Token导航 LogoToken导航

Agent Skill · 前端设计

ralph-prompt-project(拉尔夫提示项目)

用于辅助提示词、系统指令、Agent 行为约束和工作流模板的整理。它适合让 Agent 规范任务边界、统一输出格式、拆分操作步骤或优化提示词可复用性。使用时需要保留真实业务约束,不要把示例当硬规则;涉及自动执行、外部工具或高风险操作时,应在提示词中明确确认步骤、权限边界和失败处理方式。

ralph-prompt-project 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为需要联网;许可证为 MIT,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 7,000。

总安装 432周安装 18GitHub Stars 9下载 144核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ralph-prompt-project(拉尔夫提示项目)
来源仓库:https://github.com/adaptationio/skrillz
仓库路径:skills/ralph-prompt-project
安装命令:
npx skills add https://github.com/adaptationio/skrillz --skill ralph-prompt-project
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/adaptationio/skrillz --skill ralph-prompt-project

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

用于辅助提示词、系统指令和工作流模板的整理。适合规范任务边界、统一输出格式和优化可复用性。使用时需保留真实业务约束,不要把示例当硬规则。涉及自动执行时应明确确认步骤和权限边界。适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

ralph-prompt-project 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/ralph-prompt-project

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/adaptationio/skrillz --skill ralph-prompt-proj…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要需要联网,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ralph-prompt-project 怎么安装?

在终端执行 npx skills add https://github.com/adaptationio/skrillz --skill ralph-prompt-project。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ralph-prompt-project 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ralph-prompt-project 需要什么权限?

权限级别是需要联网。该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

ralph-prompt-project 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

ralph-prompt-project 用的人多吗?

公开数据是累计安装 432 次,近一周安装 18 次,下载 144 次,GitHub 9 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ralph-prompt-project 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
ralph-prompt-project

拉尔夫提示项目 · 本页

4329需要联网MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Ralph Prompt Generator: Complete Project

Overview

Generates comprehensive prompts for building entire projects from scratch using the Ralph Wiggum technique. These prompts structure development into architectural phases (design, implementation, testing, documentation) with clear milestones and incremental completion.

Best For:

  • Building complete REST APIs from scratch
  • Creating CLI tools
  • Developing libraries/packages
  • Building web applications
  • Creating automation tools
  • Greenfield projects with clear requirements

Real-World Success:

  • Geoffrey Huntley used Ralph to create the "cursed" programming language over 3 months
  • Y Combinator hackathon: 6 repositories generated overnight
  • $50k contract completed for $297 in API costs

Ralph Philosophy: These successes work because Ralph embraces that failures are deterministic and fixable. Each iteration learns from the previous. Don't fear failures—they're expected and provide data for improvement through prompt tuning, not tool changes.

Quick Start

Input Required:

  1. Project description (what to build)
  2. Technical requirements (language, framework, features)
  3. Success criteria (what makes it complete)
  4. Final completion promise

Generate prompt with:

Generate a Ralph project prompt for:
Project: [Project description]
Tech stack: [Language, framework, tools]
Features: [List of required features]
Promise: [COMPLETION_PHRASE]

Prompt Generation Workflow

Step 1: Define Project Scope

Project Definition Template:

PROJECT: [Project Name]
PURPOSE: [One sentence explaining what it does]
TECH STACK: [Languages, frameworks, tools]
TARGET USERS: [Who will use this]

CORE FEATURES:
1. [Feature 1]
2. [Feature 2]
3. [Feature 3]

NON-GOALS (Out of scope):
- [What this project will NOT do]
- [Explicit exclusions]

SUCCESS DEFINITION:
[Measurable, verifiable completion criteria]

Step 2: Map Project Phases

Standard project phases:

PhaseNamePurposeTypical %
0SetupProject scaffolding, dependencies5%
1ArchitectureDesign patterns, structure10%
2CoreMain functionality40%
3FeaturesAdditional features25%
4TestingTest coverage10%
5PolishDocumentation, cleanup10%

Step 3: Define Milestones

Each phase needs concrete milestones:

Good Milestones:

  • Verifiable by running commands
  • Binary (complete or not)
  • Independent of subjective judgment

