agent-creator

Generate Claude Code agent configurations from user requirements.

4|Updated Mar 19, 2026
One-click install
npx skills add https://github.com/ClubMediterranee/ai-core --skill agent-creator-clubmediterranee
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: agent-creator
Source: https://github.com/ClubMediterranee/ai-core/tree/main/skills/agent-creator
Command: npx skills add https://github.com/ClubMediterranee/ai-core --skill agent-creator-clubmediterranee

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Automatically convert user requirements into production-ready Claude Code agent configurations.

Core Features & Use Cases

  • Generates complete agent frontmatter with required fields (name, description, etc.) and optional fields (model, color, memory, tools)
  • Produces triggering examples and system prompts aligned with CLAUDE.md standards for reliable deployment
  • Validates output structure, includes dependencies and components discovery, and toxicity checks for safety
  • Supports both single-agent files and multi-agent swarm templates

Quick Start

To begin, provide user requirements and let the system generate a ready-to-use agent file.

Frequently Asked Questions about agent-creator

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

FAQPage Schema
How do I generate a Claude Code agent from system requirements?

To generate a Claude Code agent, provide your project requirements and the system outputs a production-ready Markdown agent file with frontmatter, system prompts, and triggering examples aligned with CLAUDE.md standards.

What frontmatter fields are included when creating Claude Code agents?

Creating Claude Code agents includes required frontmatter fields like name and description, alongside optional validated fields such as model, color, memory, tools, and dependencies for reliable deployment.

Can I generate multi-agent swarm templates or only single subagent files?

You can generate both single subagent files and multi-agent swarm templates, converting user requirements into complete configurations that follow project conventions and CLAUDE.md standards.

How are generated agent configurations validated for safe deployment?

Generated agent configurations undergo output structure validation, dependencies and components discovery, and toxicity checks to ensure safe, production-ready Claude Code deployment.

Do I need any dependencies installed to create Claude Code agents?

No dependencies are required to create Claude Code agents. The system automatically converts user requirements into validated Markdown files without external package installations.

What is the best way to automate Claude Code agent configuration creation?

Automating Claude Code agent configuration is best achieved by submitting user requirements to the generator, which produces complete Markdown files with frontmatter, system prompts, and triggering examples.