ralph

name	ralph
description	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.

Ralph PRD Converter

Converts existing PRDs to the prd.json format that Ralph uses for autonomous execution.

---

The Job

Convert .oh/tasks/<short-desc>/prd.md to .oh/tasks/<short-desc>/prd.json in the same folder.

Required arguments:

• Folder path (positional, e.g. .oh/tasks/install-prereq-detection/). The folder name is <short-desc>.
• --issue <N> — GitHub issue number this PRD addresses. Required. The branch name embeds this.
• --prefix <type> — branch prefix per .claude/skills/git/SKILL.md. One of feat | bug | task | audit | skill | agent. Default: feat.

branchName in the produced JSON follows .claude/skills/git/SKILL.md:

<prefix>/<issue#>-<short-desc>

Example: folder .oh/tasks/install-prereq-detection/ + --issue 175 + --prefix task → branchName: "task/175-install-prereq-detection".

If --issue is missing, hard-fail with: "issue number required — open the GitHub issue first per .claude/skills/git/SKILL.md and re-run with --issue <N>." This matches the project's "issue first, then branch" workflow.

The folder name IS the feature name — do not re-derive it from branchName or anywhere else.

---

Output Format

{
    "schemaVersion": 1,
    "project": "[Project Name]",
    "branchName": "<prefix>/<issue#>-<short-desc>",
    "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 agent-browser skill"

Frontend stories are NOT complete until visually verified. Ralph will use the agent-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 agent-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 agent-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 agent-browser skill"
            ],
            "priority": 4,
            "passes": false,
            "notes": ""
        }
    ]
}

---

Archiving Previous Runs

Archive fires only when all of the following hold for .oh/tasks/<short-desc>/:

1. prd.json already exists (re-running ralph on a feature that ran before).
2. progress.txt has content beyond the header (the runner has written entries — there is execution history worth preserving).

If both hold:

1. Read the current prd.json and progress.txt.

2. Create .oh/tasks/<short-desc>/archive/<ISO-timestamp>/ where the timestamp is YYYY-MM-DDTHH-MM-SS (UTC; second-resolution avoids same-day collisions).

3. Copy prd.json and progress.txt into that directory.

4. Reset progress.txt to its header only:

   # progress
   
   

5. Overwrite prd.json with the new conversion.

Different branchNames do not trigger archiving. In the per-folder layout, a different feature lives in a different folder, so there is no shared slot to protect.

---

Checklist Before Saving

Before writing prd.json, verify:

• Operating on .oh/tasks/<short-desc>/ — folder name is the feature name
• Archive on rerun: if prd.json exists AND progress.txt has run history, archived to .oh/tasks/<short-desc>/archive/<ISO-timestamp>/ before overwriting
• 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 agent-browser skill" as criterion
• Acceptance criteria are verifiable (not vague)
• No story depends on a later story