baoyu-xhs-images
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseXiaohongshu Infographic Series Generator
小红书信息图系列生成工具
Break down complex content into eye-catching infographic series for Xiaohongshu with multiple style options.
将复杂内容拆分为吸睛的小红书信息图系列,支持多种风格选项。
Usage
使用方法
bash
undefinedbash
undefinedAuto-select style and layout based on content
根据内容自动选择风格和布局
/baoyu-xhs-images posts/ai-future/article.md
/baoyu-xhs-images posts/ai-future/article.md
Specify style
指定风格
/baoyu-xhs-images posts/ai-future/article.md --style notion
/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
/baoyu-xhs-images posts/ai-future/article.md --layout dense
Combine style and layout
同时指定风格和布局
/baoyu-xhs-images posts/ai-future/article.md --style notion --layout list
/baoyu-xhs-images posts/ai-future/article.md --style notion --layout list
Direct content input
直接输入内容
/baoyu-xhs-images
[paste content]
/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]
undefinedOptions
选项
| Option | Description |
|---|---|
| Visual style (see Style Gallery) |
| Information layout (see Layout Gallery) |
| 选项 | 描述 |
|---|---|
| 视觉风格(查看风格库) |
| 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, warm, bold, minimal, retro, pop, notion, chalkboard, study-notes |
| Layout | Information structure: density, arrangement | sparse, balanced, dense, list, comparison, flow, mindmap, quadrant |
Style × Layout can be freely combined. Example: creates an intellectual-looking knowledge card with high information density.
--style notion --layout dense| 维度 | 控制项 | 可选值 |
|---|---|---|
| 风格(Style) | 视觉美学:色彩、线条、装饰 | cute, fresh, warm, bold, minimal, retro, pop, notion, chalkboard, study-notes |
| 布局(Layout) | 信息结构:密度、排列方式 | sparse, balanced, dense, list, comparison, flow, mindmap, quadrant |
风格与布局可自由组合。示例: 可生成具有高信息密度的知性风知识卡片。
--style notion --layout denseStyle Gallery
风格库
| Style | Description |
|---|---|
| Sweet, adorable, girly - classic Xiaohongshu aesthetic |
| Clean, refreshing, natural |
| Cozy, friendly, approachable |
| High impact, attention-grabbing |
| Ultra-clean, sophisticated |
| Vintage, nostalgic, trendy |
| Vibrant, energetic, eye-catching |
| Minimalist hand-drawn line art, intellectual |
| Colorful chalk on black board, educational |
| Realistic handwritten photo style, blue pen + red annotations + yellow highlighter |
Detailed style definitions:
references/presets/<style>.md| 风格 | 描述 |
|---|---|
| 甜美可爱、少女风——小红书经典美学风格 |
| 清新干净、自然风 |
| 温馨友好、亲和力强 |
| 冲击力强、吸睛度高 |
| 极简精致、高级感 |
| 复古怀旧、潮流感 |
| 活力四射、视觉冲击力强 |
| 极简手绘线条、知性风 |
| 黑板彩色粉笔效果、教育感 |
| 真实手写笔记风格:蓝笔+红批注+黄荧光笔 |
详细风格定义:
references/presets/<style>.mdLayout Gallery
布局库
| Layout | Description |
|---|---|
| Minimal information, maximum impact (1-2 points) |
| Standard content layout (3-4 points) |
| High information density, knowledge card style (5-8 points) |
| Enumeration and ranking format (4-7 items) |
| Side-by-side contrast layout |
| Process and timeline layout (3-6 steps) |
| Center radial mind map layout (4-8 branches) |
| Four-quadrant / circular section layout |
Detailed layout definitions:
references/elements/canvas.md| 布局 | 描述 |
|---|---|
| 信息极简、视觉冲击力拉满(1-2个要点) |
| 标准内容布局(3-4个要点) |
