ralph-init
Initialize Ralph environment. Creates AGENTS.md, prd.json, progress.log from a project description.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
메뉴
Initialize Ralph environment. Creates AGENTS.md, prd.json, progress.log from a project description.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Deep project initialization using the Architect-Builder pattern. Use for large projects (20+ tasks, multiple domains) where a single task breakdown would be unwieldy or exceed context limits.
Detailed Ralph execution guidance. Load when running the Ralph autonomous loop to get step-by-step implementation protocol.
Creates AGENTS.md, prd.json, and progress.log to initialize the Ralph environment. Use when setting up a new project for autonomous execution.
Shared patterns for modifying an existing Ralph project environment. Load when adding tasks, pivoting project direction, or revising objectives.
Add a new task to an existing Ralph project. Use when requirements change during execution.
Deep initialization for large projects using Architect-Builder pattern.
| name | /ralph-init |
| description | Initialize Ralph environment. Creates AGENTS.md, prd.json, progress.log from a project description. |
You are initializing the Ralph Wiggum autonomous loop environment.
Task: Create initial project files based on: $ARGUMENTS
Include these sections in priority order:
# Project Name
## Project Overview
Brief description of architecture and purpose
## Build & Test Commands
- Build: `npm run build`
- Test: `npm test`
- Lint: `npm run lint`
## Technology Stack
- Framework: [e.g., Next.js 14]
- Language: [e.g., TypeScript]
- Database: [e.g., PostgreSQL]
## Project Structure
- `src/` - Source code
- `tests/` - Test files
## Code Style
- [Standard 1]
- [Standard 2]
## Testing Requirements
- [Requirement 1]
- [Requirement 2]
## Git Workflow
- Branch strategy
- Commit format
## Security Considerations
- API key handling patterns
- What NOT to do with sensitive data
{
"project": "Project Name",
"description": "Project overview",
"tasks": [
{
"id": "task-001",
"title": "Task description",
"priority": "high|medium|low",
"status": "pending",
"dependencies": [],
"acceptance_criteria": [
"Criterion 1",
"Criterion 2"
]
}
]
}
# Ralph Wiggum Progress Log
# Started: [current timestamp]
Report: "Ralph environment initialized. Run '/ralph' to start autonomous execution."