القائمة
Creates AGENTS.md, prd.json, and progress.log to initialize the Ralph environment. Use when setting up a new project for autonomous execution.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
| name | ralph-init |
| description | Creates AGENTS.md, prd.json, and progress.log to initialize the Ralph environment. Use when setting up a new project for autonomous execution. |
Load this skill when running /ralph-init. Creates the three required Ralph files.
Universal project context file. Must contain real, runnable commands — no placeholders.
Structure:
# [Project Name]
## Project Overview
[2-3 sentences: what it does, main architecture, primary users]
## Build & Test Commands
- Build: `[exact command]`
- Test: `[exact command]`
- Lint: `[exact command]`
- Typecheck: `[exact command]`
- Dev server: `[exact command]`
## Technology Stack
- Language: [e.g., TypeScript 5.x]
- Framework: [e.g., Next.js 14]
- Database: [e.g., PostgreSQL 16 via Prisma]
- Testing: [e.g., Vitest + Testing Library]
- Styling: [e.g., Tailwind CSS 3.x]
## Project Structure
- `src/` — Source code
- `src/components/` — UI components
- `src/lib/` — Shared utilities
- `tests/` — Test files (mirrors src/ structure)
## Code Style
- [Specific rules, e.g., "Use Zod for all API input validation"]
- [Naming conventions, e.g., "React components in PascalCase, utilities in camelCase"]
- [File conventions]
## Testing Requirements
- Unit tests required for all business logic
- [Coverage threshold if applicable]
- Integration tests for all API endpoints
## Git Workflow
- Branches: `feature/description`, `fix/description`
- Commits: `type(scope): description` (conventional commits)
- No direct commits to `main`
## Security
- API keys via environment variables only — never hardcoded
- [Other project-specific boundaries]
Complete task breakdown. Be exhaustive. Each task should be 15-60 minutes of work.
{
"project": "Project Name",
"description": "What this project builds",
"tasks": [
{
"id": "task-001",
"title": "Specific, actionable task title",
"priority": "high",
"status": "pending",
"dependencies": [],
"acceptance_criteria": [
"Concrete, binary criterion — either it passes or it does not",
"Another specific, testable criterion"
]
}
]
}
Task quality rules:
high priority: core functionality that blocks other tasksmedium priority: features and functionalitylow priority: polish, docs, optional improvements# Ralph Wiggum Progress Log
# Project: [Project Name]
# Started: [YYYY-MM-DD HH:MM:SS]
After creating all three files, report:
Ralph environment initialized.
AGENTS.md— [N] sectionsprd.json— [N] tasks ([N] high, [N] medium, [N] low priority)progress.log— readyRun
/ralph-loopto start.
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.
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.
Initialize Ralph environment. Creates AGENTS.md, prd.json, progress.log from a project description.