ralph-init
Initialize a PRD (Product Requirements Document) for structured ralph-loop execution
Packaged view
This page reorganizes the original catalog entry around fit, installability, and workflow context first. The original raw source lives below.
Install command
npx @skill-hub/cli install yeachan-heo-oh-my-claude-sisyphus-ralph-init
Repository
Skill path: skills/ralph-init
Initialize a PRD (Product Requirements Document) for structured ralph-loop execution
Open repositoryBest for
Primary workflow: Research & Ops.
Technical facets: Full Stack.
Target audience: everyone.
License: Unknown.
Original source
Catalog source: SkillHub Club.
Repository owner: Yeachan-Heo.
This is still a mirrored public skill entry. Review the repository before installing into production workflows.
What it helps with
- Install ralph-init into Claude Code, Codex CLI, Gemini CLI, or OpenCode workflows
- Review https://github.com/Yeachan-Heo/oh-my-claude-sisyphus before adding ralph-init to shared team environments
- Use ralph-init for development workflows
Works across
Favorites: 0.
Sub-skills: 0.
Aggregator: No.
Original source / Raw SKILL.md
---
name: ralph-init
description: Initialize a PRD (Product Requirements Document) for structured ralph-loop execution
user-invocable: true
---
# Ralph Init Skill
[RALPH-INIT - PRD CREATION MODE]
## What is PRD?
A PRD (Product Requirements Document) structures your task into discrete user stories for ralph-loop.
## Your Task
Create `.omc/prd.json` and `.omc/progress.txt` based on the task description.
### prd.json Structure
```json
{
"project": "[Project Name]",
"branchName": "ralph/[feature-name]",
"description": "[Feature description]",
"userStories": [
{
"id": "US-001",
"title": "[Short title]",
"description": "As a [user], I want to [action] so that [benefit].",
"acceptanceCriteria": ["Criterion 1", "Typecheck passes"],
"priority": 1,
"passes": false
}
]
}
```
### progress.txt Structure
```
# Ralph Progress Log
Started: [ISO timestamp]
## Codebase Patterns
(No patterns discovered yet)
---
```
### Guidelines
1. **Right-sized stories**: Each completable in one focused session
2. **Verifiable criteria**: Include "Typecheck passes", "Tests pass"
3. **Independent stories**: Minimize dependencies between stories
4. **Priority order**: Foundational work (DB, types) before UI
After creating files, report summary and suggest running `/ralph-loop` to start.
Task to break down:
{{ARGUMENTS}}