| 高信息密度、知识卡片风格(5-8个要点) |
| 枚举与排名格式(4-7项内容) |
| 并列对比布局 |
| 流程与时间线布局(3-6个步骤) |
| 中心放射状思维导图布局(4-8个分支) |
| 四象限/环形分区布局 |
详细布局定义:
references/elements/canvas.mdAuto Selection
自动选择规则
| Content Signals | Style | Layout |
|---|---|---|
| Beauty, fashion, cute, girl, pink | | sparse/balanced |
| Health, nature, clean, fresh, organic | | balanced/flow |
| Life, story, emotion, feeling, warm | | balanced |
| Warning, important, must, critical | | list/comparison |
| Professional, business, elegant, simple | | sparse/balanced |
| Classic, vintage, old, traditional | | balanced |
| Fun, exciting, wow, amazing | | sparse/list |
| Knowledge, concept, productivity, SaaS | | dense/list |
| Education, tutorial, learning, teaching, classroom | | balanced/dense |
| Notes, handwritten, study guide, knowledge, realistic, photo | | dense/list/mindmap |
| 内容信号 | 推荐风格 | 推荐布局 |
|---|---|---|
| 美妆、时尚、可爱、少女、粉色 | | sparse/balanced |
| 健康、自然、干净、清新、有机 | | balanced/flow |
| 生活、故事、情感、感受、温暖 | | balanced |
| 警告、重要、必须、关键 | | list/comparison |
| 专业、商务、优雅、简洁 | | sparse/balanced |
| 经典、复古、老旧、传统 | | balanced |
| 有趣、激动、惊叹、惊艳 | | sparse/list |
| 知识、概念、生产力、SaaS | | dense/list |
| 教育、教程、学习、教学、课堂 | | balanced/dense |
| 笔记、手写、学习指南、知识、真实、照片 | | dense/list/mindmap |
Outline Strategies
大纲策略
Three differentiated outline strategies for different content goals:
针对不同内容目标,提供三种差异化的大纲策略:
Strategy A: Story-Driven (故事驱动型)
策略A:故事驱动型
| Aspect | Description |
|---|---|
| Concept | Personal experience as main thread, emotional resonance first |
| Features | Start from pain point, show before/after change, strong authenticity |
| Best for | Reviews, personal shares, transformation stories |
| Structure | Hook → Problem → Discovery → Experience → Conclusion |
| 维度 | 描述 |
|---|---|
| 核心思路 | 以个人经历为主线,优先打造情感共鸣 |
| 特点 | 从痛点切入,展示前后变化,真实感强 |
| 适用场景 | 测评、个人分享、蜕变故事 |
| 结构 | 钩子 → 问题 → 发现 → 体验 → 结论 |
Strategy B: Information-Dense (信息密集型)
策略B:信息密集型
| Aspect | Description |
|---|---|
| Concept | Value-first, efficient information delivery |
| Features | Clear structure, explicit points, professional credibility |
| Best for | Tutorials, comparisons, product reviews, checklists |
| Structure | Core conclusion → Info card → Pros/Cons → Recommendation |
| 维度 | 描述 |
|---|---|
| 核心思路 | 价值优先,高效传递信息 |
| 特点 | 结构清晰、要点明确、专业可信度高 |
| 适用场景 | 教程、对比、产品测评、清单 |
| 结构 | 核心结论 → 信息卡片 → 优缺点 → 推荐 |
Strategy C: Visual-First (视觉优先型)
策略C:视觉优先型
| Aspect | Description |
|---|---|
| Concept | Visual impact as core, minimal text |
| Features | Large images, atmospheric, instant appeal |
| Best for | High-aesthetic products, lifestyle, mood-based content |
| Structure | Hero image → Detail shots → Lifestyle scene → CTA |
| 维度 | 描述 |
|---|---|
| 核心思路 | 以视觉冲击力为核心,文字极简 |
| 特点 | 大尺寸图片、氛围感强、瞬间吸引注意力 |
| 适用场景 | 高审美产品、生活方式、情绪向内容 |
| 结构 | 主视觉图 → 细节展示 → 生活场景 → 行动号召(CTA) |
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 + questions asked
├── outline-strategy-a.md # Strategy A: Story-driven
├── outline-strategy-b.md # Strategy B: Information-dense
├── outline-strategy-c.md # Strategy C: Visual-first
├── outline.md # Final selected/merged outline
├── prompts/
│ ├── 01-cover-[slug].md
│ ├── 02-content-[slug].md
│ └── ...
