스킬 prompt-engineering-patterns

📝

prompt-engineering-patterns

Name: prompt-engineering-patterns
Author: sickn33

안전

Apply Prompt Engineering Patterns

또한 다음에서 사용할 수 있습니다: wshobson

Improve LLM outputs with proven prompt engineering techniques. This skill provides patterns for chain-of-thought reasoning, few-shot learning, and template systems that make AI interactions more reliable and controllable.

지원: Claude Codex Code(CC)

📊 86 적절함

스킬 ZIP 다운로드

Claude에서 업로드

설정 → 기능 → 스킬 → 스킬 업로드로 이동

토글을 켜고 사용 시작

테스트해 보기

"prompt-engineering-patterns" 사용 중입니다. Design a prompt that helps users write professional emails

예상 결과:

A structured email writing template with role definition, tone guidelines, and format sections that produces consistent, professional email outputs.

"prompt-engineering-patterns" 사용 중입니다. How can I improve code review quality with AI?

예상 결과:

A few-shot prompt providing code review examples with common bug patterns, security considerations, and best practices that guides the AI to provide thorough, constructive feedback.

보안 감사

안전

v1 • 2/24/2026

All 216 static findings are false positives. The flagged files are markdown documentation (.md) and example JSON files containing educational content about prompt engineering techniques. The scanner incorrectly interprets backticks in markdown code blocks as shell commands, text references to cryptographic terms as weak crypto implementations, and tutorial references to system commands as reconnaissance. This is a documentation skill with no executable security issues.

스캔된 파일

2,696

분석된 줄 수

발견 사항

총 감사 수

낮은 위험 문제 (4)

assets/prompt-template-library.md:6-237 references/chain-of-thought.md:12-349 references/few-shot-learning.md:12-339 references/prompt-optimization.md:6-402 references/prompt-templates.md:6-435 references/system-prompts.md:9-170 SKILL.md:22-161

False Positive: Ruby/Shell Backtick Detection in Documentation

Static scanner flagged 170 instances of 'Ruby/shell backtick execution' in markdown files. These are false positives - the backticks are markdown code block delimiters showing Python/code examples in documentation, not actual shell commands. Files affected: SKILL.md, references/*.md, assets/*.md

assets/few-shot-examples.json:12-90 assets/prompt-template-library.md:90 references/few-shot-learning.md:78 references/prompt-optimization.md:341 references/prompt-templates.md:140-452 references/system-prompts.md:1-155 SKILL.md:3-194

False Positive: Weak Cryptographic Algorithm References

Static scanner flagged 39 instances of 'Weak cryptographic algorithm' in documentation files. These are false positives - the files contain educational content explaining prompt engineering patterns, with text examples mentioning cryptographic concepts in context of AI safety, not actual crypto implementations.

assets/few-shot-examples.json:103 references/chain-of-thought.md:170-391 references/few-shot-learning.md:84-212 references/prompt-optimization.md:176-349 references/prompt-templates.md:397 references/system-prompts.md:93-165 SKILL.md:206

False Positive: System/Network Reconnaissance in Tutorials

Static scanner flagged 'System reconnaissance' and 'Network reconnaissance' patterns in markdown documentation. These are false positives - the files contain educational tutorials that reference system commands and networking concepts as part of prompt engineering examples, not actual reconnaissance tools.

references/prompt-optimization.md:128 scripts/optimize-prompt.py:229

False Positive: Filesystem Path Traversal in Documentation

Static scanner flagged 'Path traversal sequence' in references/prompt-optimization.md and scripts/optimize-prompt.py. The markdown file contains text explaining path handling concepts in prompts. The Python script is a utility for prompt optimization with legitimate file operations.

감사자: claude

품질 점수

아키텍처

100

유지보수성

콘텐츠

커뮤니티

보안

100

사양 준수

만들 수 있는 것

Build Reliable AI Products

Design production-ready prompt systems with consistent output formats and error handling patterns for AI-powered applications.

Improve Code Generation

Apply structured prompting techniques to get better code completion and generation results from Claude or Codex.

Create AI Training Materials

Develop comprehensive prompt libraries and templates for team-wide AI adoption and best practices.

이 프롬프트를 사용해 보세요

Chain-of-Thought Reasoning

Solve this problem step by step:

Problem: {problem}

Think through each step carefully:
1. [First step]
2. [Second step]
3. [Third step]

Final answer:

Few-Shot Classification

Classify the following input into one of these categories: {categories}

Examples:
{examples}

Now classify this:
Input: {input}

Category:

System Prompt Template

You are {role}. Your task is {task}.

Guidelines:
- {guideline1}
- {guideline2}
- {guideline3}

Output format:
{output_format}

Iterative Refinement

Initial request: {request}

Current draft: {draft}

Feedback to address:
{feedback}

Please revise the draft based on this feedback:

모범 사례

Start with clear role definitions in system prompts to establish AI behavior boundaries
Use specific, diverse examples in few-shot prompts that cover edge cases
Test prompts across multiple query variations to ensure consistent outputs

피하기

Using vague instructions like 'be helpful' without specific behavioral guidelines
Overloading prompts with too many examples that exceed context window limits
Assuming prompts work identically across different LLM models without testing

자주 묻는 질문

What is chain-of-thought prompting?

Chain-of-thought prompting encourages LLMs to show their reasoning step-by-step, improving accuracy on complex math, logic, and reasoning tasks.

How many examples should I include in few-shot learning?

Most tasks work well with 2-5 examples. Balance example diversity with context window limits. Too many examples can reduce response quality.

Can I use these patterns with Claude Code?

Yes, these patterns work with Claude, Claude Code, Codex, and most modern LLMs. Claude Code can execute the prompt templates directly.

How do I debug prompts that produce inconsistent outputs?

Add explicit output format constraints, include more diverse examples, and use step-by-step reasoning to make the AI process more transparent.

What is the difference between system prompts and user prompts?

System prompts define the AI assistant's role and behavior at the start of conversation. User prompts contain the specific task or question for each interaction.

How do I handle prompt injection risks?

Use clear instruction boundaries, validate user inputs, and avoid concatenating untrusted content directly into prompts. Structure prompts with distinct sections for instructions and user data.