提示工程指南：掌握AI模型提示工程技巧与最佳实践

prompt-engineering by inferen-sh/skills

7,400 周安装量

228 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/inferen-sh/skills --skill prompt-engineering

AI/机器学习开发生产力

🇨🇳中文介绍

提示工程指南

通过 inference.sh CLI 掌握 AI 模型的提示工程。

提示工程指南

快速开始

需要 inference.sh CLI (infsh)。安装说明

infsh login

# 结构良好的 LLM 提示
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "You are a senior software engineer. Review this code for security vulnerabilities:\n\n```python\nuser_input = request.args.get(\"query\")\nresult = db.execute(f\"SELECT * FROM users WHERE name = {user_input}\")\n```\n\nProvide specific issues and fixes."
}'

LLM 提示工程

基本结构

[角色/上下文] + [任务] + [约束] + [输出格式]

角色提示

infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "You are an expert data scientist with 15 years of experience in machine learning. Explain gradient descent to a beginner, using simple analogies."
}'

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

图像生成提示工程

[主体] + [风格] + [构图] + [光线] + [技术细节]

# 差：模糊
"a cat"

# 好：具体
infsh app run falai/flux-dev --input '{
  "prompt": "A fluffy orange tabby cat with green eyes, sitting on a vintage leather armchair"
}'

infsh app run falai/flux-dev --input '{
  "prompt": "Portrait photograph of a woman, shot on Kodak Portra 400 film, soft natural lighting, shallow depth of field, nostalgic mood, analog photography aesthetic"
}'

infsh app run falai/flux-dev --input '{
  "prompt": "Wide establishing shot of a cyberpunk city skyline at night, rule of thirds composition, neon signs in foreground, towering skyscrapers in background, rain-slicked streets"
}'

photorealistic, 8K, ultra detailed, sharp focus, professional,
masterpiece, high quality, best quality, intricate details

infsh app run falai/flux-dev --input '{
  "prompt": "Professional headshot portrait, clean background",
  "negative_prompt": "blurry, distorted, extra limbs, watermark, text, low quality, cartoon, anime"
}'

[镜头类型] + [主体] + [动作] + [场景] + [风格]

infsh app run google/veo-3-1-fast --input '{
  "prompt": "Slow tracking shot following a woman walking through a sunlit forest, golden hour lighting, shallow depth of field, cinematic, 4K"
}'

infsh app run google/veo-3-1-fast --input '{
  "prompt": "Close-up of hands kneading bread dough on a wooden surface, flour dust floating in morning light, slow motion, cozy baking aesthetic"
}'

slow motion, timelapse, real-time, smooth motion,
continuous shot, quick cuts, frozen moment

infsh app run openrouter/claude-sonnet-45 --input '{
  "system": "You are a helpful coding assistant. Always provide code with comments. If you are unsure about something, say so rather than guessing.",
  "prompt": "Write a Python function to validate email addresses using regex."
}'

infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Extract information from this text and return as JSON:\n\n\"John Smith, CEO of TechCorp, announced yesterday that the company raised $50 million in Series B funding. The round was led by Venture Partners.\"\n\nSchema:\n{\n  \"person\": string,\n  \"title\": string,\n  \"company\": string,\n  \"event\": string,\n  \"amount\": string,\n  \"investor\": string\n}"
}'

# 从宽泛开始
infsh app run falai/flux-dev --input '{
  "prompt": "A castle on a hill"
}'

# 添加细节
infsh app run falai/flux-dev --input '{
  "prompt": "A medieval stone castle on a grassy hill"
}'

# 添加风格
infsh app run falai/flux-dev --input '{
  "prompt": "A medieval stone castle on a grassy hill, dramatic sunset sky, fantasy art style, epic composition"
}'

# 添加技术细节
infsh app run falai/flux-dev --input '{
  "prompt": "A medieval stone castle on a grassy hill, dramatic sunset sky, fantasy art style by Greg Rutkowski, epic composition, 8K, highly detailed"
}'

