ralph
Skill0 starsChanged 9 months agoMITView on GitHub
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 this prd, turn this into ralph format, create prd.json from this, ralph json.
We split this skill into the rules it gives an agent
12 rules. 0 are common, 6 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 34 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 53
Add a database column and migration
- Distinctive: line 54
Add a UI component to an existing page
- Distinctive: line 55
Update a server action with new logic
- Distinctive: line 56
Add a filter dropdown to a list
- Distinctive: line 63
Rule of thumb: If you cannot describe the change in 2-3 sentences, it is too big.
- Distinctive: line 132
If a PRD has big features, split them:
- Very specific: line 237
Read the current prd.json if it exists
- Very specific: line 238
Check if branchName differs from the new feature's branch name
- Very specific: line 239
If different AND progress.txt has content beyond the header:
- Very specific: line 240
Create archive folder: archive/YYYY-MM-DD-feature-name/
- Very specific: line 244
The ralph.sh script handles this automatically: when you run it, but if you are manually updating prd.json between runs, archive first.
- Very specific: line 250
Before writing prd.json, verify:
“Common” is measured: kept by at least 6 in 10 of the 34 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Ralph PRD Converter
Converts existing PRDs to the prd.json format that Ralph uses for autonomous execution.
The Job
Take a PRD (markdown file or text) and convert it to prd.json in your ralph directory.
Output Format
{
"project": "[Project Name]",
"branchName": "ralph/[feature-name-kebab-case]",
"description": "[Feature description from PRD title/intro]",
"userStories": [
{
"id": "US-001",
"title": "[Story title]",
"description": "As a [user], I want [feature] so that [benefit]",
"acceptanceCriteria": [
"Criterion 1",
"Criterion 2",
"Typecheck passes"
],
"priority": 1,
"passes": false,
"notes": ""
}
]
}Story Size: The Number One Rule
Each story must be completable in ONE Ralph iteration (one context window).
Ralph spawns a fresh Amp instance per iteration with no memory of previous work. If a story is too big, the LLM runs out of context before finishing and produces broken code.
Right-sized stories:
- Add a database column and migration
- Add a UI component to an existing page
- Update a server action with new logic
- Add a filter dropdown to a list
Too big (split these):
- "Build the entire dashboard" - Split into: schema, queries, UI components, filters
- "Add authentication" - Split into: schema, middleware, login UI, session handling
- "Refactor the API" - Split into one story per endpoint or pattern
Rule of thumb: If you cannot describe the change in 2-3 sentences, it is too big.
Story Ordering: Dependencies First
Stories execute in priority order. Earlier stories must not depend on later ones.
Correct order:
- Schema/database changes (migrations)
- Server actions / backend logic
- UI components that use the backend
- Dashboard/summary views that aggregate data
Wrong order:
- UI component (depends on schema that does not exist yet)
- Schema change
Acceptance Criteria: Must Be Verifiable
Each criterion must be something Ralph can CHECK, not something vague.
Good criteria (verifiable):
- "Add
statuscolumn to tasks table with default 'pending'" - "Filter dropdown has options: All, Active, Completed"
- "Clicking delete shows confirmation dialog"
- "Typecheck passes"
- "Tests pass"
Bad criteria (vague):
- "Works correctly"
- "User can do X easily"
- "Good UX"
- "Handles edge cases"
Always include as final criterion:
"Typecheck passes"For stories with testable logic, also include:
"Tests pass"For stories that change UI, also include:
"Verify in browser using dev-browser skill"Frontend stories are NOT complete until visually verified. Ralph will use the dev-browser skill to navigate to the page, interact with the UI, and confirm changes work.
Conversion Rules
- Each user story becomes one JSON entry
- IDs: Sequential (US-001, US-002, etc.)
- Priority: Based on dependency order, then document order
- All stories:
passes: falseand emptynotes - branchName: Derive from feature name, kebab-case, prefixed with
ralph/ - Always add: "Typecheck passes" to every story's acceptance criteria
Splitting Large PRDs
If a PRD has big features, split them:
Original:
"Add user notification system"
Split into:
- US-001: Add notifications table to database
- US-002: Create notification service for sending notifications
- US-003: Add notification bell icon to header
- US-004: Create notification dropdown panel
- US-005: Add mark-as-read functionality
- US-006: Add notification preferences page
Each is one focused change that can be completed and verified independently.
Example
Input PRD:
# Task Status Feature
Add ability to mark tasks with different statuses.
