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.

ALWAYS save to the global Ralph projects directory — never ask the user where to save.

Auto-detect Project Directory

Get project directory:
```
ralph project-dir
```
Save prd.json to: $(ralph project-dir)/prd.json

Output Format

{
  "project": "[Project Name]",
  "branchName": "[detected-prefix]/[feature-name-kebab-case]",
  "description": "[Feature description from PRD title/intro]",
  "userStories": [
    {
      "id": "[TICKET-0000 or 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": ""
    }
  ]
}

Note: Branch prefix and ticket IDs are detected from project conventions. See "Ticket Convention Detection" and "Branch Convention Detection" sections below.

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, 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 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.

Ticket Convention Detection

Before assigning story IDs, detect the project's existing ticket convention from git history:

# Run in the target project directory to find ticket patterns
git log --oneline -50 | grep -oE '[A-Z]{2,10}-[0-9]+' | cut -d'-' -f1 | sort | uniq -c | sort -rn | head -1

This returns the most common ticket prefix with its count. Example output: 31 CI means "CI" prefix was found 31 times → use CI-0000.

Rules:

If a prefix is found (e.g., "CI", "JIRA", "PROJ"):
- Use that prefix + "0000" for ALL stories: CI-0000, JIRA-0000
- All stories share the same placeholder ID (no real ticket assigned)
If NO ticket convention is found:
- Use sequential IDs: US-001, US-002, etc.

Examples of detected patterns:

feat: CI-1234 - Something → prefix is CI → use CI-0000
fix: JIRA-567 Something → prefix is JIRA → use JIRA-0000
[PROJ-890] Something → prefix is PROJ → use PROJ-0000
No pattern found → use US-001, US-002, etc.

Branch Convention Detection

Before setting the branch name, detect the project's existing branch naming convention:

# Run in the target project directory to find branch prefixes
git branch -a | grep -oE '(feature|feat|fix|bugfix|hotfix|release|chore)/' | sort | uniq -c | sort -rn | head -1

This returns the most common branch prefix with its count. Example output: 150 feat/ means "feat/" prefix was found 150 times → use feat/.

Rules:

If a branch prefix is found (e.g., feature/, feat/, fix/):
- Use that prefix instead of ralph/
- Example: feature/task-status instead of ralph/task-status
If NO branch convention is found:
- Use ralph/ prefix: ralph/feature-name

Common prefixes to detect:

feature/
feat/
fix/
bugfix/
hotfix/
release/
chore/

Examples:

Project has feature/add-login, feature/user-profile → use feature/task-status
Project has feat/api-v2, feat/dashboard → use feat/task-status
Project has no convention → use ralph/task-status

Conversion Rules

Each user story becomes one JSON entry
IDs: Based on detected ticket convention (see Ticket Convention Detection)
- With convention: All stories get PREFIX-0000 (e.g., CI-0000)
- Without convention: Sequential US-001, US-002, etc.
Priority: Based on dependency order, then document order
All stories: passes: false and empty notes
branchName: Based on detected branch convention (see Branch Convention Detection)
- With convention: Use detected prefix (e.g., feature/task-status)
- Without convention: Use ralph/ prefix (e.g., ralph/task-status)
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.

Specifications for Complex Features

For features with significant logic or multiple components, create specification files in the project's .specs/ directory.

When to Create Specs

Feature has complex business logic
Multiple stories will reference the same requirements
Technical decisions need documenting (API contracts, data models)
The feature spans more than 4-5 stories

Specs Structure

<project-root>/.specs/
├── feature-name.md       # Feature specification
├── api-contracts.md      # API definitions (if applicable)
└── data-models.md        # Schema/type definitions

Spec File Format

# [Feature Name] Specification

## Overview

Brief description of the feature.

## Requirements

- REQ-1: Specific requirement
- REQ-2: Another requirement

## Technical Decisions

- Decision 1: We chose X because Y
- Decision 2: Pattern Z will be used for...

## Data Model

[Schema definitions, types, etc.]

## API Contract (if applicable)

[Endpoints, request/response formats]

Why Specs Matter

Ralph reads specs at the start of EVERY iteration. Well-written specs:

Prevent Ralph from making inconsistent decisions across iterations
Provide deterministic context loading (same files every loop)
Serve as single source of truth for requirements
Help future iterations understand the "why" behind decisions

When Converting PRD to prd.json

If the PRD describes a complex feature, suggest creating specs:

Identify if the feature has complex logic or multiple interdependent parts
If so, create .specs/<feature-name>.md with the key decisions and contracts
Reference the spec in story descriptions: "Implement per .specs/feature-name.md"

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 (no conventions detected - uses defaults):

{
  "project": "TaskApp",
  "branchName": "ralph/task-status", // No branch convention found → ralph/
  "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": ""
    }
  ]
}

Output prd.json (when project has conventions detected):

If the project has:

Ticket convention: commits like feat: CI-1234 - Add login → ticket prefix is CI
Branch convention: branches like feature/add-login → branch prefix is feature/

{
  "project": "TaskApp",
  "branchName": "feature/task-status",  // Detected branch prefix
  "userStories": [
    { "id": "CI-0000", "title": "Add status field to tasks table", ... },
    { "id": "CI-0000", "title": "Display status badge on task cards", ... },
    { "id": "CI-0000", "title": "Add status toggle to task list rows", ... },
    { "id": "CI-0000", "title": "Filter tasks by status", ... }
  ]
}

Archiving Previous Runs

Before writing a new prd.json, check if there is an existing one from a different feature:

Read the current prd.json if it exists
Check if branchName differs from the new feature's branch name
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:

Ticket convention checked (detect from git history, use PREFIX-0000 or US-XXX)
Branch convention checked (detect from branches, use detected prefix or ralph/)
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