Xiaohongshu Infographic Series Generator

Break down complex content into eye-catching infographic series for Xiaohongshu.

Usage

# Auto-select style and layout based on content
/xhs-images posts/ai-future/article.md

# Specify style
/xhs-images posts/ai-future/article.md --style notion

# Specify layout
/xhs-images posts/ai-future/article.md --layout dense

# Combine style and layout
/xhs-images posts/ai-future/article.md --style tech --layout list

# Direct content input
/xhs-images
[paste content]

Options

Two Dimensions

Style × Layout can be freely combined. Example: --style notion --layout dense creates an intellectual-looking knowledge card with high information density.

Style Gallery (Quick Reference)

For detailed style specs (colors, elements, typography): See references/styles.md

Layout Gallery (Quick Reference)

For detailed layout specs and Style×Layout matrix: See references/layouts.md

Auto Selection Logic

Auto Style Selection

Auto Layout Selection

Layout by Position

File Management

With Article Path

Save to xhs-images/ subdirectory in the same folder as the article:

posts/ai-future/
├── article.md
└── xhs-images/
    ├── outline.md
    ├── prompts/
    │   ├── 01-cover.md
    │   └── ...
    ├── 01-cover.png
    └── 02-ending.png

Without Article Path

Save to xhs-outputs/YYYY-MM-DD/[topic-slug]/

Workflow

Step 1: Analyze Content & Select Style/Layout

1. Read content
2. If --style specified, use that style; otherwise auto-select
3. If --layout specified, use that layout; otherwise auto-select per image
4. Determine image count:
   • Simple topic: 2-3 images
   • Medium complexity: 4-6 images
   • Deep dive: 7-10 images

Step 2: Generate Outline

Plan for each image with style and layout specifications. Save as outline.md:

# Xiaohongshu Infographic Series Outline

**Topic**: [topic]
**Style**: [selected style]
**Default Layout**: [selected layout or "varies"]
**Image Count**: N
**Generated**: YYYY-MM-DD HH:mm

---

## Image 1 of N

**Position**: Cover
**Layout**: sparse
**Core Message**: [one-liner]
**Filename**: 01-cover.png

**Text Content**:
- Title: xxx
- Subtitle: xxx

**Visual Concept**: [style + layout appropriate description]

---
...

Step 3: Generate Images One by One

For each image:

1. Read style details from references/styles.md (load target style section only)
2. Read layout details from references/layouts.md (load target layout section only)
3. Create prompt file in prompts/ directory
4. Generate using:

/gemini-web --promptfiles [SKILL_ROOT]/prompts/system.md [TARGET_DIR]/prompts/01-cover.md --image [TARGET_DIR]/01-cover.png

Prompt Format:

Infographic theme: [topic]
Style: [style name]
Layout: [layout name]
Position: [cover/content/ending]

Visual composition:
- Main visual: [style-appropriate description]
- Arrangement: [layout-specific structure]
- Decorative elements: [style-specific decorations]

Color scheme:
- Primary: [from style spec]
- Background: [from style spec]
- Accent: [from style spec]

Text content:
- Title: 「xxx」(large, prominent)
- Key points: [based on layout density]

Layout instructions: [from layout spec]
Style notes: [from style spec]

Step 4: Completion Report

Xiaohongshu Infographic Series Complete!

Topic: [topic]
Style: [style name]
Layout: [layout name or "varies"]
Location: [directory path]
Images: N total

- 01-cover.png ✓ Cover (sparse)
- 02-content-1.png ✓ Content (balanced)
- 03-ending.png ✓ Ending (sparse)

Outline: outline.md

Content Breakdown Principles

1. Cover (Image 1): Strong visual impact, core title, attention hook → sparse layout
2. Content (Middle): Core points per image, density varies by content
3. Ending (Last): Summary / call-to-action / memorable quote → sparse or balanced

Notes

• Image generation typically takes 10-30 seconds per image
• Auto-retry once on generation failure
• Use cartoon alternatives for sensitive public figures
• Output language matches input content language
• Maintain selected style consistency across all images in series