Back to Creative & Visual

baoyu-article-illustrator

AIillustrationcontent creationarticlevisualsmarkdownimage generationdocumentation
⭐ 21.7kπŸ•’ 2026-06-13Source β†—

Install this skill

npx skills add jimliu/baoyu-skills

Works across Claude Code, Cursor, Codex, Copilot & Antigravity

baoyu-article-illustrator transforms markdown text into visual assets by parsing structural hierarchy and core concepts. Instead of relying on manual image creation, the agent identifies specific document segments requiring graphic supplementation and generates contextually relevant illustrations. It offers over twenty distinct aesthetic presets ranging from technical blueprints and scientific diagrams to minimalist line art and nostalgic pixel styles. When processing a document, the tool generates a structured output directory containing source materials, generated image concepts, and individual style variants. The agent automates the entire pipeline, from topic slug generation based on content analysis to the delivery of curated PNG illustrations that align with the textual tone and subject matter, making it suitable for content creators looking to enhance long-form articles with consistent, high-quality graphics without needing external design software.

When to Use This Skill

  • β€’Adding technical diagrams to system design documentation
  • β€’Generating hand-drawn style headers for personal growth blogs
  • β€’Creating infographic-style assets for professional journalism
  • β€’Producing pixel-art visuals for retro-themed developer tutorials

How to Invoke This Skill

Example prompts that trigger this skill in Claude Code, Cursor, or Antigravity:

  • β€œCreate visuals for my article about machine learning
  • β€œGenerate illustrations for this markdown draft
  • β€œAdd watercolor style images to this document
  • β€œIllustrate my guide on productivity workflows
  • β€œCreate a blueprint style graphic for this system architecture

Pro Tips

  • πŸ’‘Experiment with different `--style` options (e.g., `notion`, `elegant`, `warm`) to find the perfect aesthetic that matches your article's tone and target audience.
  • πŸ’‘For optimal results, ensure your article has clear headings and distinct sections, as this helps the AI identify prime locations for relevant illustrations.
  • πŸ’‘Consider generating illustrations in a default style first to check placement and relevance, then refine with a more specific style once satisfied with the visual context.

What this skill does

  • β€’Automatic structural analysis to identify optimal illustration placement
  • β€’Twenty-plus predefined visual style categories
  • β€’Content-aware style selection engine
  • β€’Organized directory generation with source tracing and concept outlines
  • β€’Support for specific stylistic overrides via command-line arguments

When not to use it

  • βœ•When you require specific brand-compliant vector assets with exact corporate color palettes
  • βœ•For documents that do not follow a logical structure or markdown format

Example workflow

  1. Draft your long-form markdown article with clear section headers
  2. Run /baoyu-article-illustrator path/to/article.md to trigger auto-detection
  3. Review the generated outline in the output directory
  4. Use a specific flag like --style minimal if the default output needs refinement
  5. Select the preferred PNG concepts from the generated prompts folder

Prerequisites

  • –Markdown file containing the content to be illustrated

Pitfalls & limitations

  • !Automated style selection may misinterpret the desired tone if the article covers broad or conflicting topics
  • !The agent generates broad concepts; it cannot edit specific text inside the generated images
  • !Naming conflicts occur if the tool is run multiple times on the same folder without renaming previous outputs

FAQ

Can I define a custom illustration style?
The tool uses a predefined list of styles found in the style gallery; you cannot add custom artistic styles at this time.
What happens if I don't specify a style?
The agent scans your text for keywords and emotional indicators to map your content to the most appropriate style, defaulting to 'notion' style if no match is found.
Where are my images stored?
All outputs are organized in a directory named after your article's topic slug within the illustrations folder.

How it compares

Unlike generic image generation prompts, this skill enforces structure by keeping consistent artistic styles across multiple images in a single article, ensuring a unified visual identity.

Source & trust

⭐ 22k starsπŸ•’ Updated 2026-06-13
πŸ“„ Full skill instructions β€” original source: jimliu/baoyu-skills
# Smart Article Illustration Skill

Analyze article structure and content, identify positions requiring visual aids, and generate illustrations with flexible style options.

## Usage

# Auto-select style based on content
/baoyu-article-illustrator path/to/article.md

# Specify a style
/baoyu-article-illustrator path/to/article.md --style warm
/baoyu-article-illustrator path/to/article.md --style minimal
/baoyu-article-illustrator path/to/article.md --style watercolor

# Combine with other options
/baoyu-article-illustrator path/to/article.md --style playful


## Options

| Option | Description |
|--------|-------------|
| --style <name> | Specify illustration style (see Style Gallery below) |

## Style Gallery

| Style | Description | Best For |
|-------|-------------|----------|
| notion (Default) | Minimalist hand-drawn line art, intellectual | Knowledge sharing, SaaS, productivity |
| elegant | Refined, sophisticated, professional | Business, thought leadership |
| warm | Friendly, approachable, human-centered | Personal growth, lifestyle, education |
| minimal | Ultra-clean, zen-like, focused | Philosophy, minimalism, core concepts |
| playful | Fun, creative, whimsical | Tutorials, beginner guides, fun topics |
| nature | Organic, calm, earthy | Sustainability, wellness, outdoor |
| sketch | Raw, authentic, notebook-style | Ideas, brainstorming, drafts |
| watercolor | Soft artistic with natural warmth | Lifestyle, travel, creative |
| vintage | Nostalgic aged-paper aesthetic | Historical, biography, heritage |
| scientific | Academic precise diagrams | Biology, chemistry, technical |
| chalkboard | Classroom chalk drawing style | Education, tutorials, workshops |
| editorial | Magazine-style infographic | Tech explainers, journalism |
| flat | Modern flat vector illustration | Startups, digital, contemporary |
| flat-doodle | Bold outlines, pastel colors, cute | Productivity, SaaS, workflows |
| retro | 80s/90s vibrant nostalgic | Pop culture, gaming, entertainment |
| blueprint | Technical schematics, engineering precision | Architecture, system design |
| vector-illustration | Flat vector with black outlines, retro colors | Educational, creative, brand content |
| sketch-notes | Soft hand-drawn, warm educational feel | Knowledge sharing, tutorials |
| pixel-art | Retro 8-bit gaming aesthetic | Gaming, tech, developer content |
| intuition-machine | Technical briefing with bilingual labels | Academic, technical, bilingual |
| fantasy-animation | Ghibli/Disney whimsical style | Storytelling, children's, creative |

Full style specifications in references/styles/<style>.md

## Auto Style Selection

When no --style is specified, analyze content to select the best style:

| Content Signals | Selected Style |
|----------------|----------------|
| Personal story, emotion, growth, life, feeling, relationship | warm |
| Simple, zen, focus, essential, core, minimalist | minimal |
| Fun, easy, beginner, tutorial, guide, how-to, learn | playful |
| Nature, eco, wellness, health, organic, green, outdoor | nature |
| Idea, thought, concept, draft, brainstorm, sketch | sketch |
| Business, professional, strategy, analysis, corporate | elegant |
| Knowledge, concept, productivity, SaaS, notion, tool | notion |
| Lifestyle, travel, food, art, creative, artistic | watercolor |
| History, heritage, vintage, biography, classic, expedition | vintage |
| Biology, chemistry, medical, scientific, research, academic | scientific |
| Education, classroom, teaching, school, lecture, workshop | chalkboard |
| Explainer, journalism, magazine, in-depth, investigation | editorial |
| Modern, startup, app, product, digital marketing, saas | flat |
| Productivity, workflow, cute, tools, app tutorial | flat-doodle |
| 80s, 90s, retro, pop culture, music, nostalgia | retro |
| Architecture, system, infrastructure, engineering, technical | blueprint |
| Brand, explainer, children, cute, toy, geometric | vector-illustration |
| Notes, doodle, friendly, warm tutorial, onboarding | sketch-notes |
| Gaming, 8-bit, pixel, developer, retro tech | pixel-art |
| Bilingual, briefing, academic, research, documentation | intuition-machine |
| Fantasy, story, magical, Ghibli, Disney, children | fantasy-animation |
| Default | notion |

## File Management

### Output Directory

Each session creates an independent directory named by content slug:

illustrations/{topic-slug}/
β”œβ”€β”€ source-{slug}.{ext} # Source files (text, images, etc.)
β”œβ”€β”€ outline.md
β”œβ”€β”€ outline-{style}.md # Style variant outlines
β”œβ”€β”€ prompts/
β”‚ β”œβ”€β”€ illustration-concept-a.md
β”‚ β”œβ”€β”€ illustration-concept-b.md
β”‚ └── ...
β”œβ”€β”€ illustration-concept-a.png
β”œβ”€β”€ illustration-concept-b.png
└── ...


**Slug Generation**:
1. Extract main topic from content (2-4 words, kebab-case)
2. Example: "The Future of AI" β†’ future-of-ai

### Conflict Resolution

If illustrations/{topic-slug}/ already exists:
- Append timestamp: {topic-slug}-YYYYMMDD-HHMMSS
- Example: ai-future exists β†’ ai-future-20260118-143052

### Source Files

Copy all sources with naming source-{slug}.{ext}:
- source-article.md (main text content)
- source-photo.jpg (image from conversation)
- source-reference.pdf (additional file)

Multiple sources supported: text, images, files from conversation.

## Workflow

### Step 1: Analyze Content & Select Style

1. Read article content
2. If --style specified, use that style
3. Otherwise, scan for style signals and auto-select
4. **Language detection**:
- Detect **source language** from article content
- Detect **user language** from conversation context
- Note if source_language β‰  user_language (will ask in Step 4)
5. Extract key information:
- Main topic and themes
- Core messages per section
- Abstract concepts needing visualization

### Step 2: Identify Illustration Positions

**Three Purposes of Illustrations**:
1. **Information Supplement**: Help understand abstract concepts
2. **Concept Visualization**: Transform abstract ideas into concrete visuals
3. **Imagination Guidance**: Create atmosphere, enhance reading experience

**Content Suitable for Illustrations**:
- Abstract concepts needing visualization
- Processes/steps needing diagrams
- Comparisons needing visual representation
- Core arguments needing reinforcement
- Scenarios needing imagination guidance

**Illustration Count**:
- Consider at least 1 image per major section
- Prioritize core arguments and abstract concepts
- **Principle: More is better than fewer**

### Step 3: Generate Illustration Plan

# Illustration Plan

**Article**: [article path]
**Style**: [selected style]
**Illustration Count**: N images

---

## Illustration 1

**Insert Position**: [section name] / [paragraph description]
**Purpose**: [why illustration needed here]
**Visual Content**: [what the image should show]
**Filename**: illustration-[slug].png

---

## Illustration 2
...


### Step 4: Review & Confirm

**Purpose**: Let user confirm all options in a single step before image generation.

**IMPORTANT**: Present ALL options in a single confirmation step using AskUserQuestion. Do NOT interrupt workflow with multiple separate confirmations.

1. **Generate 3 style variants**:
- Analyze content to select 3 most suitable styles
- Generate complete illustration plan for each style variant
- Save as outline-{style}.md (e.g., outline-notion.md, outline-tech.md, outline-warm.md)

2. **Determine which questions to ask**:

| Question | When to Ask |
|----------|-------------|
| Style variant | Always (required) |
| Language | Only if source_language β‰  user_language |

3. **Present options** (use AskUserQuestion with all applicable questions):

**Question 1 (Style)** - always:
- Style A (recommended): [style name] - [brief description]
- Style B: [style name] - [brief description]
- Style C: [style name] - [brief description]
- Custom: Provide custom style reference

**Question 2 (Language)** - only if source β‰  user language:
- [Source language] (matches article language)
- [User language] (your preference)

**Language handling**:
- If source language = user language: Just inform user (e.g., "Prompts will be in Chinese")
- If different: Ask which language to use for prompts

4. **Apply selection**:
- Copy selected outline-{style}.md to outline.md
- If custom style provided, generate new plan with that style
- If different language selected, regenerate outline in that language
- User may edit outline.md directly for fine-tuning
- If modified, reload plan before proceeding

5. **Proceed only after explicit user confirmation**

### Step 5: Create Prompt Files

Save prompts to prompts/ directory with style-specific details.

**All prompts are written in the user's confirmed language preference.**

**Prompt Format**:

Illustration theme: [concept in 2-3 words]
Style: [style name]

Visual composition:
- Main visual: [description matching style]
- Layout: [element positioning]
- Decorative elements: [style-appropriate decorations]

Color scheme:
- Primary: [style primary color]
- Background: [style background color]
- Accent: [style accent color]

Text content (if any):
- [Any labels or captions in content language]

Style notes: [specific style characteristics]


### Step 6: Generate Images

**Image Generation Skill Selection**:
1. Check available image generation skills
2. If multiple skills available, ask user to choose

**Generation Flow**:
1. Call selected image generation skill with prompt file and output path
2. Generate images sequentially
3. After each image, output progress: "Generated X/N"
4. On failure, auto-retry once
5. If retry fails, log reason, continue to next

### Step 7: Update Article

Insert generated images at corresponding positions:

![illustration description]([article-name]/illustrations/illustration-[slug].png)


**Insertion Rules**:
- Insert image after corresponding paragraph
- Leave one blank line before and after image
- Alt text uses concise description in article's language

### Step 8: Output Summary

Article Illustration Complete!

