ralph
Execute iterative development loop through user stories. Implements one story at a time with quality gates, commits, and learning persistence. Ships features autonomously.
npx skills add majiayu000/claude-skill-registry --skill ralph-the-human-company-ai-receptionist --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 AI Development Loop Execute the complete Ralph workflow: generate a PRD with user stories, then autonomously implement them one at a time with quality gates, commits, and learning persistence. ## Invocation ```bash /ralph <requirements> [options] ``` **Arguments:** - `<requirements>` - Feature description (inline text, file path, or URL) - `--branch NAME` - Branch name (default: auto-generated with `ralph/` prefix) - `--max-stories N` - Maximum stories to generate (default: 10) - `--max-iterations N` - Maximum iterations to run (default: from prd.json or 10) **Examples:** ```bash /ralph "Build a user authentication system with login and registration" /ralph ./requirements.md --branch ralph/auth-system /ralph "Add dark mode toggle" --max-stories 5 --max-iterations 10 ``` ## Execution Flow This skill orchestrates two phases sequentially: ### Phase 1: Planning (via /ralph-plan) 1. **Gather Requirements** - Parse input (file, URL, or inline text) 2. **Analyze Codebase** - Understand existing patterns and structure 3. **Ask Clarifying Questions** - 3-5 questions to refine scope 4. **Generate PRD** - Create atomic, testable user stories 5. **Initialize Tracking** - Cr
- Invocation
- Execution Flow
- Phase 1: Planning (via /ralph-plan)
- Phase 2: Execution (via /ralph-execute)
- How It Works
- Detailed Steps
- Step 1: Invoke /ralph-plan
- Step 2: Confirm with User
- Step 3: Invoke /ralph-execute
- Step 4: Report Completion
- Error Handling
- When to Use /ralph vs Individual Skills
- Output Files
- Credits
What does the ralph skill do?
Execute iterative development loop through user stories. Implements one story at a time with quality gates, commits, and learning persistence. Ships features autonomously.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ralph-the-human-company-ai-receptionist --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.