baoyu-xhs-images

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Xiaohongshu Infographic Series Generator

小红书信息图系列生成器

Break down complex content into eye-catching infographic series for Xiaohongshu with multiple style options.

将复杂内容拆解为适合小红书的吸睛信息图系列，提供多种样式选项。

Usage

使用方法

bash

undefined

bash

undefined

Auto-select style and layout based on content

根据内容自动选择样式和布局

/baoyu-xhs-images posts/ai-future/article.md

Specify style

指定样式

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

Specify layout

指定布局

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

Combine style and layout

组合样式和布局

/baoyu-xhs-images posts/ai-future/article.md --style tech --layout list

Direct content input

直接输入内容

/baoyu-xhs-images [paste content]

Direct input with options

带选项的直接输入

/baoyu-xhs-images --style bold --layout comparison [paste content]

undefined

/baoyu-xhs-images --style bold --layout comparison [paste content]

undefined

Options

选项

Option	Description
`--style <name>`	Visual style (see Style Gallery)
`--layout <name>`	Information layout (see Layout Gallery)

选项	描述
`--style <name>`	视觉样式（查看样式库）
`--layout <name>`	信息布局（查看布局库）

Two Dimensions

两个维度

Dimension	Controls	Options
Style	Visual aesthetics: colors, lines, decorations	cute, fresh, tech, warm, bold, minimal, retro, pop, notion
Layout	Information structure: density, arrangement	sparse, balanced, dense, list, comparison, flow

Style × Layout can be freely combined. Example:

--style notion --layout dense

creates an intellectual-looking knowledge card with high information density.

维度	控制项	选项
样式	视觉美学：色彩、线条、装饰	cute, fresh, tech, warm, bold, minimal, retro, pop, notion
布局	信息结构：密度、排列方式	sparse, balanced, dense, list, comparison, flow

样式与布局可自由组合。示例：

--style notion --layout dense

会生成一张具有高信息密度的知性风知识卡片。

Style Gallery

样式库

Style	Description
`cute` (Default)	Sweet, adorable, girly - classic Xiaohongshu aesthetic
`fresh`	Clean, refreshing, natural
`tech`	Modern, smart, digital
`warm`	Cozy, friendly, approachable
`bold`	High impact, attention-grabbing
`minimal`	Ultra-clean, sophisticated
`retro`	Vintage, nostalgic, trendy
`pop`	Vibrant, energetic, eye-catching
`notion`	Minimalist hand-drawn line art, intellectual

Detailed style definitions:

references/styles/<style>.md

样式	描述
`cute` （默认）	甜美可爱、少女风 - 经典小红书审美
`fresh`	干净清爽、自然风
`tech`	现代智能、数字化风格
`warm`	温馨友好、平易近人
`bold`	冲击力强、吸睛度高
`minimal`	极简干净、精致高级
`retro`	复古怀旧、潮流感
`pop`	活力四射、醒目吸睛
`notion`	极简手绘线条风、知性气质

详细样式定义：

references/styles/<style>.md

Layout Gallery

布局库

Layout	Description
`sparse` (Default)	Minimal information, maximum impact (1-2 points)
`balanced`	Standard content layout (3-4 points)
`dense`	High information density, knowledge card style (5-8 points)
`list`	Enumeration and ranking format (4-7 items)
`comparison`	Side-by-side contrast layout
`flow`	Process and timeline layout (3-6 steps)

Detailed layout definitions:

references/layouts/<layout>.md

布局	描述
`sparse` （默认）	信息极简、视觉冲击力强（1-2个要点）
`balanced`	标准内容布局（3-4个要点）
`dense`	高信息密度、知识卡片风格（5-8个要点）
`list`	枚举与排名格式（4-7项内容）
`comparison`	并列对比布局
`flow`	流程与时间线布局（3-6个步骤）

详细布局定义：

references/layouts/<layout>.md

Auto Selection

自动选择规则

Content Signals	Style	Layout
Beauty, fashion, cute, girl, pink	`cute`	sparse/balanced
Health, nature, clean, fresh, organic	`fresh`	balanced/flow
Tech, AI, code, digital, app, tool	`tech`	dense/list
Life, story, emotion, feeling, warm	`warm`	balanced
Warning, important, must, critical	`bold`	list/comparison
Professional, business, elegant, simple	`minimal`	sparse/balanced
Classic, vintage, old, traditional	`retro`	balanced
Fun, exciting, wow, amazing	`pop`	sparse/list
Knowledge, concept, productivity, SaaS	`notion`	dense/list

内容信号	样式	布局
美妆、时尚、可爱、少女、粉色	`cute`	sparse/balanced
健康、自然、干净、清新、有机	`fresh`	balanced/flow
科技、AI、代码、数字化、应用、工具	`tech`	dense/list
生活、故事、情感、感受、温暖	`warm`	balanced
警告、重要、必须、关键	`bold`	list/comparison
专业、商务、优雅、简洁	`minimal`	sparse/balanced
经典、复古、老旧、传统	`retro`	balanced
有趣、兴奋、惊叹、惊艳	`pop`	sparse/list
知识、概念、生产力、SaaS	`notion`	dense/list

File Structure

文件结构

Each session creates an independent directory named by content slug:

xhs-images/{topic-slug}/
├── source-{slug}.{ext}             # Source files (text, images, etc.)
├── analysis.md                     # Deep analysis results
├── outline-style-[slug].md         # Variant A (e.g., outline-style-tech.md)
├── outline-style-[slug].md         # Variant B (e.g., outline-style-notion.md)
├── outline-style-[slug].md         # Variant C (e.g., outline-style-minimal.md)
├── outline.md                      # Final selected
├── prompts/
│   ├── 01-cover-[slug].md
│   ├── 02-content-[slug].md
│   └── ...
├── 01-cover-[slug].png
├── 02-content-[slug].png
└── NN-ending-[slug].png

Slug Generation:

Extract main topic from content (2-4 words, kebab-case)
Example: "AI工具推荐" →
```
ai-tools-recommend
```

Conflict Resolution: If

xhs-images/{topic-slug}/

already exists:

Append timestamp:
```
{topic-slug}-YYYYMMDD-HHMMSS
```
Example:
```
ai-tools
```
exists →
```
ai-tools-20260118-143052
```

Source Files: Copy all sources with naming

source-{slug}.{ext}

```
source-article.md
```
,
```
source-photo.jpg
```
, etc.
Multiple sources supported: text, images, files from conversation

每个会话会创建一个独立目录，以内容别名命名：

xhs-images/{topic-slug}/
├── source-{slug}.{ext}             # 源文件（文本、图片等）
├── analysis.md                     # 深度分析结果
├── outline-style-[slug].md         # 变体A（例如：outline-style-tech.md）
├── outline-style-[slug].md         # 变体B（例如：outline-style-notion.md）
├── outline-style-[slug].md         # 变体C（例如：outline-style-minimal.md）
├── outline.md                      # 最终选定版本
├── prompts/
│   ├── 01-cover-[slug].md
│   ├── 02-content-[slug].md
│   └── ...
├── 01-cover-[slug].png
├── 02-content-[slug].png
└── NN-ending-[slug].png

别名生成规则:

从内容中提取主题（2-4个单词，短横线分隔格式）
示例："AI工具推荐" →
```
ai-tools-recommend
```

冲突解决: 如果

xhs-images/{topic-slug}/

已存在：

追加时间戳：
```
{topic-slug}-YYYYMMDD-HHMMSS
```
示例：
```
ai-tools
```
已存在 →
```
ai-tools-20260118-143052
```

源文件处理: 将所有源文件复制为

source-{slug}.{ext}

格式：

```
source-article.md
```
、
```
source-photo.jpg
```
等
支持多源文件：文本、图片、会话中的文件

Workflow

工作流

Step 1: Analyze Content →

analysis.md

步骤1：分析内容 →

analysis.md

Read source content, save it if needed, and perform deep analysis.

Actions:

Save source content (if not already a file):
- If user provides a file path: use as-is
- If user pastes content: save to
```
source.md
```
  in target directory
Read source content
Deep analysis following
```
references/analysis-framework.md
```
:
- Content type classification (种草/干货/测评/教程/避坑...)
- Hook analysis (爆款标题潜力)
- Target audience identification
- Engagement potential (收藏/分享/评论)
- Visual opportunity mapping
- Swipe flow design
Detect source language
Determine recommended image count (2-10)
Select 3 style+layout combinations
Save to
analysis.md

读取源内容（如需则保存），并执行深度分析。

操作:

保存源内容（若尚未是文件）:
- 如果用户提供文件路径：直接使用
- 如果用户粘贴内容：保存到目标目录的
```
source.md
```
读取源内容
深度分析，遵循
```
references/analysis-framework.md
```
:
- 内容类型分类（种草/干货/测评/教程/避坑...）
- 钩子分析（爆款标题潜力）
- 目标受众识别
- 互动潜力（收藏/分享/评论）
- 视觉机会映射
- 滑动流设计
检测源语言
确定推荐图片数量（2-10张）
选择3种样式+布局组合
保存到
analysis.md

Step 2: Generate 3 Outline Variants

步骤2：生成3种大纲变体

Based on analysis, create three distinct style variants.

For each variant:

Generate outline (
```
outline-style-[slug].md
```
):
- YAML front matter with style, layout, image_count
- Cover design with hook
- Each image: layout, core message, text content, visual concept
- Written in user's preferred language
- Reference:
```
references/outline-template.md
```

Variant	Selection Logic	Example Filename
A	Primary recommendation	`outline-style-tech.md`
B	Alternative style	`outline-style-notion.md`
C	Different audience/mood	`outline-style-minimal.md`

All variants are preserved after selection for reference.

基于分析结果，创建3种不同的样式变体。

针对每个变体:

生成大纲（
```
outline-style-[slug].md
```
）:
- 包含样式、布局、图片数量的YAML前置元数据
- 带钩子的封面设计
- 每张图片：布局、核心信息、文本内容、视觉概念
- 以用户偏好的语言编写
- 参考：
```
references/outline-template.md
```

变体	选择逻辑	示例文件名
A	首要推荐	`outline-style-tech.md`
B	替代样式	`outline-style-notion.md`
C	面向不同受众/氛围	`outline-style-minimal.md`

选定后所有变体都会保留，以供参考。

Step 3: User Confirms All Options

步骤3：用户确认所有选项

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

Determine which questions to ask:

Question	When to Ask
Style variant	Always (required)
Default layout	Only if user might want to override
Language	Only if `source_language ≠ user_language`

Language handling:

If source language = user language: Just inform user (e.g., "Images will be in Chinese")
If different: Ask which language to use

AskUserQuestion format:

Question 1 (Style): Which style variant?
- A: tech + dense (Recommended) - 专业科技感，适合干货
- B: notion + list - 清爽知识卡片
- C: minimal + balanced - 简约高端风格
- Custom: 自定义风格描述

Question 2 (Layout) - only if relevant:
- Keep variant default (Recommended)
- sparse / balanced / dense / list / comparison / flow

Question 3 (Language) - only if mismatch:
- 中文 (匹配原文)
- English (your preference)

After confirmation:

Copy selected
```
outline-style-[slug].md
```
→
```
outline.md
```
Update YAML front matter with confirmed options
If custom style: regenerate outline with that style
User may edit
```
outline.md
```
directly for fine-tuning

重要提示：使用AskUserQuestion在单个确认步骤中展示所有选项，不要通过多次单独确认打断工作流。

确定需要询问的问题:

问题	询问时机
样式变体	始终询问（必填）
默认布局	仅当用户可能需要覆盖默认值时
语言	仅当 `source_language ≠ user_language` 时

语言处理:

如果源语言=用户语言：仅告知用户（例如："图片将以中文生成"）
如果不同：询问使用哪种语言

AskUserQuestion格式:

问题1（样式）：选择哪种样式变体？
- A: tech + dense（推荐）- 专业科技感，适合干货
- B: notion + list - 清爽知识卡片
- C: minimal + balanced - 简约高端风格
- 自定义：自定义样式描述

问题2（布局）- 仅相关时询问：
- 保留变体默认值（推荐）
- sparse / balanced / dense / list / comparison / flow

问题3（语言）- 仅当语言不匹配时询问：
- 中文（匹配原文）
- English（你的偏好）

确认后:

将选定的
```
outline-style-[slug].md
```
复制为
```
outline.md
```
更新YAML前置元数据为确认后的选项
如果是自定义样式：使用该样式重新生成大纲
用户可直接编辑
```
outline.md
```
进行微调

Step 4: Generate Images

步骤4：生成图片

With confirmed outline + style + layout:

For each image (cover + content + ending):

Save prompt to
```
prompts/NN-{type}-[slug].md
```
(in user's preferred language)
Generate image using confirmed style and layout
Report progress after each generation

Image Generation Skill Selection:

Check available image generation skills
If multiple skills available, ask user preference

Session Management: If image generation skill supports

--sessionId

Generate unique session ID:
```
xhs-{topic-slug}-{timestamp}
```
Use same session ID for all images
Ensures visual consistency across generated images

基于确认后的大纲+样式+布局：

针对每张图片（封面+内容+结尾）:

将提示词保存到
```
prompts/NN-{type}-[slug].md
```
（以用户偏好的语言）
使用确认后的样式和布局生成图片
每张图片生成后汇报进度

图片生成技能选择:

检查可用的图片生成技能
如果有多个技能可用，询问用户偏好

会话管理: 如果图片生成技能支持

--sessionId

生成唯一会话ID：
```
xhs-{topic-slug}-{timestamp}
```
所有图片使用同一个会话ID
确保生成的所有图片视觉风格一致

Step 5: Completion Report

步骤5：完成报告

Xiaohongshu Infographic Series Complete!

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

✓ analysis.md
✓ outline-style-tech.md
✓ outline-style-notion.md
✓ outline-style-minimal.md
✓ outline.md (selected: tech + dense)

Files:
- 01-cover-[slug].png ✓ Cover (sparse)
- 02-content-[slug].png ✓ Content (balanced)
- 03-content-[slug].png ✓ Content (dense)
- 04-ending-[slug].png ✓ Ending (sparse)

小红书信息图系列生成完成！

主题：[topic]
样式：[style name]
布局：[layout name 或 "多样式"]
位置：[目录路径]
图片总数：N张

✓ analysis.md
✓ outline-style-tech.md
✓ outline-style-notion.md
✓ outline-style-minimal.md
✓ outline.md（选定：tech + dense）

文件列表：
- 01-cover-[slug].png ✓ 封面（sparse布局）
- 02-content-[slug].png ✓ 内容（balanced布局）
- 03-content-[slug].png ✓ 内容（dense布局）
- 04-ending-[slug].png ✓ 结尾（sparse布局）

Image Modification

图片修改

Edit Single Image

编辑单张图片

Identify image to edit (e.g.,
```
03-content-chatgpt.png
```
)
Update prompt in
```
prompts/03-content-chatgpt.md
```
if needed
Regenerate image using same session ID

确定要编辑的图片（例如：
```
03-content-chatgpt.png
```
）
如需则更新
```
prompts/03-content-chatgpt.md
```
中的提示词
使用同一个会话ID重新生成图片

Add New Image

添加新图片

Specify insertion position (e.g., after image 3)
Create new prompt with appropriate slug
Generate new image
Renumber files: All subsequent images increment NN by 1
Update
```
outline.md
```
with new image entry

指定插入位置（例如：在第3张图片之后）
创建带合适别名的新提示词
生成新图片
重新编号文件：后续所有图片的NN编号加1
更新
```
outline.md
```
中的新图片条目

Delete Image

删除图片

Remove image file and prompt file
Renumber files: All subsequent images decrement NN by 1
Update
```
outline.md
```
to remove image entry