# 第一轮：分析
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Analyze this business problem: Our e-commerce site has a 70% cart abandonment rate. List potential causes."
}'

# 第二轮：优先级排序
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Given these causes of cart abandonment: [previous output], rank them by likely impact and ease of fixing. Format as a priority matrix."
}'

# 第三轮：行动计划
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "For the top 3 causes identified, provide specific A/B tests we can run to validate and fix each issue."
}'

擅长处理细微的指令
对角色扮演反应良好
善于遵循复杂的约束
偏好明确的输出格式

代码生成能力强
与示例配合良好
结构化输出效果好
对"让我们一步步思考"有良好反应

详细的主体描述
风格参考效果好
光线关键词很重要
支持负面提示

摄像机运动关键词
电影语言效果好
动作描述很重要
包含时间上下文

错误	问题	修复方法
过于模糊	输出不可预测	添加具体细节
过长	模型失去焦点	优先处理关键信息
相互矛盾	使模型困惑	移除矛盾之处
无格式	输出不一致	指定格式
无示例	期望不明确	添加少量示例

Review this [language] code for:
1. Bugs and logic errors
2. Security vulnerabilities
3. Performance issues
4. Code style/best practices

Code:
[code]

For each issue found, provide:
- Line number
- Issue description
- Severity (high/medium/low)
- Suggested fix

Write a [content type] about [topic].

Audience: [target audience]
Tone: [formal/casual/professional]
Length: [word count]
Key points to cover:
1. [point 1]
2. [point 2]
3. [point 3]

Include: [specific elements]
Avoid: [things to exclude]

[Subject with details], [setting/background], [lighting type],
[art style or photography style], [composition], [quality keywords]

# 视频提示指南
npx skills add inference-sh/skills@video-prompting-guide

# LLM 模型
npx skills add inference-sh/skills@llm-models

# 图像生成
npx skills add inference-sh/skills@ai-image-generation

# 完整平台技能
npx skills add inference-sh/skills@infsh-cli

浏览所有应用：infsh app list

🇺🇸English

Prompt Engineering Guide

Master prompt engineering for AI models via inference.sh CLI.

Prompt Engineering Guide

Quick Start

Requires inference.sh CLI (infsh). Install instructions

infsh login

# Well-structured LLM prompt
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "You are a senior software engineer. Review this code for security vulnerabilities:\n\n```python\nuser_input = request.args.get(\"query\")\nresult = db.execute(f\"SELECT * FROM users WHERE name = {user_input}\")\n```\n\nProvide specific issues and fixes."
}'

LLM Prompting

Basic Structure

[Role/Context] + [Task] + [Constraints] + [Output Format]

Role Prompting

infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "You are an expert data scientist with 15 years of experience in machine learning. Explain gradient descent to a beginner, using simple analogies."
}'

Task Clarity

# Bad: vague
"Help me with my code"

# Good: specific
"Debug this Python function that should return the sum of even numbers from a list, but returns 0 for all inputs:

def sum_evens(numbers):
    total = 0
    for n in numbers:
        if n % 2 == 0:
            total += n
        return total

Identify the bug and provide the corrected code."

Chain-of-Thought

infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Solve this step by step:\n\nA store sells apples for $2 each and oranges for $3 each. If someone buys 5 fruits and spends $12, how many of each fruit did they buy?\n\nThink through this step by step before giving the final answer."
}'

Few-Shot Examples

infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Convert these sentences to formal business English:\n\nExample 1:\nInput: gonna send u the report tmrw\nOutput: I will send you the report tomorrow.\n\nExample 2:\nInput: cant make the meeting, something came up\nOutput: I apologize, but I will be unable to attend the meeting due to an unforeseen circumstance.\n\nNow convert:\nInput: hey can we push the deadline back a bit?"
}'

