claude-sub-agent

🥈Silver

AI-driven workflow system that transforms project ideas into production-ready code using specialized Claude Code Sub-Agents. Benefits operations teams by automating development workflows and coordinating AI agents in phases. Integrates with existing development tools and workflows.

572980Updated Today

Intermediate30min to implementautomation

Saves ~240 min per use

Quick InstallView Source

git clone https://github.com/zhsama/claude-sub-agent.git

Works with:

Claude

Overview

About This Skill

https://github.com/zhsama/claude-sub-agent

How to Use

[{"step":"Define the project scope clearly. Replace [PROJECT_IDEA] with a detailed description of the project, including requirements, constraints, and desired outcomes. Be specific about the tech stack (e.g., 'Python Flask backend with React frontend').","tip":"Use bullet points or numbered lists to break down complex ideas into actionable components. The more precise your input, the better the Sub-Agents can execute."},{"step":"Set up the environment. Specify the [LANGUAGE/PLATFORM] (e.g., 'Node.js with Express') and [EXISTING_TOOLS] (e.g., 'GitHub for version control, AWS ECS for deployment'). Ensure the Sub-Agents have access to these tools.","tip":"If you're unsure about the tech stack, ask the Sub-Agents to recommend one based on your project requirements. For example: 'Recommend a tech stack for a real-time chat application.'"},{"step":"Execute the phased approach. The Sub-Agents will handle the workflow automatically: 1) Generate technical specs, 2) Implement core functionality, 3) Write tests, and 4) Deploy. Monitor progress via the generated logs and outputs.","tip":"Use the 'claude-sub-agent' tool in your terminal or IDE to trigger the workflow. For example: `claude-sub-agent --project 'task-manager-api' --language 'Node.js'`."},{"step":"Review and iterate. After the Sub-Agents complete their tasks, review the generated code, tests, and documentation. Provide feedback or request adjustments if needed. For example: 'Update the database schema to include a priority field for tasks.'","tip":"Use the 'claude-sub-agent feedback' command to iterate on specific parts of the project. For example: `claude-sub-agent feedback --issue 'Add priority field to tasks' --solution 'Modify the Task model to include a priority enum.'`"},{"step":"Integrate with your workflow. Connect the generated code with your existing development tools (e.g., CI/CD pipelines, monitoring tools). For example, add the GitHub repository to your CI/CD pipeline or set up logging with ELK Stack.","tip":"Document the integration steps in the project's README file. Include any necessary configuration files or scripts to ensure smooth adoption."}]

Use Cases

Automate the creation of a task management web application with user authentication.

Generate a personal blog platform by orchestrating the entire development workflow.

Develop a CRM system with customer management and analytics features while maintaining high-quality standards.

Create a microservices-based e-commerce platform by running specific phases of development.

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/zhsama/claude-sub-agent

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Transform the project idea '[PROJECT_IDEA]' into production-ready code using a phased approach with specialized Claude Code Sub-Agents. First, generate a detailed technical specification including architecture, dependencies, and API contracts. Then, implement the core functionality in [LANGUAGE/PLATFORM]. Finally, write unit tests and integration tests, and ensure the code passes all quality checks. Use [EXISTING_TOOLS] for version control and deployment. Document the entire process in [FORMAT].

Example Output

Project Idea: Build a RESTful API for a task management system with user authentication, task CRUD operations, and real-time notifications.

**Phase 1: Technical Specification**
- Architecture: Microservice with Express.js backend, PostgreSQL database, and Redis for caching.
- Dependencies: Express, Passport.js, Sequelize ORM, Socket.io, Jest, Docker.
- API Contracts: 
  - POST /api/auth/login → { email, password } → { token }
  - GET /api/tasks → { userId } → [ { id, title, status, dueDate } ]
  - POST /api/tasks → { title, dueDate } → { id, title }
  - PUT /api/tasks/:id → { status } → { success }
  - DELETE /api/tasks/:id → { success }
- Deployment: Docker containers on AWS ECS with CI/CD via GitHub Actions.

**Phase 2: Core Implementation**
- Created a new GitHub repository 'task-manager-api' with MIT license.
- Implemented user authentication with JWT tokens using Passport.js.
- Developed task CRUD endpoints with Sequelize ORM for PostgreSQL.
- Added real-time notifications using Socket.io for task updates.
- Structured the codebase with clear separation of concerns (routes, controllers, models, services).

**Phase 3: Testing and Deployment**
- Wrote unit tests for all controllers and services using Jest (95% coverage).
- Implemented integration tests for API endpoints (Postman collection included).
- Added Dockerfile and docker-compose.yml for local development.
- Configured GitHub Actions workflow for automated testing and deployment to AWS ECS.
- Generated API documentation using Swagger/OpenAPI.

**Output:**
- GitHub repository: https://github.com/your-org/task-manager-api
- Docker images: task-manager-api:latest
- API documentation: https://api.task-manager.example.com/docs
- Deployment status: Successfully deployed to AWS ECS (Region: us-east-1, Cluster: task-manager-prod).