prompt-engineering
Advanced prompt engineering techniques for optimal AI responses. Use this when crafting prompts, optimizing AI interactions, or designing system prompts for applications.
Best use case
prompt-engineering is best used when you need a repeatable AI agent workflow instead of a one-off prompt. It is especially useful for teams working in multi. Advanced prompt engineering techniques for optimal AI responses. Use this when crafting prompts, optimizing AI interactions, or designing system prompts for applications.
Advanced prompt engineering techniques for optimal AI responses. Use this when crafting prompts, optimizing AI interactions, or designing system prompts for applications.
Users should expect a more consistent workflow output, faster repeated execution, and less time spent rewriting prompts from scratch.
Practical example
Example input
Use the "prompt-engineering" skill to help with this workflow task. Context: Advanced prompt engineering techniques for optimal AI responses. Use this when crafting prompts, optimizing AI interactions, or designing system prompts for applications.
Example output
A structured workflow result with clearer steps, more consistent formatting, and an output that is easier to reuse in the next run.
When to use this skill
- Use this skill when you want a reusable workflow rather than writing the same prompt again and again.
When not to use this skill
- Do not use this when you only need a one-off answer and do not need a reusable workflow.
- Do not use it if you cannot install or maintain the related files, repository context, or supporting tools.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/prompt-engineering/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How prompt-engineering Compares
| Feature / Agent | prompt-engineering | 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?
Advanced prompt engineering techniques for optimal AI responses. Use this when crafting prompts, optimizing AI interactions, or designing system prompts for applications.
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 Engineering
효과적인 프롬프트 작성을 위한 고급 기법 가이드입니다.
## Core Principles
### 1. Clarity (명확성)
```
❌ "코드 좀 고쳐줘"
✅ "auth.js의 validateToken 함수에서 만료된 토큰 처리 시
발생하는 TypeError를 수정해주세요"
```
### 2. Context (맥락)
```
❌ "이 에러 해결해줘: TypeError"
✅ "Node.js 18, Express 4 환경에서 JWT 검증 시
다음 에러 발생: TypeError: Cannot read property 'exp' of undefined
관련 코드: [코드 첨부]"
```
### 3. Specificity (구체성)
```
❌ "좋은 API 만들어줘"
✅ "다음 요구사항의 REST API 설계:
- 리소스: 사용자, 게시물
- 인증: JWT Bearer
- 페이지네이션: cursor 기반
- 응답 형식: JSON:API 스펙"
```
## Prompting Techniques
### Zero-Shot Prompting
```
직접 지시만으로 결과 도출
예: "다음 텍스트의 감정을 분석하세요: [텍스트]"
```
### Few-Shot Prompting
```
예시를 통한 패턴 학습
예시 1: 입력 → 출력
예시 2: 입력 → 출력
---
실제 입력 → ?
```
### Chain-of-Thought (CoT)
```
단계별 추론 유도
"단계별로 생각해보세요:
1. 먼저 문제를 분석합니다
2. 가능한 해결책을 나열합니다
3. 각 해결책의 장단점을 평가합니다
4. 최적의 해결책을 선택합니다"
```
### Role Prompting
```
특정 역할 부여
"당신은 10년 경력의 시니어 백엔드 개발자입니다.
코드 리뷰 관점에서 다음 코드를 평가해주세요..."
