Claude Code Requirements Builder

An intelligent requirements gathering system for Claude Code that progressively builds context through automated discovery, asks simple yes/no questions, and generates comprehensive requirements documentation.

This system transforms the requirements gathering process by:

• Codebase-Aware Questions: AI analyzes your code first, then asks informed questions
• Simple Yes/No Format: All questions are yes/no with smart defaults - just say "idk" to use defaults
• Two-Phase Questioning: 5 high-level questions for context, then 5 expert questions after code analysis
• Automated Documentation: Generates comprehensive specs with specific file paths and patterns
• Product Manager Friendly: No code knowledge required to answer questions

AI analyzes the entire codebase structure to understand the architecture, tech stack, and patterns.

The AI asks 5 yes/no questions to understand the problem space:

AI autonomously:

• Searches for specific files based on discovery answers
• Reads relevant code sections
• Analyzes similar features in detail
• Documents technical constraints and patterns

With deep context, asks 5 detailed yes/no questions:

Generates comprehensive spec with:

• Problem statement and solution overview
• Functional requirements from all 10 answers
• Technical requirements with specific file paths
• Implementation patterns to follow
• Acceptance criteria

Begins gathering requirements for a new feature or change.

Example:

Shows current requirement progress and continues gathering.

Output:

Finalizes current requirement, even if incomplete.

Options:

1. Generate spec with current info
2. Mark incomplete for later
3. Cancel and delete

Shows all requirements with their status.

Output:

Reminds AI to follow requirements gathering rules.

Use when AI:

• Asks open-ended questions
• Starts implementing code
• Asks multiple questions at once

Every question includes an intelligent default based on:

• Best practices
• Codebase patterns
• Context discovered

• Phase 1: Analyzes codebase structure first
• Phase 2: 5 high-level questions for product managers
• Phase 3: Autonomous deep dive into relevant code
• Phase 4: 5 expert questions based on code understanding

• All files created automatically
• Progress tracked between sessions
• Can resume anytime

• Links to development sessions
• References PRs and commits
• Searchable requirement history

1. Be Specific: Clear initial descriptions help AI ask better questions
2. Use Defaults: "idk" is perfectly fine - defaults are well-reasoned
3. Stay Focused: Use /remind if AI goes off track
4. Complete When Ready: Don't feel obligated to answer every question

1. One Feature at a Time: Keep requirements focused
2. Think Implementation: Consider how another AI will use this
3. Document Decisions: The "why" is as important as the "what"
4. Link Everything: Connect requirements to sessions and PRs

1. Clone this repository:

2. Copy the commands to your project:

3. Create requirements directory:

4. Add to .gitignore if needed:

1. Fork the repository
2. Create your feature branch
3. Add new commands or improve existing ones
4. Submit a pull request

• Add requirement templates for common features
• Create requirement validation commands
• Build requirement-to-implementation tracking
• Add multi-language question support

MIT License - Feel free to use and modify for your projects.

Inspired by @iannuttall's claude-sessions project, which pioneered the concept of structured session management for Claude Code.

Remember: Good requirements today prevent confusion tomorrow!