Examples:

  • "Project builds without errors" (verifiable)
  • "All tests pass" (verifiable)
  • "CLI help command works" (verifiable)

Step 4: Structure the Prompt

Use this template:

# Project: [Project Name]

## Vision
[2-3 sentences describing what this project is and why it exists]

## Technical Specifications
- **Language**: [e.g., TypeScript, Python, Go]
- **Framework**: [e.g., Express, FastAPI, none]
- **Database**: [e.g., PostgreSQL, SQLite, none]
- **Testing**: [e.g., Jest, pytest, go test]
- **Build**: [e.g., npm, poetry, go build]

## Core Features
1. [Feature 1]: [Brief description]
2. [Feature 2]: [Brief description]
3. [Feature 3]: [Brief description]
[...]

## Non-Goals
- [Explicit exclusion 1]
- [Explicit exclusion 2]

---

## Phase 0: Project Setup (Foundation)

### Objective
Initialize project structure with all dependencies and configuration.

### Tasks
1. Initialize project structure
2. Set up package management
3. Configure development tools (linting, formatting)
4. Create initial directory structure
5. Add basic configuration files

### Deliverables
- [ ] Project directory created
- [ ] Dependencies installed
- [ ] Linting configured and passing
- [ ] Basic structure in place
- [ ] README with setup instructions

### Verification

Project builds

[build command]

Lint passes

[lint command]

Basic structure exists

ls -la [expected directories]


### Phase 0 Checkpoint

PHASE 0 COMPLETE:

  • Project initialized: [path]
  • Dependencies: Installed
  • Lint: Passing

→ Continue to Phase 1

---

## Phase 1: Architecture & Design

### Objective

Establish core architecture, interfaces, and patterns.

### Tasks

1. Define main interfaces/types
2. Create directory structure following chosen pattern
3. Implement core utilities
4. Set up error handling patterns
5. Create configuration management

### Deliverables

- Core types/interfaces defined
- Directory structure matches architecture
- Utility functions implemented
- Error handling pattern established
- Configuration loading works

### Verification

Types compile

[typecheck command]

Config loads

[test config command]


### Phase 1 Checkpoint

PHASE 1 COMPLETE:

  • Architecture: [pattern used]
  • Types: Defined and compiling
  • Config: Loading correctly

→ Continue to Phase 2

---

## Phase 2: Core Implementation

### Objective

Implement the primary functionality that defines this project.

### Tasks

[List core implementation tasks based on project type]

### Deliverables

- [Core deliverable 1]
- [Core deliverable 2]
- [Core deliverable 3]
- Core tests passing

### Verification

Core functionality works

[verification command]

Tests pass

[test command]


### Phase 2 Checkpoint

PHASE 2 COMPLETE:

  • Core feature 1: Working
  • Core feature 2: Working
  • Tests: Passing

→ Continue to Phase 3

---

## Phase 3: Feature Implementation

### Objective

Add all required features beyond the core.

### Tasks

[List additional feature tasks]

### Deliverables

- [Feature deliverable 1]
- [Feature deliverable 2]
- All feature tests passing

### Verification

Features work

[feature verification commands]

All tests pass

[full test command]


### Phase 3 Checkpoint

PHASE 3 COMPLETE:

  • Feature 1: Working
  • Feature 2: Working
  • All tests: Passing

→ Continue to Phase 4

---

## Phase 4: Testing & Quality

### Objective

Ensure comprehensive test coverage and code quality.

### Tasks

1. Write unit tests for all modules
2. Write integration tests
3. Add edge case tests
4. Ensure code coverage target met
5. Fix any linting issues

### Deliverables

- Unit test coverage ≥ [X]%
- Integration tests passing
- Edge cases covered
- All lint rules pass
- No TypeScript/type errors

### Verification

Coverage report

[coverage command]

All quality checks

[lint command] && [typecheck command] && [test command]


### Phase 4 Checkpoint

PHASE 4 COMPLETE:

  • Coverage: [X]%
  • All tests: Passing
  • Quality: All checks green

→ Continue to Phase 5

---

## Phase 5: Documentation & Polish

### Objective

Complete documentation and final polish.