删除图片文件和提示词文件
重新编号文件：后续所有图片的NN编号减1
更新
```
outline.md
```
以移除该图片条目

Content Breakdown Principles

内容拆解原则

Cover (Image 1): Hook + visual impact →
```
sparse
```
layout
Content (Middle): Core value per image →
```
balanced
```
/
```
dense
```
/
```
list
```
/
```
comparison
```
/
```
flow
```
Ending (Last): CTA / summary →
```
sparse
```
or
```
balanced
```

Style × Layout Matrix (✓✓ = highly recommended, ✓ = works well):

	sparse	balanced	dense	list	comparison	flow
cute	✓✓	✓✓	✓	✓✓	✓	✓
fresh	✓✓	✓✓	✓	✓	✓	✓✓
tech	✓	✓✓	✓✓	✓✓	✓✓	✓✓
warm	✓✓	✓✓	✓	✓	✓✓	✓
bold	✓✓	✓	✓	✓✓	✓✓	✓
minimal	✓✓	✓✓	✓✓	✓	✓	✓
retro	✓✓	✓✓	✓	✓✓	✓	✓
pop	✓✓	✓✓	✓	✓✓	✓✓	✓
notion	✓✓	✓✓	✓✓	✓✓	✓✓	✓✓

封面（第1张图）：钩子+视觉冲击力 → 使用
```
sparse
```
布局
内容（中间图）：每张图承载核心价值 → 使用
```
balanced
```
/
```
dense
```
/
```
list
```
/
```
comparison
```
/
```
flow
```
布局
结尾（最后1张图）：行动号召/总结 → 使用
```
sparse
```
或
```
balanced
```
布局

样式×布局矩阵（✓✓ = 高度推荐，✓ = 效果良好）:

	sparse	balanced	dense	list	comparison	flow
cute	✓✓	✓✓	✓	✓✓	✓	✓
fresh	✓✓	✓✓	✓	✓	✓	✓✓
tech	✓	✓✓	✓✓	✓✓	✓✓	✓✓
warm	✓✓	✓✓	✓	✓	✓✓	✓
bold	✓✓	✓	✓	✓✓	✓✓	✓
minimal	✓✓	✓✓	✓✓	✓	✓	✓
retro	✓✓	✓✓	✓	✓✓	✓	✓
pop	✓✓	✓✓	✓	✓✓	✓✓	✓
notion	✓✓	✓✓	✓✓	✓✓	✓✓	✓✓

References

参考资料

Detailed templates and guidelines in

references/

directory:

```
analysis-framework.md
```
- XHS-specific content analysis
```
outline-template.md
```
- Outline format and examples
```
styles/<style>.md
```
- Detailed style definitions
```
layouts/<layout>.md
```
- Detailed layout definitions
```
base-prompt.md
```
- Base prompt template

详细模板和指南位于

references/

```
analysis-framework.md
```
- 小红书专属内容分析框架
```
outline-template.md
```
- 大纲格式与示例
```
styles/<style>.md
```
- 详细样式定义
```
layouts/<layout>.md
```
- 详细布局定义
```
base-prompt.md
```
- 基础提示词模板

Notes

注意事项

Image generation typically takes 10-30 seconds per image
Auto-retry once on generation failure
Use cartoon alternatives for sensitive public figures
All prompts and text use confirmed language preference
Maintain style consistency across all images in series

单张图片生成通常需要10-30秒
生成失败时自动重试一次
敏感公众人物使用卡通替代
所有提示词和文本使用确认后的偏好语言
保持系列中所有图片的样式一致性

Extension Support

扩展支持

Custom styles and configurations via EXTEND.md.

Check paths (priority order):

.baoyu-skills/baoyu-xhs-images/EXTEND.md

(project)

~/.baoyu-skills/baoyu-xhs-images/EXTEND.md

(user)

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

通过EXTEND.md实现自定义样式和配置。

路径检查优先级:

.baoyu-skills/baoyu-xhs-images/EXTEND.md

（项目级）

~/.baoyu-skills/baoyu-xhs-images/EXTEND.md

（用户级）

如果找到，在步骤1之前加载。扩展内容会覆盖默认设置。