ralph
Autonomous agent loop for completing features. Use when asked to 'use ralph', 'ralph this', or to autonomously implement a feature end-to-end. Creates prd.json with user stories, then executes them one by one until complete.
npx skills add majiayu000/claude-skill-registry --skill ralph-main --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# 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 R
- Quick Start
- Workflow
- Step 1: Understand the Feature
- Step 2: Create prd.json
- Step 3: Run the Loop
- Critical Rules for User Stories
- Size: One Context Window
- Order: Dependencies First
- Acceptance Criteria: Verifiable
- Example
- How Ralph Executes
- Files Reference
Run ralph in current project (assumes prd.json exists)
What does the ralph skill do?
Autonomous agent loop for completing features. Use when asked to 'use ralph', 'ralph this', or to autonomously implement a feature end-to-end. Creates prd.json with user stories, then executes them one by one until complete.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ralph-main --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.