agentleFS
jellydnjellydn/my-ai-tools/skills/ralph/SKILL.md

ralph

Skill127 starsChanged 26 days agoMITView on GitHub

Convert PRDs to prd.json format for the Ralph autonomous agent system

45 other projects use a version of this, 14 of them edited.

Adopted by

Most recently taken up by

Used with

Projects with it also use ultrawork, cancel 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.
  • zephyrpersonalSkill

    ultrawork

    Obsessive task completion mode (Sisyphus Mode) - activates maximum intensity work with todo continuation enforcement

    Also in 7 projects that use this

  • woosikkimSkill

    cancel

    Clear any stale OMC-Slim state

    Also in 7 projects that use this

  • ibahgatSkill

    ralplan

    Create a strict, quality-first execution plan with explicit gates and rollback-ready sequencing.

    Also in 5 projects that use this

  • Jurel89Skill

    ultraqa

    QA cycling loop — build/lint/test, fix, retry up to 5 cycles

    Also in 3 projects that use this

  • JokerRunSkill

    compound-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

  • Jurel89Skill

    ai-slop-cleaner

    Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode

    Also in 3 projects that use this

The file

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 41 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
  1. Distinctive:

    Add a database column and migration

    line 57
  2. Distinctive:

    Add a UI component to an existing page

    line 58
  3. Distinctive:

    Update a server action with new logic

    line 59
  4. Distinctive:

    Add a filter dropdown to a list

    line 60
  5. Distinctive:

    Rule of thumb: If you cannot describe the change in 2-3 sentences, it is too big.

    line 68
  6. Distinctive:

    If a PRD has big features, split them:

    line 144
  7. Very specific:

    Read the current prd.json if it exists

    line 254
  8. Very specific:

    Check if branchName differs from the new feature's branch name

    line 255
  9. Very specific:

    If different AND progress.txt has content beyond the header:

    line 256
  10. Very specific:

    Create archive folder: archive/YYYY-MM-DD-feature-name/

    line 257
  11. Very specific:

    The ralph.sh script handles this automatically: when you run it, but if you are manually updating prd.json between runs, archive first.

    line 261
  12. Very specific:

    Before writing prd.json, verify:

    line 267

“Common” is measured: kept by at least 6 in 10 of the 41 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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:

  1. Schema/database changes (migrations)
  2. Server actions / backend logic
  3. UI components that use the backend
  4. Dashboard/summary views that aggregate data

Wrong order:

  1. UI component (depends on schema that does not exist yet)
  2. Schema change

Acceptance Criteria: Must Be Verifiable

Each criterion must be something Ralph can CHECK, not something vague.

Good criteria (verifiable):

  • "Add status column 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

  1. Each user story becomes one JSON entry
  2. IDs: Sequential (US-001, US-002, etc.)
  3. Priority: Based on dependency order, then document order
  4. All stories: passes: false and empty notes
  5. branchName: Derive from feature name, kebab-case, prefixed with ralph/
  6. 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:

  1. US-001: Add notifications table to database
  2. US-002: Create notification service for sending notifications
  3. US-003: Add notification bell icon to header
  4. US-004: Create notification dropdown panel
  5. US-005: Add mark-as-read functionality
  6. 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 database

Output 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:

  1. Read the current prd.json if it exists
  2. Check if branchName differs from the new feature's branch name
  3. If different AND progress.txt has content beyond the header:
    • Create archive folder: archive/YYYY-MM-DD-feature-name/
    • Copy current prd.json and progress.txt to archive
    • Reset progress.txt with fresh header

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

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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.