This repository provides a comprehensive collection of specialized AI agents designed to accelerate and enhance rapid development workflows. It targets developers, designers, marketers, and product managers seeking to leverage AI for specific tasks within a structured "6-day sprint" methodology. The benefit is increased efficiency and expertise across various development lifecycle stages.

How It Works

The agents are implemented as Markdown files, each containing YAML frontmatter defining its name, description, color, and available tools, followed by a detailed system prompt. This structure allows for easy organization, customization, and integration into AI-powered development environments like Claude Code. The system prompts are designed to imbue agents with specific domain expertise and operational guidelines, enabling them to perform specialized tasks effectively.

Quick Start & Requirements

• Install by cloning the repository and copying agent files to ~/.claude/agents/.
• Requires Claude Code to load and utilize the agents.
• Agents are automatically available or can be explicitly requested by name.
• Learn more: Claude Code Sub-Agents Documentation (Note: This link points to the README itself, implying the documentation is within the repo).

Highlighted Details

• Agents are organized into departments (e.g., Engineering, Design, Marketing, Product).
• Includes "Proactive Agents" that trigger automatically in specific contexts.
• Provides detailed guidelines and checklists for creating and customizing new agents.
• Outlines a "6-day sprint" philosophy for rapid iteration and development.

Maintenance & Community

The repository is maintained by contains-studio. Contributions are encouraged by following customization checklists, testing, documenting, and sharing successful patterns.

Licensing & Compatibility

The repository's license is not explicitly stated in the provided README content.

Limitations & Caveats

The effectiveness of the agents is dependent on the underlying AI model's capabilities and the quality of the system prompts. The README implies integration with "Claude Code," suggesting potential platform lock-in or specific environment requirements. Performance metrics are outlined as goals but not provided as benchmarks within the README.