prompt-engineering

安装 belt CLI 技能： npx skills add belt-sh/cli

提示词工程指南

通过 inference.sh CLI 掌握 AI 模型的提示词工程。

快速开始

需要 inference.sh CLI（belt）。安装说明

belt login

# Well-structured LLM prompt
belt 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."
}'

大模型提示

基本结构

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

角色提示

belt 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."
}'

明确任务

# 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."

思维链

belt 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."
}'

少样本示例

belt 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?"
}'

输出格式规范

belt 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."
}'

设定约束

belt 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]"
}'

图像生成提示

基本结构

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

主体描述

# Bad: vague
"a cat"

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

风格关键词

belt 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"
}'

构图控制

belt 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"
}'

质量关键词

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

负面提示词

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

视频提示

基本结构

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

摄像机运动

belt 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"
}'

动作描述

belt 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"
}'

时间关键词

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

高级技巧

系统提示词

belt 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."
}'

结构化输出

belt 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}"
}'

迭代优化

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

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

# Add style
belt 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
belt 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"
}'

多轮推理

# First: analyze
belt 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
belt 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
belt 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."
}'

特定模型的技巧

Claude

• 擅长理解细致的指令
• 对角色扮演响应良好
• 善于遵循复杂约束
• 偏好明确的输出格式

GPT-4

• 擅长代码生成
• 能很好地利用示例
• 擅长结构化输出
• 对“让我们一步一步思考”这类提示有响应

FLUX

• 详细描述主体
• 风格参考效果良好
• 光照关键词很重要
• 支持负面提示词

Veo

• 使用摄像机运动关键词
• 电影化语言效果良好
• 动作描述很重要
• 加入时间背景

常见错误

错误	问题	修正方法
过于含糊	输出不可预测	补充具体信息
过于冗长	模型容易偏离重点	优先提供关键信息
相互矛盾	令模型困惑	删除矛盾内容
未指定格式	输出不一致	指定格式
没有示例	预期不明确	添加少样本示例

提示词模板

代码审查

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

内容创作

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]

图像生成

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

相关技能

# 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

浏览所有应用：belt app list