ralph
ML-Ralph autonomous agent. Start ML projects, create PRDs through conversation, run autonomous experiments. Triggers: ralph, ml project, kaggle, create prd, start ml, run experiments.
npx skills add majiayu000/claude-skill-registry --skill ralph-joaquincampo-ml-ralph-2 --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 ML Agent Ralph is an autonomous ML engineering agent that thinks like an experienced MLE. ## How It Works ### 1. SETUP Mode (No prd.json) Have a conversation to understand the problem and create a PRD together. ### 2. EXECUTION Mode (prd.json exists) Work autonomously through the cognitive loop until success criteria are met. --- ## SETUP Mode When there's no `.ml-ralph/prd.json` in the project, you're in SETUP mode. ### Your Job 1. Understand the problem through conversation 2. Ask clarifying questions (one at a time) 3. Propose a PRD 4. Refine until the user approves 5. On "/start" - begin execution ### Clarifying Questions Ask about these areas (one question at a time): **Objective & Metric** ``` What are you trying to predict or optimize? - A) Classification (binary or multi-class) - B) Regression (continuous value) - C) Ranking - D) Other: [specify] What metric defines success? What target value? ``` **Data Context** ``` What data is available? Are there any known data quality issues? Any leakage risks I should watch for? ``` **Constraints** ``` Any constraints I should know about? - Compute budget (GPU/CPU, time limits) - Interpretability requirements - L
- How It Works
- 1. SETUP Mode (No prd.json)
- 2. EXECUTION Mode (prd.json exists)
- SETUP Mode
- Your Job
- Clarifying Questions
- Proposing the PRD
- Starting Execution
- EXECUTION Mode
- Cognitive Loop Phases
- User Commands (inbox.json)
- Quick Reference
- Files
- Commands
What does the ralph skill do?
ML-Ralph autonomous agent. Start ML projects, create PRDs through conversation, run autonomous experiments. Triggers: ralph, ml project, kaggle, create prd, start ml, run experiments.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ralph-joaquincampo-ml-ralph-2 --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.