prompt-master
The ultimate prompt engineering toolkit that combines three powerful skills: 50+ role templates from awesome-chatgpt-prompts (143k+ stars), systematic learning of 58+ techniques from beginner to expert, and intelligent prompt optimizer with 6-dimensional quality assessment. Automatically routes to the right capability based on your request - get templates, learn techniques, or optimize prompts seamlessly.
Best use case
prompt-master is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
The ultimate prompt engineering toolkit that combines three powerful skills: 50+ role templates from awesome-chatgpt-prompts (143k+ stars), systematic learning of 58+ techniques from beginner to expert, and intelligent prompt optimizer with 6-dimensional quality assessment. Automatically routes to the right capability based on your request - get templates, learn techniques, or optimize prompts seamlessly.
Teams using prompt-master should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/prompt-master/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How prompt-master Compares
| Feature / Agent | prompt-master | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
The ultimate prompt engineering toolkit that combines three powerful skills: 50+ role templates from awesome-chatgpt-prompts (143k+ stars), systematic learning of 58+ techniques from beginner to expert, and intelligent prompt optimizer with 6-dimensional quality assessment. Automatically routes to the right capability based on your request - get templates, learn techniques, or optimize prompts seamlessly.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Prompt Master - 终极提示词工程工具包
> **三合一超级技能**:模板库 + 学习系统 + 优化器
>
> 整合三大核心能力,智能路由到最适合的工具
---
## 🎯 核心能力
### 1️⃣ 提示词模板库
来自 awesome-chatgpt-prompts(143k+ stars)的 50+ 角色模板
**使用场景**:
- 需要快速启动专业角色对话
- 查找特定场景的提示词模板
- 角色扮演、面试准备等
**核心角色**:
- 开发技术:Linux Terminal, JS Console, SQL Terminal
- 创意写作:Storyteller, Poet, Novelist, Screenwriter
- 专业角色:Doctor, Lawyer, Recruiter, Developer
- 实用工具:Job Interviewer, Travel Guide, Translator
### 2️⃣ 提示词学习系统
系统化学习 58+ 种提示词技术
**使用场景**:
- 从零学习提示词工程
- 掌握特定技术(Few-shot, CoT, ReAct等)
- 查看实战案例和学习路径
**技术分类**:
- 入门级(8种):角色扮演、逐步思考、示例驱动等
- 进阶级(8种):思维树、自我反思、多角色辩论等
- 专家级(8种):ReAct、提示词链、元提示等
### 3️⃣ 提示词优化器
6 维度质量评估和智能优化
**使用场景**:
- 优化现有提示词
- 评估提示词质量
- 生成多个变体版本
**评估维度**:
清晰度、具体性、结构性、完整性、语气、约束条件
---
## 🚀 快速开始
### 自动识别触发
Prompt Master 会自动识别你的意图并调用合适的能力:
**获取角色模板**:
```
"扮演一个面试官"
"我需要一个医生的角色提示词"
"给我一个Linux终端的模板"
```
**学习提示词技术**:
```
"如何学习提示词工程"
"教我 Few-shot learning"
"什么是 Chain-of-Thought"
"我想掌握提示词技术"
```
**优化提示词**:
```
"优化这个提示词:..."
"评估我的提示词质量"
"如何改进这个提示"
```
### 显式调用
如果需要明确指定能力:
```
"使用模板库找..."
"调用学习系统..."
"用优化器处理..."
