ralph-execute
Autonomously implement user stories from the PRD, running quality gates and committing after each successful story. Maintains progress across sessions. Ships features while you sleep.
npx skills add majiayu000/claude-skill-registry --skill ralph-execute --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.
--- name: ralph-execute description: Execute iterative development loop through user stories. Implements one story at a time with quality gates, commits, and learning persistence. Ships features autonomously. allowed-tools: Read, Write, Edit, Bash, Glob, Grep, TodoWrite, Task user_invocable: true argument-hint: [--max-iterations N] [--story US-XXX] [--dry-run] [--skip-blocked] --- # Ralph Execution Skill Autonomously implement user stories from the PRD, running quality gates and committing after each successful story. Maintains progress across sessions. Ships features while you sleep. ## What is Ralph? Ralph is an autonomous AI coding loop that ships features while you sleep. Each iteration is a fresh context window (keeping context small). Memory persists via git history, progress.txt, prd.json, and AGENTS.md. ## Invocation ```bash /ralph-execute [options] ``` **Arguments:** - `--max-iterations N` - Override max iterations (default: from prd.json or 10) - `--story US-XXX` - Target a specific story instead of next priority - `--dry-run` - Show what would be done without making changes - `--skip-blocked` - Skip blocked stories without re-attempting **Examples:** ```bash /ralph-execu
- What is Ralph?
- Invocation
- Execution Flow
- Phase 1: Session Initialization
- Phase 2: Story Selection
- Phase 3: Story Implementation (Compound Engineering)
- Phase 4: Loop or Complete
- Phase 5: Failure Handling
- Session Persistence
- Resuming Across Sessions
- Cross-Session Learnings
- Critical Success Factors
- 1. Small Stories
- 2. Feedback Loops
mkdir -p .ralph/archive/[old-branch]-[timestamp] mv .ralph/prd.json .ralph/archive/[old-branch]-[timestamp]/ mv .ralph/progress.txt .ralph/archive/[old-branch]-[timestamp]/ git branch --show-current git checkout [prd.branchName] npm run check 2>&1 npm run lint 2>&1 npm run test 2>&1 npm run build 2>&1 git add -A
What does the ralph-execute skill do?
Autonomously implement user stories from the PRD, running quality gates and committing after each successful story. Maintains progress across sessions. Ships features while you sleep.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ralph-execute --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.