Agent skill · AI & Agents

ralph

Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert to ralph, convert this prd, turn this into ralph format, create prd.json, ralph json, run ralph on this.

majiayu000github.com/majiayu000GitHub ↗
claude-codeMIT
Install
npx skills add majiayu000/claude-skill-registry --skill ralph-grenos-gh-viewer --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 8 KB
Bundled scripts: none
Path: skills/agent/ralph-grenos-gh-viewer/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Ralph PRD Converter Converts existing markdown PRDs to the `prd.json` format that Ralph uses for autonomous execution. --- ## The Job 1. Read the PRD from `tasks/prd-[feature-name].md` (or ask user which PRD) 2. Convert user stories to properly-sized JSON entries 3. Validate story sizing and dependencies 4. Save to `ralph-cc/prd.json` --- ## Story Size: The Number One Rule > **Each story must be completable in ONE Ralph iteration (one context window).** Ralph spawns a fresh Claude Code instance per iteration with no memory of previous work. If a story is too big, Claude runs out of context before finishing and produces broken code. ### Right-sized stories (GOOD): - Add a TypeScript type/interface - Create a single component - Add a Zustand store - Create a custom hook - Add translations to i18n - Update a configuration file ### Too big (SPLIT THESE): - "Build the entire feature" → Split into: types, store, hooks, components, screen - "Add authentication" → Split into: types, store, hook, UI components, routes - "Create a dashboard" → Split into: types, data hooks, individual cards, layout ### Rule of Thumb If you cannot describe the change in 2-3 sentences, it is too big. --- ##

What's inside
Steps it walks through
  1. The Job
  2. Story Size: The Number One Rule
  3. Right-sized stories (GOOD):
  4. Too big (SPLIT THESE):
  5. Rule of Thumb
  6. Story Ordering: Dependencies First
  7. Output Format
  8. Acceptance Criteria: Must Be Verifiable
  9. Good criteria (verifiable):
  10. Bad criteria (vague):
  11. Always include:
  12. Conversion Rules
  13. Splitting Large Stories
  14. Archiving Previous Runs
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the ralph skill do?

Convert PRDs to prd.json format for the Ralph autonomous agent system. Use when you have an existing PRD and need to convert it to Ralph's JSON format. Triggers on: convert to ralph, convert this prd, turn this into ralph format, create prd.json, ralph json, run ralph on this.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill ralph-grenos-gh-viewer --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.

Keep going