```
---
## 📖 能力详解
### 模板库使用流程
```
1. 描述需求场景
↓
2. 自动匹配角色/模板
↓
3. 替换占位符(如 ${Position})
↓
4. 直接使用或微调
↓
5. 可选:调用优化器增强
```
### 学习系统路径
**初学者路径**(0-1个月):
```
Week 1-2: 角色扮演 + 系统指令
Week 3-4: 逐步思考 + 示例驱动
Week 5-6: 结构化输出 + 任务分解
Week 7-8: 输出格式化 + 约束条件
```
**进阶路径**(1-3个月):
```
Month 2: 思维树 + 自我反思 + 对比分析
Month 3: 多角色辩论 + CoT 优化 + 知识蒸馏
```
**专家路径**(3+个月):
```
掌握 ReAct、提示词链、元提示等高级技术
实战项目:构建复杂的多步骤 AI 工作流
```
### 优化器工作流
```
原始提示词
↓
[步骤 1] 分析需求
↓
[步骤 2] 6 维度评估
↓
[步骤 3] 识别适用技术
↓
[步骤 4] 生成优化方案
↓
[步骤 5] 应用技术优化
↓
优化后的提示词
```
---
## 🔄 智能协同工作流
### 完整示例:创建面试准备提示词
**用户请求**:"帮我准备一个前端开发面试"
**[步骤 1] 调用模板库**
→ 检索到 "Job Interviewer" 模板
**[步骤 2] 调用学习系统**
→ 识别适用技术:角色扮演、任务分解、约束条件
**[步骤 3] 调用优化器**
→ 应用技术生成定制版本
**最终输出**:
```
你是一位资深前端技术面试官,曾在多家大厂任职。
请模拟真实的前端开发面试流程:
1. 自我介绍环节(2-3分钟)
2. 技术问题环节(5-8个问题,涵盖HTML/CSS/JS/框架)
3. 算法题环节(1-2道中等难度)
4. 项目经验讨论
5. 反向提问环节
要求:
- 每次只问一个问题
- 等待我的回答后再继续
- 对每个回答给予反馈(优秀/良好/需改进)
- 最后给出总体评价和改进建议
```
### 路由逻辑
```
用户请求
↓
[关键词检测] + [意图分析]
↓
├─→ [角色模板] → 模板库
├─→ [学习技术] → 学习系统
├─→ [优化提示] → 优化器
└─→ [综合需求] → 协同工作流
```
---
## 💡 最佳实践
### 1. 渐进式学习
```
入门:模板库 + 基础技术
进阶:优化技术 + 进阶技术
专家:组合技术 + 自定义工作流
```
### 2. 迭代优化
```
第一版:使用模板快速开始
第二版:根据反馈微调
第三版:应用优化技术
最终版:多次迭代后的高质量版本
```
### 3. 建立个人库
```
my-prompts/
├── templates/ # 常用模板
├── optimized/ # 优化后的提示词
└── cases/ # 实战案例
```
---
## 📊 技术速查表
| 技术 | 难度 | 适用场景 | 触发词 |
|------|------|---------|--------|
| 角色扮演 | ⭐ | 专业任务 | "扮演", "你是" |
| 逐步思考 | ⭐ | 复杂推理 | "一步步", "分析" |
| 示例驱动 | ⭐⭐ | 格式不明确 | "例如", "像这样" |
| 结构化输出 | ⭐ | 需要格式 | "JSON", "表格" |
| 思维树 | ⭐⭐⭐ | 多方案对比 | "考虑多种可能" |
| 自我反思 | ⭐⭐ | 质量要求高 | "检查", "改进" |
| ReAct | ⭐⭐⭐⭐ | 复杂推理循环 | "思考→行动→观察" |
---
## 📚 参考文档
详细内容请查看:
- **模板库完整列表**:`references/templates.md`
- **技术详解**:`references/techniques.md`
- **优化方法**:`references/optimizer.md`
- **工作流案例**:`references/workflows.md`
---
## 🎯 使用场景
### 场景 1:快速启动角色对话
```
你:"扮演一个Python专家,帮我调试代码"
→ Prompt Master:加载模板 + 优化上下文
→ 输出:专业的Python开发者角色提示词
```
### 场景 2:学习新技术
```
你:"什么是Few-shot learning?给我例子"
→ Prompt Master:解释技术 + 提供案例 + 推荐练习
→ 输出:完整的技术教程和实战案例
```
### 场景 3:优化提示词
```
你:"优化:帮我写文章"
→ Prompt Master:评估质量 + 识别技术 + 生成优化版
→ 输出:结构化、具体化的高质量提示词
```
### 场景 4:综合需求
```
你:"帮我创建一个数据分析助手提示词"
→ Prompt Master:
1. 从模板库找到 "Data Analyst" 角色
2. 应用学习系统的技术和最佳实践
3. 用优化器增强和定制
→ 输出:专业定制的数据分析助手提示词
```
---
## ⚙️ 技术细节
### 版本信息
- **版本**: 1.0.0
- **创建日期**: 2026-01-30
- **整合技能**: chatgpt-prompts, prompt-learning-assistant, prompt-optimizer
- **总模板数**: 50+
- **总技术数**: 58+
- **评估维度**: 6
### 来源
- awesome-chatgpt-prompts: https://github.com/f/awesome-chatgpt-prompts (143k+ stars)
- OpenAI Prompt Engineering Guide
- Anthropic Prompt Library
---
## 🎓 进阶使用
### 自定义工作流
创建多步骤协同工作流:
```
步骤 1: 使用模板库获取基础模板
步骤 2: 学习系统提供技术指导
步骤 3: 优化器进行质量提升
步骤 4: 迭代测试和改进
步骤 5: 保存到个人库
```
### 技术组合
常见高效组合:
**写作任务**:
角色扮演 + 逐步思考 + 约束条件
**分析任务**:
结构化输出 + 示例驱动 + 自我反思
**创作任务**:
角色扮演 + 思维树 + 风格迁移
**推理任务**:
ReAct + 提示词链 + 自我反思
---
## ✨ 特性亮点
- ✅ **智能路由**:自动识别意图,无需手动选择
- ✅ **零门槛**:初学者可直接使用模板
- ✅ **系统化**:完整的学习路径从入门到专家
- ✅ **高效优化**:6 维度评估提升提示词质量
- ✅ **实战导向**:所有技术都有真实案例
- ✅ **持续进化**:整合最新技术进展
---
**提示**:Prompt Master 会自动识别你的需求。你可以自然地描述你的需求,无需记住特定的命令格式。
开始你的提示词工程之旅!🚀Related Skills