├── 01-cover-[slug].png
├── 02-content-[slug].png
└── NN-ending-[slug].pngSlug Generation:
- Extract main topic from content (2-4 words, kebab-case)
- Example: "AI工具推荐" →
ai-tools-recommend
Conflict Resolution:
If already exists:
xhs-images/{topic-slug}/- Append timestamp:
{topic-slug}-YYYYMMDD-HHMMSS - Example: exists →
ai-toolsai-tools-20260118-143052
Source Files:
Copy all sources with naming :
source-{slug}.{ext}- ,
source-article.md, etc.source-photo.jpg - Multiple sources supported: text, images, files from conversation
每个会话会创建一个独立目录,目录名由内容slug生成:
xhs-images/{topic-slug}/
├── source-{slug}.{ext} # 源文件(文本、图片等)
├── analysis.md # 深度分析+待确认问题
├── outline-strategy-a.md # 策略A:故事驱动型
├── outline-strategy-b.md # 策略B:信息密集型
├── outline-strategy-c.md # 策略C:视觉优先型
├── outline.md # 最终选定/合并的大纲
├── prompts/
│ ├── 01-cover-[slug].md
│ ├── 02-content-[slug].md
│ └── ...
├── 01-cover-[slug].png
├── 02-content-[slug].png
└── NN-ending-[slug].pngSlug生成规则:
- 从内容中提取主题关键词(2-4个词,短横线分隔格式)
- 示例:"AI工具推荐" →
ai-tools-recommend
冲突解决:
如果已存在:
xhs-images/{topic-slug}/- 追加时间戳:
{topic-slug}-YYYYMMDD-HHMMSS - 示例:已存在 →
ai-toolsai-tools-20260118-143052
源文件处理:
将所有源文件复制并重命名为:
source-{slug}.{ext}- 支持、
source-article.md等格式source-photo.jpg - 支持多源文件:文本、图片、会话中的文件
Workflow
工作流
Progress Checklist
进度检查清单
Copy and track progress:
XHS Infographic Progress:
- [ ] Step 0: Check preferences (EXTEND.md) ⛔ BLOCKING
- [ ] Found → load preferences → continue
- [ ] Not found → run first-time setup → MUST complete before Step 1
- [ ] Step 1: Analyze content → analysis.md
- [ ] Step 2: Confirmation 1 - Content understanding ⚠️ REQUIRED
- [ ] Step 3: Generate 3 outline + style variants
- [ ] Step 4: Confirmation 2 - Outline & style & elements selection ⚠️ REQUIRED
- [ ] Step 5: Generate images (sequential)
- [ ] Step 6: Completion report复制以下内容跟踪进度:
小红书信息图制作进度:
- [ ] 步骤0:检查偏好设置(EXTEND.md) ⛔ 阻塞项
- [ ] 已找到 → 加载偏好设置 → 继续
- [ ] 未找到 → 运行首次设置 → 必须在步骤1前完成
- [ ] 步骤1:内容分析 → analysis.md
- [ ] 步骤2:确认1 - 内容理解 ⚠️ 必填
- [ ] 步骤3:生成3种大纲+风格变体
- [ ] 步骤4:确认2 - 大纲&风格&元素选择 ⚠️ 必填
- [ ] 步骤5:生成图片(按顺序)
- [ ] 步骤6:完成报告Flow
流程示意图
Input → [Step 0: Preferences] ─┬─ Found → Continue
│
└─ Not found → First-Time Setup ⛔ BLOCKING
│
└─ Complete setup → Save EXTEND.md → Continue
│
┌───────────────────────────────────────────────────────────────────────────┘
↓
Analyze → [Confirm 1] → 3 Outlines → [Confirm 2: Outline + Style + Elements] → Generate → Complete输入 → [步骤0:偏好设置] ─┬─ 已找到 → 继续
│
└─ 未找到 → 首次设置 ⛔ 阻塞项
│
└─ 完成设置 → 保存EXTEND.md → 继续
│
┌───────────────────────────────────────────────────────────────────────────┘
↓
分析 → [确认1] → 3种大纲 → [确认2:大纲+风格+元素] → 生成图片 → 完成Step 0: Load Preferences (EXTEND.md) ⛔ BLOCKING
步骤0:加载偏好设置(EXTEND.md) ⛔ 阻塞项
Purpose: Load user preferences or run first-time setup.
CRITICAL: If EXTEND.md not found, MUST complete first-time setup before ANY other questions or steps. Do NOT proceed to content analysis, do NOT ask about style, do NOT ask about layout — ONLY complete the preferences setup first.
Use Bash to check EXTEND.md existence (priority order):
bash
undefined目的:加载用户偏好或运行首次设置。
关键注意事项:如果未找到EXTEND.md,必须先完成首次设置,才能进行任何其他操作或提问。不得直接进入内容分析、询问风格或布局,只能先完成偏好设置。
使用Bash检查EXTEND.md的存在(优先级顺序):
bash
undefinedCheck project-level first
先检查项目级目录
test -f .baoyu-skills/baoyu-xhs-images/EXTEND.md && echo "project"
test -f .baoyu-skills/baoyu-xhs-images/EXTEND.md && echo "project"
Then user-level (cross-platform: $HOME works on macOS/Linux/WSL)
再检查用户级目录(跨平台:$HOME适用于macOS/Linux/WSL)
test -f "$HOME/.baoyu-skills/baoyu-xhs-images/EXTEND.md" && echo "user"
┌────────────────────────────────────────────────────┬───────────────────┐
│ Path │ Location │
├────────────────────────────────────────────────────┼───────────────────┤
│ .baoyu-skills/baoyu-xhs-images/EXTEND.md │ Project directory │
├────────────────────────────────────────────────────┼───────────────────┤
│ $HOME/.baoyu-skills/baoyu-xhs-images/EXTEND.md │ User home │
└────────────────────────────────────────────────────┴───────────────────┘
┌───────────┬─────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ Result │ Action │
├───────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Found │ Read, parse, display summary → Continue to Step 1 │
├───────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ Not found │ ⛔ BLOCKING: Run first-time setup ONLY (see below) → Complete and save EXTEND.md → Then Step 1 │
└───────────┴─────────────────────────────────────────────────────────────────────────────────────────────────────┘
**First-Time Setup** (when EXTEND.md not found):
**Language**: Use user's input language or saved language preference.
Use AskUserQuestion with ALL questions in ONE call. See `references/config/first-time-setup.md` for question details.
**EXTEND.md Supports**: Watermark | Preferred style/layout | Custom style definitions | Language preference
Schema: `references/config/preferences-schema.md`test -f "$HOME/.baoyu-skills/baoyu-xhs-images/EXTEND.md" && echo "user"
┌────────────────────────────────────────────────────┬───────────────────┐
│ 路径 │ 位置 │
├────────────────────────────────────────────────────┼───────────────────┤
│ .baoyu-skills/baoyu-xhs-images/EXTEND.md │ 项目目录 │
├────────────────────────────────────────────────────┼───────────────────┤
│ $HOME/.baoyu-skills/baoyu-xhs-images/EXTEND.md │ 用户主目录 │
└────────────────────────────────────────────────────┴───────────────────┘
┌───────────┬─────────────────────────────────────────────────────────────────────────────────────────────────────┐
│ 检查结果 │ 操作 │
├───────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ 已找到 │ 读取、解析、显示摘要 → 进入步骤1 │
├───────────┼─────────────────────────────────────────────────────────────────────────────────────────────────────┤
│ 未找到 │ ⛔ 阻塞项:仅运行首次设置(见下文) → 完成并保存EXTEND.md → 进入步骤1 │
└───────────┴─────────────────────────────────────────────────────────────────────────────────────────────────────┘
**首次设置**(未找到EXTEND.md时):
**语言**:使用用户输入语言或已保存的语言偏好。
通过一次调用AskUserQuestion完成所有问题。详细问题请参考`references/config/first-time-setup.md`。
**EXTEND.md支持**:水印 | 偏好风格/布局 | 自定义风格定义 | 语言偏好
Schema参考:`references/config/preferences-schema.md`Step 1: Analyze Content → analysis.md
analysis.md步骤1:内容分析 → analysis.md
analysis.mdRead 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 in target directory
source.md - Backup rule: If exists, rename to
source.mdsource-backup-YYYYMMDD-HHMMSS.md
- Read source content
- Deep analysis following :
references/workflows/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)
- Generate clarifying questions (see Step 2)
- Save to
analysis.md
读取源内容(如需保存则保存),并执行深度分析。
操作步骤:
- 保存源内容(如果不是文件形式):
- 用户提供文件路径:直接使用
- 用户粘贴内容:保存到目标目录的
source.md - 备份规则:如果已存在,重命名为
source.mdsource-backup-YYYYMMDD-HHMMSS.md
- 读取源内容
- 深度分析(遵循):
references/workflows/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)
- 视觉机会挖掘
- 滑动流设计
- 检测源语言
- 确定推荐图片数量(2-10张)
- 生成待确认问题(见步骤2)
- 保存到
analysis.md
Step 2: Confirmation 1 - Content Understanding ⚠️
步骤2:确认1 - 内容理解 ⚠️
Purpose: Validate understanding + collect missing info. Do NOT skip.
Display summary:
- Content type + topic identified
- Key points extracted
- Tone detected
- Source images count
Use AskUserQuestion for:
- Core selling point (multiSelect: true)
- Target audience
- Style preference: Authentic sharing / Professional review / Aesthetic mood / Auto
- Additional context (optional)
After response: Update → Step 3
analysis.md目的:验证理解程度+收集缺失信息。不得跳过。
显示摘要:
- 已识别的内容类型+主题
- 提取的核心要点
- 检测到的语气
- 源图片数量
通过AskUserQuestion收集以下信息:
- 核心卖点(支持多选)
- 目标受众
- 风格偏好:真实分享 / 专业测评 / 美学氛围 / 自动选择
- 额外上下文(可选)
用户回复后:更新 → 进入步骤3
analysis.mdStep 3: Generate 3 Outline + Style Variants
步骤3:生成3种大纲+风格变体
Based on analysis + user context, create three distinct strategy variants. Each variant includes both outline structure and visual style recommendation.
For each strategy:
| Strategy | Filename | Outline | Recommended Style |
|---|---|---|---|
| A | | Story-driven: emotional, before/after | warm, cute, fresh |
| B | | Information-dense: structured, factual | notion, minimal, chalkboard |
| C | | Visual-first: atmospheric, minimal text | bold, pop, retro |
Outline format (YAML front matter + content):
yaml
---
strategy: a # a, b, or c
name: Story-Driven
style: warm # recommended style for this strategy
style_reason: "Warm tones enhance emotional storytelling and personal connection"
elements: # from style preset, can be customized in Step 4
background: solid-pastel
decorations: [clouds, stars-sparkles]
emphasis: star-burst
typography: highlight
layout: balanced # primary layout
image_count: 5
---基于分析结果+用户上下文,创建三种差异化的策略变体。每个变体包含大纲结构和视觉风格推荐。
每种策略详情:
| 策略 | 文件名 | 大纲 | 推荐风格 |
|---|---|---|---|
| A | | 故事驱动型:情感化、前后对比 | warm, cute, fresh |
| B | | 信息密集型:结构化、事实导向 | notion, minimal, chalkboard |
| C | | 视觉优先型:氛围感、文字极简 | bold, pop, retro |
大纲格式(YAML前置元数据+内容):
yaml
---
strategy: a # a, b, 或 c
name: 故事驱动型
style: warm # 本策略推荐风格
style_reason: "暖色调能增强情感叙事与个人连接"
elements: # 来自风格预设,可在步骤4中自定义
background: solid-pastel
decorations: [clouds, stars-sparkles]
emphasis: star-burst
typography: highlight
layout: balanced # 主布局
image_count: 5
---P1 Cover
P1 封面
Type: cover
Hook: "入冬后脸不干了🥹终于找到对的面霜"
Visual: Product hero shot with cozy winter atmosphere
Layout: sparse
类型: 封面
钩子: "入冬后脸不干了🥹终于找到对的面霜"
视觉: 产品主图+温馨冬季氛围
布局: sparse
P2 Problem
P2 痛点
Type: pain-point
Message: Previous struggles with dry skin
Visual: Before state, relatable scenario
Layout: balanced
...
**Differentiation requirements**:
- Each strategy MUST have different outline structure AND different recommended style
- Adapt page count: A typically 4-6, B typically 3-5, C typically 3-4
- Include `style_reason` explaining why this style fits the strategy
- Consider user's style preference from Step 2
Reference: `references/workflows/outline-template.md`类型: 痛点
信息: 之前皮肤干燥的困扰
视觉: 前后对比场景
布局: balanced
...
**差异化要求**:
- 每种策略必须有不同的大纲结构和推荐风格
- 适配页面数量:A策略通常4-6页,B策略3-5页,C策略3-4页
- 包含`style_reason`字段,说明该风格适配策略的原因
- 参考步骤2中用户的风格偏好
参考模板:`references/workflows/outline-template.md`Step 4: Confirmation 2 - Outline & Style & Elements Selection ⚠️
步骤4:确认2 - 大纲&风格&元素选择 ⚠️
Purpose: User chooses outline strategy, confirms visual style, and customizes elements. Do NOT skip.
Display each strategy:
- Strategy name + page count + recommended style
- Page-by-page summary (P1 → P2 → P3...)
Use AskUserQuestion with three questions:
Question 1: Outline Strategy
- Strategy A (Recommended if "authentic sharing")
- Strategy B (Recommended if "professional review")
- Strategy C (Recommended if "aesthetic mood")
- Combine: specify pages from each
Question 2: Visual Style
- Use strategy's recommended style (show which style)
- Or select from: cute / fresh / warm / bold / minimal / retro / pop / notion / chalkboard
- Or type custom style description
Question 3: Visual Elements (show after style selection)
Display the selected style's default elements from preset, then ask:
- Use style defaults (Recommended) - show preview: background, decorations, emphasis
- Adjust background - options: solid-pastel / solid-saturated / gradient-linear / gradient-radial / paper-texture / grid
- Adjust decorations - options: hearts / stars-sparkles / flowers / clouds / leaves / confetti
- Type custom element preferences
After response:
- Single strategy → copy to with confirmed style
outline.md - Combination → merge specified pages with confirmed style
- Custom request → regenerate based on feedback
- Style defaults → use preset's Element Combination as-is
- Background adjustment → update elements.background with user choice
- Decorations adjustment → update elements.decorations with user choice
- Custom elements → parse user's preferences into elements fields
- Update frontmatter with final style and elements
outline.md
目的:用户选择大纲策略、确认视觉风格、自定义元素。不得跳过。
展示每种策略:
- 策略名称+页面数量+推荐风格
- 逐页摘要(P1 → P2 → P3...)
通过AskUserQuestion提出三个问题:
问题1:大纲策略选择
- 策略A(如果用户选择“真实分享”则推荐)
- 策略B(如果用户选择“专业测评”则推荐)
- 策略C(如果用户选择“美学氛围”则推荐)
- 组合:指定来自不同策略的页面
问题2:视觉风格选择
- 使用策略推荐风格(显示具体风格)
- 或从以下选项选择:cute / fresh / warm / bold / minimal / retro / pop / notion / chalkboard
- 或输入自定义风格描述
问题3:视觉元素调整(选择风格后展示)
展示所选风格的默认预设元素,然后询问:
- 使用风格默认设置(推荐)- 预览:背景、装饰、强调元素
- 调整背景 - 选项:solid-pastel / solid-saturated / gradient-linear / gradient-radial / paper-texture / grid
- 调整装饰 - 选项:hearts / stars-sparkles / flowers / clouds / leaves / confetti
- 输入自定义元素偏好
用户回复后:
- 单一策略 → 复制到并确认风格
outline.md - 组合策略 → 合并指定页面并确认风格
- 自定义需求 → 根据反馈重新生成
- 使用默认风格 → 直接采用预设的元素组合
- 调整背景 → 更新elements.background为用户选择
- 调整装饰 → 更新elements.decorations为用户选择
- 自定义元素 → 将用户偏好解析为elements字段
- 在的前置元数据中更新最终风格和元素
outline.md
Step 5: Generate Images
步骤5:生成图片
With confirmed outline + style + layout:
For each image (cover + content + ending):
- Save prompt to (in user's preferred language)
prompts/NN-{type}-[slug].md- Backup rule: If prompt file exists, rename to
prompts/NN-{type}-[slug]-backup-YYYYMMDD-HHMMSS.md
- Backup rule: If prompt file exists, rename to
- Generate image using confirmed style and layout
- Backup rule: If image file exists, rename to
NN-{type}-[slug]-backup-YYYYMMDD-HHMMSS.png
- Backup rule: If image file exists, rename to
- Report progress after each generation
Watermark Application (if enabled in preferences):
Add to each image generation prompt:
Include a subtle watermark "[content]" positioned at [position].
The watermark should be legible but not distracting from the main content.Reference:
references/config/watermark-guide.mdImage 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+风格+布局:
每张图片(封面+内容+结尾)的操作:
- 将提示词保存到(使用用户偏好语言)
prompts/NN-{type}-[slug].md- 备份规则:如果提示词文件已存在,重命名为
prompts/NN-{type}-[slug]-backup-YYYYMMDD-HHMMSS.md
- 备份规则:如果提示词文件已存在,重命名为
- 使用确认后的风格和布局生成图片
- 备份规则:如果图片文件已存在,重命名为
NN-{type}-[slug]-backup-YYYYMMDD-HHMMSS.png
- 备份规则:如果图片文件已存在,重命名为
- 每生成一张图片后报告进度
水印添加(如果偏好设置中启用):
在每张图片的生成提示词中添加:
添加一个微妙的水印“[内容]”,位置在[指定位置]。
水印需清晰可辨,但不得干扰主要内容。参考文档:
references/config/watermark-guide.md图片生成工具选择:
- 检查可用的图片生成工具
- 如果有多个工具可用,询问用户偏好
会话管理:
如果图片生成工具支持:
--sessionId- 生成唯一会话ID:
xhs-{topic-slug}-{timestamp} - 所有图片使用同一个会话ID
- 确保生成的图片视觉风格一致
Step 6: Completion Report
步骤6:完成报告
Xiaohongshu Infographic Series Complete!
Topic: [topic]
Strategy: [A/B/C/Combined]
Style: [style name]
Layout: [layout name or "varies"]
Location: [directory path]
Images: N total
✓ analysis.md
✓ outline-strategy-a.md
✓ outline-strategy-b.md
✓ outline-strategy-c.md
✓ outline.md (selected: [strategy])
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)小红书信息图系列制作完成!
主题: [主题]
策略: [A/B/C/组合]
风格: [风格名称]
布局: [布局名称或“多种布局”]
存储位置: [目录路径]
图片数量: 共N张
✓ analysis.md
✓ outline-strategy-a.md
✓ outline-strategy-b.md
✓ outline-strategy-c.md
✓ outline.md(已选:[策略])
生成文件:
- 01-cover-[slug].png ✓ 封面(sparse布局)
- 02-content-[slug].png ✓ 内容页(balanced布局)
- 03-content-[slug].png ✓ 内容页(dense布局)
- 04-ending-[slug].png ✓ 结尾页(sparse布局)Image Modification
图片修改规则
| Action | Steps |
|---|---|
| Edit | Update prompt file FIRST → Regenerate with same session ID |
| Add | Specify position → Create prompt → Generate → Renumber subsequent files (NN+1) → Update outline |
| Delete | Remove files → Renumber subsequent (NN-1) → Update outline |
IMPORTANT: When updating images, ALWAYS update the prompt file () FIRST before regenerating. This ensures changes are documented and reproducible.
