KS
Killer-Skills

ralph — Categories.community

v1.0.0
GitHub

About this Skill

Perfect for Autonomous Execution Agents needing PRD conversion to JSON format. The most comprehensive Claude Code skills registry | Web Search: https://skills-registry-web.vercel.app

majiayu000 majiayu000
[0]
[0]
Updated: 2/20/2026

Quality Score

Top 5%
80
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
Cursor IDE Windsurf IDE VS Code IDE
> npx killer-skills add majiayu000/claude-skill-registry/ralph

Agent Capability Analysis

The ralph MCP Server by majiayu000 is an open-source Categories.community integration for Claude and other AI agents, enabling seamless task automation and capability expansion.

Ideal Agent Persona

Perfect for Autonomous Execution Agents needing PRD conversion to JSON format.

Core Value

Empowers agents to convert existing PRDs to prd.json format, utilizing markdown files or text, and outputting JSON with project, branchName, description, and userStories, enabling seamless autonomous execution with Ralph.

Capabilities Granted for ralph MCP Server

Converting PRDs for autonomous project execution
Generating prd.json files for Ralph directory
Parsing markdown files for feature description extraction

! Prerequisites & Limits

  • Requires input PRD in markdown file or text format
  • Output limited to prd.json format
Project
SKILL.md
7.5 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8

# Tags

[No tags]
SKILL.md
Readonly

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

json
1{ 2 "project": "[Project Name]", 3 "branchName": "ralph/[feature-name-kebab-case]", 4 "description": "[Feature description from PRD title/intro]", 5 "userStories": [ 6 { 7 "id": "US-001", 8 "title": "[Story title]", 9 "description": "As a [user], I want [feature] so that [benefit]", 10 "acceptanceCriteria": [ 11 "Criterion 1", 12 "Criterion 2", 13 "Typecheck passes" 14 ], 15 "priority": 1, 16 "passes": false, 17 "notes": "" 18 } 19 ] 20}

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:

markdown
1# Task Status Feature 2 3Add ability to mark tasks with different statuses. 4 5## Requirements 6- Toggle between pending/in-progress/done on task list 7- Filter list by status 8- Show status badge on each task 9- Persist status in database

Output prd.json:

json
1{ 2 "project": "TaskApp", 3 "branchName": "ralph/task-status", 4 "description": "Task Status Feature - Track task progress with status indicators", 5 "userStories": [ 6 { 7 "id": "US-001", 8 "title": "Add status field to tasks table", 9 "description": "As a developer, I need to store task status in the database.", 10 "acceptanceCriteria": [ 11 "Add status column: 'pending' | 'in_progress' | 'done' (default 'pending')", 12 "Generate and run migration successfully", 13 "Typecheck passes" 14 ], 15 "priority": 1, 16 "passes": false, 17 "notes": "" 18 }, 19 { 20 "id": "US-002", 21 "title": "Display status badge on task cards", 22 "description": "As a user, I want to see task status at a glance.", 23 "acceptanceCriteria": [ 24 "Each task card shows colored status badge", 25 "Badge colors: gray=pending, blue=in_progress, green=done", 26 "Typecheck passes", 27 "Verify in browser using dev-browser skill" 28 ], 29 "priority": 2, 30 "passes": false, 31 "notes": "" 32 }, 33 { 34 "id": "US-003", 35 "title": "Add status toggle to task list rows", 36 "description": "As a user, I want to change task status directly from the list.", 37 "acceptanceCriteria": [ 38 "Each row has status dropdown or toggle", 39 "Changing status saves immediately", 40 "UI updates without page refresh", 41 "Typecheck passes", 42 "Verify in browser using dev-browser skill" 43 ], 44 "priority": 3, 45 "passes": false, 46 "notes": "" 47 }, 48 { 49 "id": "US-004", 50 "title": "Filter tasks by status", 51 "description": "As a user, I want to filter the list to see only certain statuses.", 52 "acceptanceCriteria": [ 53 "Filter dropdown: All | Pending | In Progress | Done", 54 "Filter persists in URL params", 55 "Typecheck passes", 56 "Verify in browser using dev-browser skill" 57 ], 58 "priority": 4, 59 "passes": false, 60 "notes": "" 61 } 62 ] 63}

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!)
  • ALL stories have passes: false (CRITICAL - never copy old pass status!)
  • 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" as criterion
  • Acceptance criteria are verifiable (not vague)
  • No story depends on a later story

CRITICAL: Always Reset passes to false

When creating a new prd.json, ALWAYS set passes: false for every story. Never:

  • Copy pass status from an old prd.json
  • Leave stories marked as passes: true
  • Assume previous work carries over

Each new prd.json is a fresh start. The Ralph loop will mark stories as passes: true only after successfully implementing them.

Related Skills

Looking for an alternative to ralph or building a Categories.community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

149.6k
0
Design

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

73.0k
0
Communication

zustand

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication

data-fetching

Logo of lobehub
lobehub

The ultimate space for work and life — to find, build, and collaborate with agent teammates that grow with you. We are taking agent harness to the next level — enabling multi-agent collaboration, effortless agent team design, and introducing agents as the unit of work interaction.

72.8k
0
Communication