## Requirements
- Toggle between pending/in-progress/done on task list
- Filter list by status
- Show status badge on each task
- Persist status in databaseOutput prd.json:
{
"project": "TaskApp",
"branchName": "ralph/task-status",
"description": "Task Status Feature - Track task progress with status indicators",
"userStories": [
{
"id": "US-001",
"title": "Add status field to tasks table",
"description": "As a developer, I need to store task status in the database.",
"acceptanceCriteria": [
"Add status column: 'pending' | 'in_progress' | 'done' (default 'pending')",
"Generate and run migration successfully",
"Typecheck passes"
],
"priority": 1,
"passes": false,
"notes": ""
},
{
"id": "US-002",
"title": "Display status badge on task cards",
"description": "As a user, I want to see task status at a glance.",
"acceptanceCriteria": [
"Each task card shows colored status badge",
"Badge colors: gray=pending, blue=in_progress, green=done",
"Typecheck passes",
"Verify in browser using dev-browser skill"
],
"priority": 2,
"passes": false,
"notes": ""
},
{
"id": "US-003",
"title": "Add status toggle to task list rows",
"description": "As a user, I want to change task status directly from the list.",
"acceptanceCriteria": [
"Each row has status dropdown or toggle",
"Changing status saves immediately",
"UI updates without page refresh",
"Typecheck passes",
"Verify in browser using dev-browser skill"
],
"priority": 3,
"passes": false,
"notes": ""
},
{
"id": "US-004",
"title": "Filter tasks by status",
"description": "As a user, I want to filter the list to see only certain statuses.",
"acceptanceCriteria": [
"Filter dropdown: All | Pending | In Progress | Done",
"Filter persists in URL params",
"Typecheck passes",
"Verify in browser using dev-browser skill"
],
"priority": 4,
"passes": false,
"notes": ""
}
]
}Archiving Previous Runs
Before writing a new prd.json, check if there is an existing one from a different feature:
- Read the current
prd.jsonif it exists - Check if
branchNamediffers from the new feature's branch name - If different AND
progress.txthas content beyond the header:- Create archive folder:
archive/YYYY-MM-DD-feature-name/ - Copy current
prd.jsonandprogress.txtto archive - Reset
progress.txtwith fresh header
- Create archive folder:
The ralph.sh script handles this automatically when you run it, but if you are manually updating prd.json between runs, archive first.
Checklist Before Saving
Before writing prd.json, verify:
- Previous run archived (if prd.json exists with different branchName, archive it first)
- Each story is completable in one iteration (small enough)
- Stories are ordered by dependency (schema to backend to UI)
- Every story has "Typecheck passes" as criterion
- UI stories have "Verify in browser using dev-browser skill" as criterion
- Acceptance criteria are verifiable (not vague)
- No story depends on a later story
Other versions43 projects use a version of this.
Word for word · 5
- snarktank/ralph★ 22k100% same
- Bradymck/claude-code-harness★ 2100% same
- richardwu/agent-skills★ 2100% same
- Throokie/claude-code-skills★ 1100% same
- tylerprogramming/claude-skills★ 0100% same
Edited · 8
- jellydn/my-ai-tools★ 12695% same
- simone-rizzo/ralph-wiggum-claude-code-★ 16100% same
- Dr4gon42/ralph★ 223% same
- pepebot-space/skills★ 216% same
- diego-tobalina/vibe-coding★ 199% same
- igianni84/ralph-potenziato★ 173% same
- morshed272/claude-build-workflow★ 192% same
- MortuisVMain/ai-agent-superpowers★ 082% same
Wrote their own version · 30
- Yeachan-Heo/oh-my-claudecode★ 40ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 40ksame name
- Yeachan-Heo/oh-my-codex★ 34ksame name
- Q00/ouroboros★ 6.3ksame name
- zereight/gitlab-mcp★ 2.1ksame name
- srid/emanote★ 963same name
- opentabs-dev/opentabs★ 926same name
- first-fluke/fullstack-starter★ 223same name
- team-attention/hoyeon★ 173same name
- Open-Harness/open-harness★ 17same name
20 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use cancel, configure-notifications and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
ibahgatSkillcancel
Gracefully stop active autonomous workflow, preserve progress, and produce a resume-ready handoff.
Also in 9 projects that use this
Jurel89Skillconfigure-notifications
Wire Telegram / Discord / Slack notifications for copilot-omni run events (start, progress, completion, error)
Also in 4 projects that use this
ibahgatSkillralplan
Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.
Also in 7 projects that use this
zephyrpersonalSkillultrawork
Obsessive task completion mode (Sisyphus Mode) - activates maximum intensity work with todo continuation enforcement
Also in 7 projects that use this
Jurel89Skillai-slop-cleaner
Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode
Also in 5 projects that use this
JokerRunSkillcompound-engineering
Compound Engineering workflow for AI-assisted development. Use when planning features, executing work, reviewing code, or codifying learnings. Follows the Plan → Work → Review → Compound loop where each unit of engineering makes subsequent work easier. Triggers on: plan this feature, implement this, review this code, compound learnings, create implementation plan, systematic development.
Also in 3 projects that use this
- +3 more from Jurel89
- +1 more from ibahgat
In this repository29 other files it gives its agents.
- .agents/skills/vercel-composition-patterns/AGENTS.mdAGENTS.md
- .agents/skills/vercel-react-best-practices/AGENTS.mdAGENTS.md
- agent-browserSkill
- ai-sdkSkill
- algorithmic-artSkill
- audit-websiteSkill
- before-and-afterSkill
- core-web-vitalsSkill
- find-skillsSkill
- frontend-designSkill
- mcp-builderSkill
- next-best-practicesSkill
- pdfSkill
- performanceSkill
- prdSkill
- programmatic-seoSkill
- seo-auditSkill
- skill-creatorSkill
- theme-factorySkill
- ui-ux-pro-maxSkill
- using-git-worktreesSkill
- vercel-composition-patternsSkill
- vercel-react-best-practicesSkill
- webapp-testingSkill
- web-design-guidelinesSkill
- cold-outreachSkill
- continuous-claudemd-updatesSkill
- design-tasteSkill
- pr-review-handlerSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