```
## Prompt Structure
### 기본 구조
```markdown
## Role (역할)
[AI가 수행할 역할 정의]
## Context (맥락)
[배경 정보, 제약 조건]
## Task (작업)
[구체적인 요청 사항]
## Format (형식)
[원하는 출력 형식]
## Examples (예시) - 선택적
[입출력 예시]
```
### 코드 관련 프롬프트
```markdown
## 환경
- 언어/프레임워크: [명시]
- 버전: [명시]
- 관련 의존성: [명시]
## 현재 상태
[현재 코드 또는 상황]
## 목표
[달성하려는 결과]
## 제약 조건
- [제약 1]
- [제약 2]
```
## Anti-Patterns
### 피해야 할 패턴
| 안티패턴 | 문제점 | 개선 |
|----------|--------|------|
| 모호한 요청 | 해석의 여지가 많음 | 구체적 조건 명시 |
| 과도한 정보 | 핵심이 묻힘 | 관련 정보만 포함 |
| 부정형 지시 | "~하지 마세요" | "~해주세요" 로 변경 |
| 열린 결말 | 범위가 무한함 | 범위와 제약 명시 |
### 예시
```
❌ "이상한 코드 패턴 사용하지 마세요"
✅ "ESLint 규칙을 따르고, 함수는 20줄 이내로 작성해주세요"
❌ "좋은 성능으로 만들어주세요"
✅ "응답 시간 100ms 이내, 메모리 사용 512MB 이하로 최적화해주세요"
```
## System Prompt Design
### 구조
```markdown
# Identity
[AI의 정체성과 목적]
# Capabilities
[할 수 있는 것]
# Constraints
[제한 사항]
# Response Format
[응답 형식 규칙]
# Examples
[대표적인 상호작용 예시]
```
### 예시: 코드 리뷰 봇
```markdown
# Identity
당신은 코드 품질 향상을 돕는 시니어 개발자입니다.
# Capabilities
- 코드 스타일 검토
- 버그 탐지
- 성능 개선 제안
- 보안 취약점 식별
# Constraints
- 개인적 스타일 강요 금지
- 프로젝트 컨벤션 우선
- 건설적 피드백만 제공
# Response Format
## 요약
[한 줄 요약]
## 주요 발견
- [이슈 1]: [설명] → [제안]
## 긍정적 측면
- [잘한 점]
```
## Iteration Strategies
```
1. 초기 프롬프트 작성
2. 결과 평가
3. 문제점 식별:
- 불완전한 응답 → 더 구체적인 지시 추가
- 잘못된 방향 → 제약 조건 강화
- 형식 불일치 → 예시 추가
4. 프롬프트 수정
5. 반복
```Related Skills
prompt-optimize
Expert prompt engineering skill that transforms Claude into "Alpha-Prompt" - a master prompt engineer who collaboratively crafts high-quality prompts through flexible dialogue. Activates when user asks to "optimize prompt", "improve system instruction", "enhance AI instruction", or mentions prompt engineering tasks.
prompt-repetition
A prompt repetition technique for improving LLM accuracy. Achieves significant performance gains in 67% (47/70) of 70 benchmarks. Automatically applied on lightweight models (haiku, flash, mini).
protocol-reverse-engineering
Master network protocol reverse engineering including packet analysis, protocol dissection, and custom protocol documentation. Use when analyzing network traffic, understanding proprietary protocols, or debugging network communication.
prompt-library
Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.
prompt-engineering-patterns
Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, or designing production prompt templates.
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)
prompt-caching
Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.
llm-application-dev-prompt-optimize
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and model-specific optimizati
data-engineering-data-pipeline
You are a data pipeline architecture expert specializing in scalable, reliable, and cost-effective data pipelines for batch and streaming data processing.
data-engineering-data-driven-feature
Build features guided by data insights, A/B testing, and continuous measurement using specialized agents for analysis, implementation, and experimentation.
seedance-prompt
为 Seedance 2.0 视频生成模型撰写产品宣传动画提示词（Motion Graphics Prompt）。 生成 15 秒一镜到底的动态影像提示词，支持 4 种美学风格（Apple/Microsoft/Bauhaus/Vercel）。 支持垫图（参考图）模式，自动标注图片占位符。 生成提示词后可通过即梦 Dreamina CLI 直接生成视频（自动检测安装状态）。 TRIGGER when: 用户需要生成 Seedance 视频提示词、产品宣传动画提示词、motion graphics prompt， 或提到 "Seedance"、"视频提示词"、"产品动画"、"宣传视频提示词"、"video prompt"。 Keywords: Seedance, 视频提示词, video prompt, motion graphics, 产品动画, 宣传动画, 垫图, Dreamina
video-prompting-guide
Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts