跳到主内容
智客 ZICQ

技能库 智客分类:媒体内容 image-generation

Image Generation

创建有效的 AI 图像生成提示 DALL- E, Midjourney, 和稳定扩散 。 生成各种样式的提示并使用大小写 .

4899 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

创建有效的 AI 图像生成提示 DALL- E, Midjourney, 和稳定扩散 。 生成各种样式的提示并使用大小写 .

何时用

官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Image Generation Skill、Overview、How to Use Me、Step 1: Describe Your Vision、Step 2: Choose the Platform、Step 3: Specify Parameters。 其中含规范建议的小节:分步指令。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。

官方 description(原文)

Create effective AI image generation prompts for DALL-E, Midjourney, and Stable Diffusion. Generate prompts for various styles and use cases.

Image Generation SkillOverviewHow to Use MeStep 1: Describe Your VisionStep 2: Choose the PlatformStep 3: Specify ParametersPrompt Engineering FrameworkBasic Prompt StructureDetailed TemplatePlatform-Specific TipsDALL-E 3Midjourney

· 许可:MIT

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
image-generation
description
Create effective AI image generation prompts for DALL-E, Midjourney, and Stable Diffusion. Generate prompts for various styles and use cases.
许可
MIT
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「image-generation」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-8d7a4df3c0352562-%E5%9B%BE%E5%83%8F%E7%94%9F%E6%88%90.html
请存为 .cursor/skills/image-generation/SKILL.md 或 .claude/skills/image-generation/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

npx skills add 'https://github.com/claude-office-skills/skills' --list

npx skills add 'https://github.com/claude-office-skills/skills' --skill 'image-generation'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版

═══════════════════════════════════════════════════════════════════════════════

CLAUDE OFFICE SKILL - Image Generation

═══════════════════════════════════════════════════════════════════════════════

name: image-generation description: "Create effective AI image generation prompts for DALL-E, Midjourney, and Stable Diffusion. Generate prompts for various styles and use cases." version: "1.0.0" author: claude-office-skills license: MIT

category: visualization tags:

  • image
  • ai-art
  • prompts
  • dall-e
  • midjourney department: Design/Marketing

models: recommended: - claude-sonnet-4 - claude-opus-4 compatible: - claude-3-5-sonnet - gpt-4 - gpt-4o

capabilities:

  • prompt_engineering
  • style_specification
  • composition_guidance
  • negative_prompting
  • prompt_optimization

languages:

  • en
  • zh

related_skills:

  • ppt-visual
  • infographic
  • brand-guidelines

Image Generation Skill

Overview

I help you create effective prompts for AI image generation tools like DALL-E, Midjourney, and Stable Diffusion. I understand the nuances of different platforms and can help you achieve specific visual styles.

What I can do:

  • Write detailed image generation prompts
  • Optimize prompts for specific AI tools
  • Suggest style keywords and modifiers
  • Create negative prompts to avoid unwanted elements
  • Adapt prompts for different aspect ratios
  • Generate variations and alternatives

What I cannot do:

  • Generate images directly
  • Guarantee exact output from AI tools
  • Predict how AI will interpret prompts
  • Bypass content policies of AI tools

How to Use Me

Step 1: Describe Your Vision

Tell me:

  • What you want to see in the image
  • The purpose (presentation, social media, marketing)
  • Style preferences (realistic, artistic, minimalist)
  • Mood or emotion to convey

Step 2: Choose the Platform

  • DALL-E 3: Best for clarity and instruction-following
  • Midjourney: Best for artistic and aesthetic images
  • Stable Diffusion: Most customizable, local options

Step 3: Specify Parameters

  • Aspect ratio (1:1, 16:9, 4:3, etc.)
  • Quality level
  • Style references
  • Things to avoid

Prompt Engineering Framework

Basic Prompt Structure

[Subject] + [Action/State] + [Environment] + [Style] + [Technical Parameters]

Detailed Template

[Main Subject]
- Who/what is the focus?
- What are they doing?

[Environment/Setting]
- Where is this taking place?
- Time of day? Weather? Season?

[Composition]
- Camera angle (eye-level, bird's eye, low angle)
- Framing (close-up, medium shot, wide shot)
- Focus (depth of field)

[Style]
- Art style (photorealistic, watercolor, oil painting, etc.)
- Artist reference (optional)
- Era/period

[Lighting]
- Type (natural, studio, dramatic, soft)
- Direction (backlit, side-lit, front-lit)

[Color]
- Palette (warm, cool, monochrome)
- Specific colors to include

[Mood/Atmosphere]
- Emotion to evoke
- Overall feeling

[Technical]
- Quality modifiers
- Aspect ratio
- Negative prompts

Platform-Specific Tips

DALL-E 3

Strengths:

  • Follows complex instructions well
  • Good at text in images
  • Natural language understanding

Prompt Style: Write naturally, be descriptive

A professional photograph of a modern office space with floor-to-ceiling 
windows overlooking a city skyline at sunset. The room features a minimalist 
wooden desk with a laptop, a potted monstera plant, and warm ambient lighting 
from a designer floor lamp. The mood is productive yet peaceful.