Output Format Specification

infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Analyze the sentiment of these customer reviews. Return a JSON array with objects containing \"text\", \"sentiment\" (positive/negative/neutral), and \"confidence\" (0-1).\n\nReviews:\n1. \"Great product, fast shipping!\"\n2. \"Meh, its okay I guess\"\n3. \"Worst purchase ever, total waste of money\"\n\nReturn only valid JSON, no explanation."
}'

Constraint Setting

infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Summarize this article in exactly 3 bullet points. Each bullet must be under 20 words. Focus only on actionable insights, not background information.\n\n[article text]"
}'

Image Generation Prompting

Basic Structure

[Subject] + [Style] + [Composition] + [Lighting] + [Technical]

Subject Description

# Bad: vague
"a cat"

# Good: specific
infsh app run falai/flux-dev --input '{
  "prompt": "A fluffy orange tabby cat with green eyes, sitting on a vintage leather armchair"
}'

Style Keywords

infsh app run falai/flux-dev --input '{
  "prompt": "Portrait photograph of a woman, shot on Kodak Portra 400 film, soft natural lighting, shallow depth of field, nostalgic mood, analog photography aesthetic"
}'

Composition Control

infsh app run falai/flux-dev --input '{
  "prompt": "Wide establishing shot of a cyberpunk city skyline at night, rule of thirds composition, neon signs in foreground, towering skyscrapers in background, rain-slicked streets"
}'

Quality Keywords

photorealistic, 8K, ultra detailed, sharp focus, professional,
masterpiece, high quality, best quality, intricate details

Negative Prompts

infsh app run falai/flux-dev --input '{
  "prompt": "Professional headshot portrait, clean background",
  "negative_prompt": "blurry, distorted, extra limbs, watermark, text, low quality, cartoon, anime"
}'

Video Prompting

Basic Structure

[Shot Type] + [Subject] + [Action] + [Setting] + [Style]

Camera Movement

infsh app run google/veo-3-1-fast --input '{
  "prompt": "Slow tracking shot following a woman walking through a sunlit forest, golden hour lighting, shallow depth of field, cinematic, 4K"
}'

Action Description

infsh app run google/veo-3-1-fast --input '{
  "prompt": "Close-up of hands kneading bread dough on a wooden surface, flour dust floating in morning light, slow motion, cozy baking aesthetic"
}'

Temporal Keywords

slow motion, timelapse, real-time, smooth motion,
continuous shot, quick cuts, frozen moment

Advanced Techniques

System Prompts

infsh app run openrouter/claude-sonnet-45 --input '{
  "system": "You are a helpful coding assistant. Always provide code with comments. If you are unsure about something, say so rather than guessing.",
  "prompt": "Write a Python function to validate email addresses using regex."
}'

Structured Output

infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Extract information from this text and return as JSON:\n\n\"John Smith, CEO of TechCorp, announced yesterday that the company raised $50 million in Series B funding. The round was led by Venture Partners.\"\n\nSchema:\n{\n  \"person\": string,\n  \"title\": string,\n  \"company\": string,\n  \"event\": string,\n  \"amount\": string,\n  \"investor\": string\n}"
}'

Iterative Refinement

# Start broad
infsh app run falai/flux-dev --input '{
  "prompt": "A castle on a hill"
}'

# Add specifics
infsh app run falai/flux-dev --input '{
  "prompt": "A medieval stone castle on a grassy hill"
}'

# Add style
infsh app run falai/flux-dev --input '{
  "prompt": "A medieval stone castle on a grassy hill, dramatic sunset sky, fantasy art style, epic composition"
}'

# Add technical
infsh app run falai/flux-dev --input '{
  "prompt": "A medieval stone castle on a grassy hill, dramatic sunset sky, fantasy art style by Greg Rutkowski, epic composition, 8K, highly detailed"
}'

Multi-Turn Reasoning

# First: analyze
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Analyze this business problem: Our e-commerce site has a 70% cart abandonment rate. List potential causes."
}'