### Tasks

1. Write comprehensive README
2. Add inline documentation/comments for complex code
3. Create usage examples
4. Add CHANGELOG if applicable
5. Final code cleanup

### Deliverables

- README complete with all sections
- Usage examples documented
- Complex code has comments
- No TODO comments remaining
- Code formatted consistently

### Verification

Check for TODOs

grep -r "TODO" src/

Lint final

[lint command]

Build final

[build command]


---

## Final Project Verification

### Complete Checklist

- Phase 0: Setup complete
- Phase 1: Architecture established
- Phase 2: Core functionality working
- Phase 3: All features implemented
- Phase 4: Tests passing, quality green
- Phase 5: Documentation complete

### Final Verification Commands

Clean build

[clean and build command]

All tests

[full test command]

Lint

[lint command]

Type check (if applicable)

[typecheck command]

Manual smoke test

[manual verification steps]


## Completion

When ALL of the following are true:

- All 6 phases completed and verified
- All tests passing
- All quality checks green
- Documentation complete
- No TODO items remaining

Output: [COMPLETION_PHRASE]

## Progress Tracking

Update after each phase:

PROJECT PROGRESS: Phase 0 (Setup): [COMPLETE/IN PROGRESS] Phase 1 (Architecture): [COMPLETE/IN PROGRESS/NOT STARTED] Phase 2 (Core): [COMPLETE/IN PROGRESS/NOT STARTED] Phase 3 (Features): [COMPLETE/IN PROGRESS/NOT STARTED] Phase 4 (Testing): [COMPLETE/IN PROGRESS/NOT STARTED] Phase 5 (Documentation): [COMPLETE/IN PROGRESS/NOT STARTED]

Current Phase: [X] Overall: [description of state]


## If Stuck

After multiple iterations on same issue:

1. Document the specific blocker
2. List what approaches have been tried
3. Identify the root cause if possible
4. Consider if feature should be descoped (but DO NOT skip without documenting)
5. Do NOT output false promise - continue or wait for max-iterations

Example: REST API Project

Input:

  • Project: Todo List REST API
  • Tech: Node.js, Express, TypeScript, SQLite
  • Features: CRUD todos, user auth, categories, due dates
  • Promise: TODO_API_COMPLETE

Generated Prompt:

# Project: Todo List REST API

## Vision
A RESTful API for managing todo items with user authentication, categories, and due date tracking. Built with TypeScript and Express for type safety and ease of development.

## Technical Specifications
- **Language**: TypeScript
- **Framework**: Express.js
- **Database**: SQLite with better-sqlite3
- **Testing**: Jest with supertest
- **Build**: npm with tsc

## Core Features
1. **User Authentication**: JWT-based auth with signup/login/logout
2. **Todo CRUD**: Create, read, update, delete todo items
3. **Categories**: Organize todos by category
4. **Due Dates**: Set and track due dates with overdue detection
5. **Filtering**: Filter todos by status, category, due date

## Non-Goals
- Frontend/UI (API only)
- Real-time updates (polling only)
- File attachments
- Collaboration/sharing

---

## Phase 0: Project Setup

### Tasks
1. `npm init` with TypeScript configuration
2. Install dependencies: express, better-sqlite3, jsonwebtoken, bcrypt
3. Install dev dependencies: typescript, jest, supertest, eslint
4. Configure tsconfig.json, eslint, jest
5. Create directory structure: src/{routes,controllers,models,middleware}

### Deliverables
- [ ] package.json with all dependencies
- [ ] tsconfig.json configured
- [ ] ESLint configured and passing
- [ ] Directory structure created
- [ ] `npm run build` works

### Verification

npm run build npm run lint ls src/


### Phase 0 Checkpoint

PHASE 0 COMPLETE: Project scaffolded, builds successfully


---

## Phase 1: Architecture

### Tasks

1. Define TypeScript interfaces: User, Todo, Category
2. Create database schema and initialization
3. Set up Express app structure with middleware
4. Implement error handling middleware
5. Create config management

### Deliverables

- Types in src/types/
- Database schema creates tables
- Express app configured with JSON parsing, CORS
- Error handler returns proper JSON errors
- Config loads from environment

