ralph-plan

Decompose feature requests into atomic stories with dependencies, acceptance criteria, and tests.

Updated Jul 6, 2020
One-click install
npx skills add https://github.com/guifry/devconfig --skill ralph-plan-guifry
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: ralph-plan
Source: https://github.com/guifry/devconfig/tree/main/claude/skills/ralph-plan
Command: npx skills add https://github.com/guifry/devconfig --skill ralph-plan-guifry

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Decompose a feature request into atomic, independently implementable stories to create a clear, actionable PRD.json blueprint for development and validation.

Core Features & Use Cases

  • Break features into 5-15 independent stories, each with an id, title, description, status, depends_on, files, acceptance criteria, and tests to enable incremental delivery.
  • Validate sequencing rules (no circular dependencies, early milestones, and clear acceptance criteria) to ensure safe, parallelizable implementation.
  • Generate a PRD.json in the current directory that documents the feature, created timestamp, and a structured list of stories guiding development, testing, and review.

Quick Start

Write a feature brief or user need and ask Ralph Plan to generate a PRD.json describing 5-15 atomic stories.

Frequently Asked Questions about ralph-plan

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I decompose a feature request into actionable development stories?

To decompose a feature request into actionable stories, you write a feature brief or user need. The tool then generates a structured PRD.json with 5-15 atomic stories, each including dependencies, acceptance criteria, and tests for incremental delivery.

What is a PRD.json schema for agile backlog planning?

A PRD.json schema for agile backlog planning documents a feature, description, created timestamp, and a structured list of stories. Each story entry includes an id, title, description, status, depends_on, files, acceptance_criteria, and tests to guide development.

How do I structure story dependencies to ensure safe parallelizable implementation?

Structuring story dependencies for parallelizable implementation requires validating sequencing rules to prevent circular dependencies. This ensures early milestones are clear and acceptance criteria are met before dependent stories begin.

Can I generate a product requirements document with acceptance criteria and tests automatically?

Yes, you can automatically generate a product requirements document with acceptance criteria and tests by providing a feature brief. The output is a PRD.json containing 5-15 atomic stories, each with defined acceptance criteria and tests.

What is the best way to break down a large feature into 5-15 independent stories?

The best way to break down a large feature into 5-15 independent stories is to validate sequencing rules and enforce a strict PRD.json schema. This prevents circular dependencies and ensures clear acceptance criteria for safe, parallelizable implementation.