Golden Master
Track source-of-truth relationships between files — know when derived content becomes stale.
create-prompt
Expert prompt engineering for creating effective prompts for Claude, GPT, and other LLMs. Use when writing system prompts, user prompts, few-shot examples, or optimizing existing prompts for better performance.
create-custom-prompt
Prompt for creating custom prompt files
agentv-prompt-optimizer
Iteratively optimize prompt files against AgentV evaluation datasets by analyzing failures and refining instructions.
ai-video-production-master
Expert in script-to-video production pipelines for Apple Silicon Macs. Specializes in hybrid local/cloud workflows, LoRA training for character consistency, motion graphics generation, and artist commissioning. Activate on 'AI video production', 'script to video', 'video generation pipeline', 'character consistency', 'LoRA training', 'cloud GPU', 'motion graphics', 'Wan I2V', 'InVideo alternative'. NOT for real-time video editing, video compositing (use DaVinci/Premiere), audio production, or 3D modeling (use Blender/Maya).
skill-master
Intelligent skill orchestrator that automatically finds, creates, executes, and improves skills. When you need to accomplish a task, this skill searches for existing skills (internal, GitHub via MCP, web), creates new skills if none found, executes them, and reviews execution to improve skills based on actual usage. Also handles feedback about skill-generated outputs - if you want to fix/adjust an output AND improve the skill that created it, invoke this with your feedback. Use when you want automated skill discovery, continuous improvement, or to provide feedback on previous skill outputs.
prompt-engineer
Transforms user prompts into optimized prompts using frameworks (RTF, RISEN, Chain of Thought, RODES, Chain of Density, RACE, RISE, STAR, SOAP, CLEAR, GROW)
javascript-mastery
Comprehensive JavaScript reference covering 33+ essential concepts every developer should know. From fundamentals like primitives and closures to advanced patterns like async/await and functional p...
python-fastapi-scalable-api-cursorrules-prompt-fil
Apply for python-fastapi-scalable-api-cursorrules-prompt-fil. --- description: Defines conventions specific to FastAPI usage in the backend. globs: backend/src/**/*.py
python-django-best-practices-cursorrules-prompt-fi
Apply for python-django-best-practices-cursorrules-prompt-fi. --- description: Configurations for Django settings file with the list of dependencies and conventions. globs: **/settings.py
go-servemux-rest-api-cursorrules-prompt-file
Apply for go-servemux-rest-api-cursorrules-prompt-file. --- description: This rule emphasizes security, scalability, and maintainability best practices in Go API development. globs: /*/**/*_api.go
go-backend-scalability-cursorrules-prompt-file-cursorrules
Apply for go-backend-scalability-cursorrules-prompt-file. --- description: General rule for backend development expertise across the project. globs: **/*