup for X" --tools "Read,Grep,Glob"

Frequently Asked Questions about agent-creator

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

FAQPage Schema
How do I create a custom agent for automation tasks?

Create agents by generating markdown files in ~/.claude/agents/ with defined structure, frontmatter configuration, and skeleton sections. Use the init_agent.py script to template a new agent, specifying model, description, and available tools for focused task automation.

What goes into an agent's configuration and backstory?

Agent configuration includes frontmatter fields (name, description, tools, model) and markdown sections: Backstory, Your Role, Process, Response Format, Should NOT Attempt, Escalation, and Rules. These define scope, capabilities, routing behavior, and when to escalate to human review.

Can I use subagents to break down complex workflows?

Yes. Subagents let you partition workflows by defining narrowly-scoped agents with clear boundaries and escalation rules. Each agent type routes specific tasks, preventing scope creep and enabling orchestrated automation across multiple focused agents.

How do I validate a new agent before deploying it?

Agent creation enforces functional requirements: model validation, proper frontmatter generation, and all skeleton sections. Status reporting confirms successful creation; test agent routing and escalation rules by running sample tasks through the defined agent.

What's the difference between an agent and a task subagent?

A task subagent is a specialized Claude agent defined in ~/.claude/agents/ for the Task tool system. It differs from a standalone agent by using frontmatter-driven configuration, template structure, and integration within Claude's Task orchestration layer for automated routing.

Do I need programming experience to create an agent?

No. The init_agent.py script generates templates and guides initialization. You define agent purpose, role, and escalation rules in plain markdown; no code required. Basic familiarity with command-line arguments and text editing is sufficient.