document-illustrator

Document Illustrator Skill

A document illustration generation tool based on AI intelligent analysis. No need to rely on a specific format; it automatically understands the content and generates professional illustrations.

🎯 Core Features

✨ AI Intelligent Summarization: Automatically understands document content and intelligently extracts core topics
🎨 Format Agnostic: Supports documents in any format (Markdown, plain text, PDF, etc.)
📐 Flexible Ratios: Supports 16:9 (landscape) and 3:4 (portrait)
🖼️ Optional Cover Image: Can generate a cover image that summarizes the entire text
🎭 Three Styles: Gradient glass card, ticket style, vector illustration

🚀 How to Use

Tell Claude directly

帮我为这个文档生成配图：/path/to/document.md

Or:

我想为这篇文章生成一些配图

📝 Complete Workflow

Step 1: Claude reads and understands the document

When you request illustration generation, Claude will:

Use the Read tool to read the complete document
AI analyzes and understands the document content and structure
Identify core topics and key points

No need to worry about document format：

✅ Standard Markdown (##, ###)
✅ Separator line format (======, ------)
✅ Plain text paragraphs
✅ Any other format

Step 2: Configure options (3 questions)

Claude will ask for your preferences:

Question 1: Image aspect ratio

请选择图片比例：
1. 16:9 (横屏) - 适合演示文稿、幻灯片、横屏展示
2. 3:4 (竖屏) - 适合社交媒体、手机查看、海报

请选择 (1/2):

Question 2: Cover image

是否生成封面图？
封面图将概括文档的所有核心信息，作为系列配图的引导。

1. 是 - 生成封面图 + 内容配图
2. 否 - 仅生成内容配图

请选择 (1/2):

Question 3: Number of content illustrations

期望生成多少张内容配图？
建议范围：3-10 张
根据文档内容，推荐生成 6 张

请输入数字：

Step 3: Claude summarizes the content and displays it

Based on the number you specify, Claude will intelligently summarize the document and then display it for your confirmation:

📋 内容归纳完成

📄 封面图内容：（如果选择生成）
"AI 编程工具概念演化：从 Rules 到 Skills"
- 核心概念：静态上下文 vs 动态上下文
- 演化路径：Rules → Commands → MCP → Modes → Skills
- 最佳实践：简化为两个核心工具

📚 内容配图（共 6 张）：

1. Rules 的诞生与演化
   包含：早期模型幻觉问题、rules 文件的作用、静态上下文概念

2. Commands 和工作流打包
   包含：固定工作流的出现、slash command、团队分享

3. MCP Servers 带来动态能力
   包含：第三方工具集成、OAuth 认证、上下文膨胀问题

4. Modes 和 Subagents 的登场
   包含：人设提示词、系统提示词修改、可靠性设计、Hooks 确定性

5. Skills 统一动态上下文
   包含：Skills 概念、动态加载、编程工具优化

6. 最佳实践与未来展望
   包含：Rules 使用建议、Skills 探索、核心理念总结

✓ 所有内容已覆盖，无遗漏

确认开始生成配图吗？(Y/N)

Key Guarantees：

✅ Complete content: All important information will be included in one of the images
✅ Clear logic: Segmented according to the natural logic of the content
✅ User-controllable: Displays the summarization results and waits for user confirmation

Step 4: Generate illustrations

After confirmation, Claude calls a Python script to generate the images:

🖼️  开始生成配图...

正在生成封面图...
  ✓ 已保存: /path/to/document/images/cover.png

正在生成第 1/6 张...
  标题: Rules 的诞生与演化
  ✓ 已保存: /path/to/document/images/illustration-01.png

正在生成第 2/6 张...
  标题: Commands 和工作流打包
  ✓ 已保存: /path/to/document/images/illustration-02.png

...