# Second: prioritize
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "Given these causes of cart abandonment: [previous output], rank them by likely impact and ease of fixing. Format as a priority matrix."
}'

# Third: action plan
infsh app run openrouter/claude-sonnet-45 --input '{
  "prompt": "For the top 3 causes identified, provide specific A/B tests we can run to validate and fix each issue."
}'

Model-Specific Tips

Claude

Excels at nuanced instructions
Responds well to role-playing
Good at following complex constraints
Prefers explicit output formats

GPT-4

Strong at code generation
Works well with examples
Good structured output
Responds to "let's think step by step"

FLUX

Detailed subject descriptions
Style references work well
Lighting keywords important
Negative prompts supported

Veo

Camera movement keywords
Cinematic language works well
Action descriptions important
Include temporal context

Common Mistakes

Mistake	Problem	Fix
Too vague	Unpredictable output	Add specifics
Too long	Model loses focus	Prioritize key info
Conflicting	Confuses model	Remove contradictions
No format	Inconsistent output	Specify format
No examples	Unclear expectations	Add few-shot

Prompt Templates

Code Review

Review this [language] code for:
1. Bugs and logic errors
2. Security vulnerabilities
3. Performance issues
4. Code style/best practices

Code:
[code]

For each issue found, provide:
- Line number
- Issue description
- Severity (high/medium/low)
- Suggested fix

Content Writing

Write a [content type] about [topic].

Audience: [target audience]
Tone: [formal/casual/professional]
Length: [word count]
Key points to cover:
1. [point 1]
2. [point 2]
3. [point 3]

Include: [specific elements]
Avoid: [things to exclude]

Image Generation

[Subject with details], [setting/background], [lighting type],
[art style or photography style], [composition], [quality keywords]

Related Skills

# Video prompting guide
npx skills add inference-sh/skills@video-prompting-guide

# LLM models
npx skills add inference-sh/skills@llm-models

# Image generation
npx skills add inference-sh/skills@ai-image-generation

# Full platform skill
npx skills add inference-sh/skills@infsh-cli

Browse all apps: infsh app list

Weekly Installs

7.3K

Repository

inferen-sh/skills

GitHub Stars

202

First Seen

14 days ago

Security Audits

Gen Agent Trust HubPass SocketWarn SnykPass

Installed on

claude-code5.8K

gemini-cli5.2K

codex5.2K

opencode5.2K

amp5.2K

kimi-cli5.2K

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

102,200 周安装

提示工程指南：掌握AI模型提示工程技巧与最佳实践

🇨🇳中文介绍

提示工程指南

快速开始

LLM 提示工程

基本结构

角色提示

相关 Skills

任务清晰度

思维链

少量示例

输出格式规范

约束设置

图像生成提示工程

基本结构

主体描述

风格关键词

构图控制

质量关键词

负面提示

视频提示工程

基本结构

摄像机运动

动作描述

时间关键词

高级技巧

系统提示

结构化输出

迭代优化

多轮推理

模型特定技巧

Claude

GPT-4

FLUX

Veo

常见错误

提示模板

代码审查

内容写作

图像生成

相关技能

🇺🇸English

Prompt Engineering Guide

Quick Start

LLM Prompting

Basic Structure

Role Prompting

Task Clarity

Chain-of-Thought

Few-Shot Examples

Output Format Specification

Constraint Setting

Image Generation Prompting

Basic Structure

Subject Description

Style Keywords

Composition Control

Quality Keywords

Negative Prompts

Video Prompting

Basic Structure

Camera Movement

Action Description

Temporal Keywords

Advanced Techniques

System Prompts

Structured Output

Iterative Refinement

Multi-Turn Reasoning

Model-Specific Tips

Claude

GPT-4

FLUX

Veo

Common Mistakes

Prompt Templates

Code Review

Content Writing

Image Generation

Related Skills