### Verification

npm run build npm test -- --grep "database"


---

## Phase 2: Core Implementation

### Tasks

1. Implement User model with password hashing
2. Create auth routes: POST /auth/signup, POST /auth/login
3. Implement JWT middleware for protected routes
4. Implement Todo model and CRUD
5. Create todo routes: GET, POST, PUT, DELETE /todos

### Deliverables

- Signup creates user, returns JWT
- Login validates, returns JWT
- Protected routes require valid JWT
- CRUD operations work for todos
- User can only access their own todos

### Verification

Signup

curl -X POST -H "Content-Type: application/json" \ -d '{"email":"test@test.com","password":"password123"}' \ http://localhost:3000/auth/signup

Login and use token for todos

TOKEN=$(curl -s -X POST -H "Content-Type: application/json" \ -d '{"email":"test@test.com","password":"password123"}' \ http://localhost:3000/auth/login | jq -r '.token')

curl -H "Authorization: Bearer $TOKEN" http://localhost:3000/todos


---

## Phase 3: Features

### Tasks

1. Implement Category model and routes
2. Add category relationship to todos
3. Implement due date field with validation
4. Add overdue detection endpoint
5. Implement filtering (status, category, due date range)

### Deliverables

- Categories CRUD works
- Todos can be assigned to categories
- Due dates stored and validated
- GET /todos/overdue returns overdue items
- Filtering by query params works

---

## Phase 4: Testing

### Tasks

1. Unit tests for models
2. Integration tests for all routes
3. Auth flow tests
4. Edge case tests (invalid inputs, unauthorized access)

### Deliverables

- ≥80% code coverage
- All auth scenarios tested
- All CRUD scenarios tested
- Error cases tested

### Verification

npm test -- --coverage


---

## Phase 5: Documentation

### Tasks

1. README with API documentation
2. Setup instructions
3. Example requests for each endpoint
4. Environment variables documentation

### Deliverables

- README complete
- All endpoints documented
- Examples provided
- No TODOs remaining

---

## Final Verification

npm run lint npm run build npm test -- --coverage npm start # Manual smoke test


## Completion

When all phases verified and:

- All tests passing with ≥80% coverage
- All endpoints working
- Documentation complete

Output: TODO_API_COMPLETE

Best Practices

Project Scope

  • Define clear boundaries (non-goals)
  • Start smaller than you think necessary
  • Add features incrementally

Phase Management

  • Complete phases in order
  • Don't skip testing phase
  • Document checkpoints

Verification

  • Include actual commands to run
  • Make success criteria binary
  • Automate where possible

DO:

  • Define clear project scope
  • Use all 6 phases
  • Include verification commands
  • Set realistic feature scope
  • Document progress at checkpoints

DON'T:

  • Skip architectural phase
  • Rush to implementation
  • Leave testing for "later"
  • Scope creep mid-project
  • Output promise before documentation

Integration with Ralph Loop

/ralph-wiggum:ralph-loop "[paste generated prompt]" --completion-promise "YOUR_PROMISE" --max-iterations 100

Recommended iterations by project size:

  • Small project (CLI tool, simple API): --max-iterations 60-80
  • Medium project (Full API with auth): --max-iterations 100-150
  • Large project (Multi-feature app): --max-iterations 150-200

Tip: For large projects, consider splitting into multiple Ralph sessions:

  1. First session: Phases 0-2 (Setup through Core)
  2. Second session: Phases 3-5 (Features through Polish)

For single-task prompts, see ralph-prompt-single-task. For multi-task prompts, see ralph-prompt-multi-task. For research/analysis prompts, see ralph-prompt-research.

平台分布

github-copilot

28.26%
按下载量换算41

Claude Code

21.62%
按下载量换算31

mcpjam

17.37%
按下载量换算25

moltbot

11.69%
按下载量换算17

windsurf

7.68%
按下载量换算11

zencoder

3.13%
按下载量换算5

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

需要联网

该 Skill 可能需要联网访问来源站点、仓库或外部 API;具体网络访问范围需要结合源码和 README 复核。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills