ralphlisted

# Ralph - Autonomous Feature Implementation Ralph is an autonomous loop that implements features by breaking them into small user stories and completing them one at a time. Each iteration is a fresh agent with clean context. Memory persists via git, `progress.txt`, and `prd.json`. ## Quick Start ```bash # Run ralph in current project (assumes prd.json exists) ~/skills/ralph/scripts/ralph.sh [max_iterations] ``` ## Workflow ### Step 1: Understand the Feature Ask clarifying questions if needed: - What problem does this solve? - What are the key user actions? - What's out of scope? - How do we know it's done? ### Step 2: Create prd.json Generate a `prd.json` file in the project root: ```json { "project": "[Project Name]", "branchName": "ralph/[feature-name-kebab-case]", "description": "[Feature description]", "userStories": [ { "id": "US-001", "title": "[Story title]", "description": "As a [user], I want [feature] so that [benefit]", "acceptanceCriteria": [ "Criterion 1", "Criterion 2", "Typecheck passes" ], "priority": 1, "passes": false, "notes": "" } ] } ``` ### Step 3: Run the Loop ```bash ~/skills/ralph/scripts/ralph.sh [max_iterations] ``` Default is 10 iterations. ## Critical Rules for User Stories ### Size: One Context Window Each story MUST be completable in ONE iteration. If you can't describe it in 2-3 sentences, it's too big. **Right-sized:** - Add a database col