✨ 完成！共生成 7 张配图（1 张封面 + 6 张内容）

Step 5: Output results

Output location: The images/ folder in the directory where the document is located

/path/to/your/document/
└── images/
    ├── cover.png              # 封面图（如果选择生成）
    ├── illustration-01.png    # 第 1 张内容配图
    ├── illustration-02.png    # 第 2 张内容配图
    ├── illustration-03.png
    ├── illustration-04.png
    ├── illustration-05.png
    └── illustration-06.png

🎨 Explanation of the Three Styles

1. Gradient glass card style (gradient-glass)

Features：

Apple Keynote-style minimalism
Glassmorphism design
Deep void black or pure ceramic white base
Flowing aurora gradient colors
3D glass objects and glowing effects

Applicable scenarios：

Technology product introductions
Data analysis reports
Future trend outlooks
Product feature demonstrations

2. Ticket style (ticket)

Features：

Digital minimalist ticket design
High-contrast black and white color scheme
Structure similar to boarding passes and tickets
Precise geometric partitions
Mixed Chinese and English typesetting, multi-directional text layout

Use Cases：

Infographics
Statistical data presentation
Timelines and flowcharts
Key point summaries

3. Vector illustration style (vector-illustration)

Features：

Flat vector illustration
Uniform-thickness black outlines
Retro soft color palette
Geometric treatment
Horizontal panoramic composition

Use Cases：

Storytelling
Concept explanation
Educational content
Brand promotion

💡 Usage Examples

Example 1: Complete workflow

用户: 帮我为 ~/blog/ai-tools.md 生成配图，用票据风格

Claude: 好的，让我先读取这个文档...
        [读取文档，分析内容]

        检测到文档长度约 3000 字，内容涉及 AI 工具演化。

        请选择图片比例：
        1. 16:9 (横屏)
        2. 3:4 (竖屏)

用户: 1

Claude: 是否生成封面图？
        1. 是
        2. 否

用户: 是

Claude: 期望生成多少张内容配图？
        建议范围：3-10 张
        根据文档内容，推荐生成 5 张

用户: 5

Claude: [展示归纳的 5 个主题]
        确认开始生成配图吗？

用户: Y

Claude: [调用 Python 脚本生成 6 张图片]
        ✨ 完成！配图已保存到 ~/blog/images/

Example 2: Plain text document

用户: 为这个纯文本笔记生成配图

Claude: [读取笔记，即使没有任何标题也能理解内容]
        [智能识别 3 个核心主题]
        [询问配置、展示归纳、生成配图]

Example 3: Custom quantity

用户: 我想要 8 张图，竖屏的，不要封面

Claude: 好的，16:9 竖屏，不生成封面，8 张内容配图。
        [将文档归纳为 8 个主题]
        [展示归纳结果，用户确认后生成]

🔧 Technical Details

Image Specifications

Aspect ratio	Resolution	Use Cases
16:9	2560x1440 (2K)	Presentations, landscape display
3:4	1920x2560	Social media, portrait viewing

Optional 4K resolution:

16:9 → 3840x2160
3:4 → 2880x3840

API Calls

Model：Gemini 2.0 Flash Image Preview (Nano Banana Pro)
Cost: 1 API call per image
Speed: average 10-20 seconds/image

Environment Requirements

Required：

pip install google-genai pillow python-dotenv

API Key：

In ~/.claude/skills/document-illustrator/.env configuration
or set the environment variable GEMINI_API_KEY

📊 Content Summarization Principles

Claude follows these principles when summarizing content:

1. Completeness first

✅ All important information will be included
✅ Key concepts will not be omitted
✅ Retain the core viewpoints of the original text

2. Clear logic

Segment according to the natural logic of the content
Group related content together
Maintain narrative coherence

3. Balanced distribution

Each image contains a similar amount of information
Avoid making one image too crowded or too empty
Adjust according to the importance of the content

4. User controllable

Show the summarization result to the user for confirmation
The user can request adjustments
Start generation only after confirmation

🐛 Troubleshooting

Issue 1: API key error

Error message：

Error: Invalid API key

Solution：

Check .env in the GEMINI_API_KEY
Ensure the API key is valid and has not expired
Get a new key:https://makersuite.google.com/app/apikey

Issue 2: Unsatisfactory content summarization

Issue: The summarized topics do not meet expectations

Solution：

During the summarization presentation stage, tell Claude your expectations
Claude will re-summarize and adjust
Start generation only after you are satisfied and confirm

Issue 3: Image generation failed

Possible causes：

Network connection issues
API quota exhausted
Content too long and exceeds the limit