Midjourney

Strengths:

  • Exceptional aesthetics
  • Strong artistic styles
  • Good at specific looks

Prompt Style: Use keywords, parameters, and style references

modern office space, floor-to-ceiling windows, city skyline sunset, 
minimalist wooden desk, monstera plant, warm ambient lighting, 
productive atmosphere --ar 16:9 --style raw --v 6

Key Parameters:

  • --ar X:Y Aspect ratio
  • --v 6 Version
  • --style raw Less stylized
  • --q 2 Quality
  • --s 250 Stylize amount

Stable Diffusion

Strengths:

  • Highly customizable
  • Local/private generation
  • Extensive community models

Prompt Style: Weighted tokens, negative prompts essential

(modern office:1.2), (floor-to-ceiling windows:1.1), city skyline, 
golden hour sunset, minimalist wooden desk, laptop, monstera plant, 
(warm ambient lighting:1.3), professional photograph, 8k, detailed

Negative: cartoon, drawing, illustration, (worst quality:1.4), 
(low quality:1.4), blurry, watermark

Style Keywords Reference

Photography Styles

| Style | Keywords | |-------|----------| | Portrait | portrait photography, headshot, bokeh, 85mm lens | | Product | product photography, studio lighting, white background | | Landscape | landscape photography, golden hour, dramatic sky | | Street | street photography, candid, urban, documentary | | Fashion | fashion editorial, vogue style, high fashion |

Art Styles

| Style | Keywords | |-------|----------| | Realistic | photorealistic, hyperrealistic, 8k, detailed | | Illustration | digital illustration, vector art, flat design | | Watercolor | watercolor painting, soft edges, flowing colors | | Oil Painting | oil painting, brush strokes, impasto | | Anime | anime style, manga, cel shading | | 3D Render | 3D render, octane render, blender, CGI |

Mood/Atmosphere

| Mood | Keywords | |------|----------| | Professional | corporate, business, clean, modern | | Cozy | warm, inviting, comfortable, hygge | | Dramatic | cinematic, high contrast, moody lighting | | Cheerful | bright, colorful, happy, vibrant | | Minimalist | simple, clean, whitespace, zen |

Lighting

| Type | Keywords | |------|----------| | Natural | natural light, soft daylight, golden hour | | Studio | studio lighting, softbox, rim light | | Dramatic | chiaroscuro, dramatic shadows, volumetric | | Neon | neon lights, cyberpunk, colorful glow |


Output Format

# Image Generation Prompts: [Concept]

**Purpose**: [What the image is for]
**Target Platform**: [DALL-E / Midjourney / SD]
**Aspect Ratio**: [X:Y]

---

## Primary Prompt

### For DALL-E 3:

[Natural language prompt with full description]


### For Midjourney:

[Keyword-based prompt with parameters]


### For Stable Diffusion:

[Weighted prompt]

Negative: [Things to avoid]


---

## Variations

### Variation 1: [Description]

[Prompt]


### Variation 2: [Description]

[Prompt]


### Variation 3: [Description]

[Prompt]


---

## Style Alternatives

### Option A: [Style Name]
Add these keywords: `[keywords]`

### Option B: [Style Name]
Add these keywords: `[keywords]`

---

## Tips for This Image

1. [Specific tip for achieving desired result]
2. [Tip]
3. [Tip]

---

## Iteration Suggestions

If the result isn't quite right:
- Try: [Adjustment 1]
- Try: [Adjustment 2]
- Try: [Adjustment 3]

Common Use Cases

Business/Corporate

Professional headshot, corporate portrait, business casual attire, 
neutral background, studio lighting, confident expression, 
sharp focus, high resolution

Marketing/Social Media

Lifestyle product photography, natural setting, soft natural light, 
pastel color palette, Instagram aesthetic, flat lay composition, 
millennial pink, minimalist

Presentation Graphics

Abstract business concept, isometric illustration, blue and white 
color scheme, clean design, corporate style, flat design, 
technology theme, professional

Blog/Article Headers

Wide banner image, [topic] concept art, editorial style, 
cinematic composition, 16:9 aspect ratio, headline-friendly 
(space for text overlay), muted colors

Tips for Better Results

  1. Be specific - "golden retriever" > "dog"
  2. Describe what you want, not what you don't (use negative prompts separately)
  3. Use quality modifiers - "professional", "detailed", "8k"
  4. Reference styles - "in the style of [artist/genre]"
  5. Specify composition - "close-up", "wide shot", "bird's eye view"
  6. Include lighting - dramatically affects mood
  7. Iterate - refine based on results
  8. Use consistent seeds for variations (when possible)

Limitations

  • Cannot generate images directly
  • Results vary between AI platforms
  • Some concepts are restricted by platform policies
  • Exact output is unpredictable
  • May require multiple iterations

Built by the Claude Office Skills community. Contributions welcome!

相关技能

媒体内容

Nano Banana Pro

以纳米·香蕉Pro(Gemini 3 Pro Image)来生成/编辑图像. 用于创建/修改请求,包括编辑。 支持文本到图像+图像到图像; 1K/2K/4K; 使用 -- input-image.

媒体内容

Youtube Watcher

从YouTube视频中获取并读取文字记录. 需要汇总视频时使用,回答有关视频内容的问题,或者从中提取信息.

媒体内容

Atxp

Access ATXP支付API工具用于网页搜索,AI图像生成,音乐创建,视频生成,X/Twitter搜索,电子邮件,代理账户管理. 当用户需要实时网络搜索时使用,AI生成的媒体(图像,音乐,视频),X/Twitter搜索,发送/接收电子邮件,或创建和资助代理账户. 需要通过“ …

媒体内容

Youtube

YouTube Data API与管理的OAuth的集成. 搜索视频,管理播放列表,访问频道数据,并与评论互动. 用户想与YouTube互动时使用此技能. 对于其他第三方应用,使用api-gateway技能(https://clawhub.ai/byungkyu/api-gate…