mvp-builder
🥈SilverDocument-Driven Development framework for Claude Code . structured specs, TDD cycles, feedback loops, and skills system
1010Updated 3mo ago
Intermediate30min to implementautomation
Saves ~180 min per use
Quick InstallView Source
git clone https://github.com/petbrains/mvp-builder.gitWorks with:
Claude
Overview
About This Skill
MVP Builder is a Document-Driven Development framework that transforms how Claude Code builds products. It enforces a structured pipeline from product requirements through design and implementation, with TDD cycles and mandatory self-review to catch incomplete code before shipping. Instead of relying on prompts alone, MVP Builder uses specification documents that map directly to tests and implementation tasks, making progress verifiable and sessions persistent across context resets. The framework prevents common AI coding failures—hallucinations, stub implementations, and context loss—through atomic commits, review feedback loops, and a skills system that extends capabilities without modifying core agents. Teams building MVPs with Claude Code gain enforced quality gates, architectural clarity, and a reusable template that scales from single features to full projects.
How to Use
Run the install script (`curl -fsSL https://raw.githubusercontent.com/petbrains/mvp-builder/main/scripts/install.sh | bash` on macOS/Linux, or the PowerShell equivalent on Windows) to set up `.claude/` directory, `CLAUDE.md`, and MCP configuration. Start with `/docs:prd` in Claude Code to generate your product requirements and design references. Follow the pipeline through Define → Design → Build → Ship phases using the documented commands and agents.
Use Cases
Building production-ready MVPs with Claude Code without manual debugging of incomplete features
Enforcing TDD workflows across AI-assisted development with automatic RED-GREEN cycles
Maintaining context and progress across multiple Claude sessions using persistent specification documents
Standardizing design-to-code workflows with Figma integration and component mapping
Tags
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/petbrains/mvp-builderRequirements
- Claude Code or compatible AI agent
- Works with: Claude
Quick Start Guide
1
Install the Skill
Copy the install command above and run it in your terminal.
2
Open Your AI Agent
Launch Claude Code, Cursor, or your preferred AI coding agent.
3
Try It Out
Use the prompt template or examples below to test the skill.
4
Customize
Adapt the skill to your specific use case and workflow.
Usage Examples
Prompt Template
Act as an MVP Builder for a [COMPANY] in the [INDUSTRY] sector. Using the Document-Driven Development framework, create a structured specification for a minimum viable product (MVP) based on the following [DATA]. Include TDD cycles, feedback loops, and a skills system. Focus on key features, user flows, and technical requirements.
Example Output
# MVP Builder: E-Commerce Platform for GreenTech Solutions ## **1. Overview** - **Company**: GreenTech Solutions - **Industry**: E-Commerce - **Objective**: Develop an MVP for an online platform selling sustainable products. ## **2. Key Features** - **User Registration & Authentication**: Secure sign-up and login. - **Product Catalog**: Display sustainable products with filters. - **Shopping Cart & Checkout**: Seamless purchase process. - **User Reviews & Ratings**: Allow customers to leave feedback. ## **3. User Flows** 1. **Browse Products**: Users can search and filter products. 2. **Add to Cart**: Users can add products to their cart. 3. **Checkout**: Users can proceed to checkout and complete the purchase. 4. **Leave Review**: Users can leave a review after purchase. ## **4. Technical Requirements** - **Frontend**: React.js for dynamic user interfaces. - **Backend**: Node.js with Express for server-side logic. - **Database**: MongoDB for storing product and user data. - **Authentication**: JWT for secure user authentication. ## **5. Feedback Loops & TDD Cycles** - **User Feedback**: Collect feedback post-purchase to improve the platform. - **TDD Cycles**: Implement test-driven development to ensure code quality. - **Skills System**: Integrate a skills system to track user engagement and preferences. ## **6. Next Steps** - **Prototype Development**: Start with a basic prototype. - **User Testing**: Conduct user testing to gather feedback. - **Iterative Development**: Continuously improve based on feedback.
Apply to these tools
Browse all toolsRive
Create and collaborate on interactive animations with powerful, user-friendly tools.
Claude
AI assistant built for thoughtful, nuanced conversation
Microsoft Teams
Get more done every day with Microsoft Teams – powered by AI
GPT for work
Automate your spreadsheet tasks with AI power
Respell
Agentic AI Workflow platform
Notion
Connected workspace for docs, wikis, and projects
Compatible MCP servers
Browse all MCP servers
Find the right skills for your stack
Take a free 3-minute scan and get personalized AI skill recommendations.
Take free scan