Solution：

Check the network connection
Check the API quota
Try increasing the number of images (to distribute the content)

💰 Cost Estimation

Number of images	Number of API calls	Estimated Cost
No cover + 3 images	3 times	Low
With cover + 5 images	6 times	Medium
With cover + 10 images	11 times	Relatively high

Recommendations：

Short document (<1000 words): 3-5 images
Medium document (1000-3000 words): 5-7 images
Long document (>3000 words): 8-10 images

📚 Best Practices

1. Choose a reasonable number of images

Too few：

Each image carries too much information
Hard to understand and remember

Too many：

Content is scattered
Increases cost and generation time

Recommended：

Choose based on document length
Each image covers 1-2 core points

2. Choose the aspect ratio based on use case

16:9 is suitable for：

PPT presentations
Website banners
Video covers
Blog images (desktop)

3:4 is suitable for：

Social media (Instagram, Xiaohongshu)
Mobile articles
Poster design
Vertical videos

3. Use of cover images

Scenarios where generating a cover image is recommended：

Article series (as a unified introduction)
Social sharing (as a preview image)
Document homepage (summarizes the full text)

Scenarios where it can be skipped：

Internal use only
The number of images is already sufficient
Want to reduce costs

4. Style selection recommendations

Technical documentation → Gradient glass card style Data reports → Receipt style Tutorial stories → Vector illustration style Product introductions → Gradient glass card style

🔄 How It Works

Traditional approach (deprecated)

[代码] 读取文档 → 识别 ## ### 标题 → 机械切分
       ↓
    依赖特定格式
    容易遗漏内容
    不够智能

New approach (current implementation)

[Claude] 读取文档 → AI 理解内容 → 智能归纳主题
         ↓
      格式无关
      内容完整
      用户可控

Core differences：

❌ Old approach: relies on code parsing, can only handle standard formats
✅ New approach: AI understands the content, can handle any format

🎯 Comparison with other tools

Feature	Document Illustrator	Traditional PPT tools	AI image generators
Understands document content	✅ AI intelligent understanding	❌ Requires manual work	❌ Requires manual input
Format dependency	✅ Format-agnostic	❌ Depends on specific formats	✅ No dependency
Content completeness	✅ Automatic verification	⚠️ Manual assurance	❌ Cannot guarantee
Batch generation	✅ Generate multiple at once	❌ Create one by one	⚠️ Requires multiple inputs
Style consistency	✅ Automatically maintained	⚠️ Manual adjustment	⚠️ Requires repeated prompts

📞 Get Help

If you have questions or suggestions:

Ask Claude directly in Claude Code
View the plan file:~/.claude/plans/shimmering-tickling-seahorse.md
Check the Skill directory:~/.claude/skills/document-illustrator/

Let AI help you understand and summarize the content, and generate professional illustrations! ✨

About this skill

🎯 Core Features

🚀 How to Use

Tell Claude directly

📝 Complete Workflow

Step 1: Claude reads and understands the document

Step 2: Configure options (3 questions)

Question 1: Image aspect ratio

Question 2: Cover image

Question 3: Number of content illustrations

Step 3: Claude summarizes the content and displays it

Step 4: Generate illustrations

Step 5: Output results

🎨 Explanation of the Three Styles

1. Gradient glass card style (gradient-glass)

2. Ticket style (ticket)

3. Vector illustration style (vector-illustration)

💡 Usage Examples

Example 1: Complete workflow

Example 2: Plain text document

Example 3: Custom quantity

🔧 Technical Details

Image Specifications

API Calls

Environment Requirements

📊 Content Summarization Principles

1. Completeness first

2. Clear logic

3. Balanced distribution

4. User controllable

🐛 Troubleshooting

Issue 1: API key error

Issue 2: Unsatisfactory content summarization

Issue 3: Image generation failed

💰 Cost Estimation

📚 Best Practices

1. Choose a reasonable number of images

2. Choose the aspect ratio based on use case

3. Use of cover images

4. Style selection recommendations

🔄 How It Works

Traditional approach (deprecated)

New approach (current implementation)

🎯 Comparison with other tools

📞 Get Help