Article: [article path]
Style: [style name]
Generated: X/N images successful

Illustration Positions:
- illustration-xxx.png β†’ After section "Section Name"
- illustration-yyy.png β†’ After section "Another Section"
...

[If any failures]
Failed:
- illustration-zzz.png: [failure reason]


## Illustration Modification

Support for modifying individual illustrations after initial generation.

### Edit Single Illustration

Regenerate a specific illustration with modified prompt:

1. Identify illustration to edit (e.g., illustration-concept-overview.png)
2. Update prompt in prompts/illustration-concept-overview.md if needed
3. If content changes significantly, update slug in filename
4. Regenerate image
5. Update article if image reference changed

### Add New Illustration

Add a new illustration to the article:

1. Identify insertion position in article
2. Create new prompt with appropriate slug (e.g., illustration-new-concept.md)
3. Generate new illustration image
4. Update outline.md with new illustration entry
5. Insert image reference in article at the specified position

### Delete Illustration

Remove an illustration from the article:

1. Identify illustration to delete (e.g., illustration-concept-overview.png)
2. Remove image file and prompt file
3. Remove image reference from article
4. Update outline.md to remove illustration entry

### File Naming Convention

Files use meaningful slugs for better readability:
illustration-[slug].png
illustration-[slug].md (in prompts/)


Examples:
- illustration-concept-overview.png
- illustration-workflow-diagram.png
- illustration-key-benefits.png

**Slug rules**:
- Derived from illustration purpose/content (kebab-case)
- Must be unique within the article
- When content changes significantly, update slug accordingly

## References

| File | Content |
|------|---------|
| references/styles/<style>.md | Full style specifications with colors, elements, rules |

## Notes

- Illustrations serve the content: supplement information, visualize concepts
- Maintain selected style consistency across all illustrations in one article
- Image generation typically takes 10-30 seconds per image
- Sensitive figures should use cartoon alternatives
- Prompts written in user's confirmed language preference
- Illustration text (labels, captions) should match article language

## Extension Support

Custom styles and configurations via EXTEND.md.

**Check paths** (priority order):
1. .baoyu-skills/baoyu-article-illustrator/EXTEND.md (project)
2. ~/.baoyu-skills/baoyu-article-illustrator/EXTEND.md (user)

If found, load before Step 1. Extension content overrides defaults.

How to Use This Skill Unit

Option A: Project-Specific (Recommended)

  1. Click "Download" above
  2. In your project, create the directory: .agent/skills/baoyu-article-illustrator/
  3. Save the file as SKILL.md
  4. The agent will automatically discover the skill based on its description.

Option B: Global Installation (All Agents)

Save the file to these locations to make it available across all projects:

  • Claude Code: ~/.claude/skills/jimliu/baoyu-skills/baoyu-article-illustrator/SKILL.md
  • Cursor: ~/.cursor/skills/jimliu/baoyu-skills/baoyu-article-illustrator/SKILL.md
  • Antigravity: ~/.gemini/antigravity/skills/jimliu/baoyu-skills/baoyu-article-illustrator/SKILL.md

πŸš€ Install with CLI:
npx skills add jimliu/baoyu-skills

Read the Master Guide: Mastering Agent Skills β†’

Recommended Rules

View more rules β†’

Recommended Workflows

View more workflows β†’

Recommended MCP Servers

View more MCP servers β†’

Take It Further

Maximize your productivity with these powerful resources

πŸ“‹

Define Your Standards

Set up coding standards to ensure this workflow produces consistent, high-quality results.

Browse Rules Library
πŸ“–

Master Workflows

Learn how to create custom workflows, use Turbo Mode, and build your automation library.

Complete Guide

How to use this Skill in Claude Code & Cursor

For Claude Code (CLI)

To use this skill in Claude Code, copy the rule content into your project's custom instructions or follow our Add-Skill CLI guide. This ensures Claude follows your standards during every code generation.

For Cursor & Windsurf

For Cursor or Windsurf, individual skills are best used in the "Rules for AI" section. This specific unit helps the agent avoid creative & visual issues, leading to cleaner, more efficient code.

Why the skill format matters: the standardized Agent Skills format lets your AI agent load detailed instructions only when they are relevant, keeping your prompt clean while improving results.

Source & attribution

This skill is categorized under Creative & Visual and is published by Jim Liu, maintained in jimliu/baoyu-skills.

← Browse All Agent Skills
Sponsored AI assistant. Recommendations may be paid.