ralph-wiggum
Autonomous task completion loop with PRD tracking and LLM memory
npx skills add majiayu000/claude-skill-registry --skill ralph-wiggum-skill --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 Wiggum Technique ## Overview The Ralph Wiggum technique is a simple but powerful pattern for autonomous AI-driven development: 1. **PRD (prd.json)**: JSON file with user stories, each having a `passes` boolean 2. **Progress file (progress.txt)**: LLM memory between iterations 3. **Loop**: Run Claude Code repeatedly until all tasks pass Named after Ralph Wiggum from The Simpsons - simple but effective. > "Me fail English? That's unpossible!" - Ralph Wiggum ## Why It Works ### The Problem with AI Coding - LLMs lose context between sessions - No persistent memory of what worked/failed - Tendency to declare victory without verification - Complex orchestration systems add overhead ### The Solution 1. **Structured task list (JSON)**: Machine-readable, hard for LLM to corrupt 2. **Progress file**: Persistent memory across iterations 3. **Verification gate**: MUST pass all checks before marking complete 4. **Git commits**: Checkpoint after each success 5. **Simple loop**: No complex orchestration needed ## Components ### 1. PRD File (plans/prd.json) ```json { "project": "My Project", "version": "1.0.0", "user_stories": [ { "id": "US-001", "epic": "Authentication", "title": "User ca
- Overview
- Why It Works
- The Problem with AI Coding
- The Solution
- Components
- 1. PRD File (plans/prd.json)
- Key Fields
- 2. Progress File (plans/progress.txt)
- 3. Verification Pipeline
- Workflow Diagram
- Invocation
- Initialize (First Time)
- Run the Loop
- Best Practices
pnpm turbo run type-check # TypeScript compilation pnpm turbo run lint # ESLint + Ruff linting pnpm turbo run test # Unit tests (Vitest/Pytest) pnpm turbo run build # Production build pnpm --filter=web test:e2e # Playwright E2E tests Unix/Mac/WSL Windows PowerShell Claude Code command git log --oneline
What does the ralph-wiggum skill do?
Autonomous task completion loop with PRD tracking and LLM memory
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ralph-wiggum-skill --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.