prompts/NN-{type}-[slug].md| 操作 | 步骤 |
|---|---|
| 编辑 | 先更新提示词文件 → 使用同一个会话ID重新生成 |
| 添加 | 指定位置 → 创建提示词 → 生成 → 后续文件重新编号(NN+1) → 更新大纲 |
| 删除 | 删除文件 → 后续文件重新编号(NN-1) → 更新大纲 |
重要提示:更新图片时,必须先更新提示词文件(),再重新生成图片。确保修改可记录、可复现。
prompts/NN-{type}-[slug].mdContent Breakdown Principles
内容拆分原则
- Cover (Image 1): Hook + visual impact → layout
sparse - Content (Middle): Core value per image → /
balanced/dense/list/comparisonflow - Ending (Last): CTA / summary → or
sparsebalanced
Style × Layout Matrix (✓✓ = highly recommended, ✓ = works well):
| sparse | balanced | dense | list | comparison | flow | mindmap | quadrant | |
|---|---|---|---|---|---|---|---|---|
| cute | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓ | ✓ | ✓ | ✓ |
| fresh | ✓✓ | ✓✓ | ✓ | ✓ | ✓ | ✓✓ | ✓ | ✓ |
| warm | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ | ✓ | ✓ | ✓ |
| bold | ✓✓ | ✓ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ |
| minimal | ✓✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| retro | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓ | ✓ | ✓ | ✓ |
| pop | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓ |
| notion | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ |
| chalkboard | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓✓ | ✓ |
| study-notes | ✗ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ | ✓ |
- 封面(第1张图):钩子+视觉冲击力 → 使用布局
sparse - 内容页(中间部分):每张图承载一个核心价值 → 使用/
balanced/dense/list/comparison布局flow - 结尾页(最后1张图):行动号召/总结 → 使用或
sparse布局balanced
风格×布局适配矩阵(✓✓ = 高度推荐,✓ = 适配性好):
| sparse | balanced | dense | list | comparison | flow | mindmap | quadrant | |
|---|---|---|---|---|---|---|---|---|
| cute | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓ | ✓ | ✓ | ✓ |
| fresh | ✓✓ | ✓✓ | ✓ | ✓ | ✓ | ✓✓ | ✓ | ✓ |
| warm | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ | ✓ | ✓ | ✓ |
| bold | ✓✓ | ✓ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ |
| minimal | ✓✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓ | ✓ | ✓ |
| retro | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓ | ✓ | ✓ | ✓ |
| pop | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓ |
| notion | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓✓ |
| chalkboard | ✓✓ | ✓✓ | ✓✓ | ✓✓ | ✓ | ✓✓ | ✓✓ | ✓ |
| study-notes | ✗ | ✓ | ✓✓ | ✓✓ | ✓ | ✓ | ✓✓ | ✓ |
References
参考文档
Detailed templates in directory:
references/Elements (Visual building blocks):
- - Aspect ratios, safe zones, grid layouts
elements/canvas.md - - Cutout, stroke, filters
elements/image-effects.md - - Decorated text (花字), tags, text direction
elements/typography.md - - Emphasis marks, backgrounds, doodles, frames
elements/decorations.md
Presets (Style presets):
- - Element combination definitions (cute, notion, warm...)
presets/<name>.md
Workflows (Process guides):
- - Content analysis framework
workflows/analysis-framework.md - - Outline template with layout guide
workflows/outline-template.md - - Prompt assembly guide
workflows/prompt-assembly.md
Config (Settings):
- - EXTEND.md schema
config/preferences-schema.md - - First-time setup flow
config/first-time-setup.md - - Watermark configuration
config/watermark-guide.md
详细模板位于目录:
references/元素(视觉构建模块):
- - 宽高比、安全区、网格布局
elements/canvas.md - - 抠图、描边、滤镜
elements/image-effects.md - - 花字、标签、文字方向
elements/typography.md - - 强调标记、背景、涂鸦、边框
elements/decorations.md
预设(风格预设):
- - 元素组合定义(cute、notion、warm等)
presets/<name>.md
工作流(流程指南):
- - 内容分析框架
workflows/analysis-framework.md - - 带布局指南的大纲模板
workflows/outline-template.md - - 提示词组装指南
workflows/prompt-assembly.md
配置(设置项):
- - EXTEND.md schema
config/preferences-schema.md - - 首次设置流程
config/first-time-setup.md - - 水印配置指南
config/watermark-guide.md
Notes
注意事项
- Auto-retry once on failure | Cartoon alternatives for sensitive figures
- Use confirmed language preference | Maintain style consistency
- Two confirmation points required (Steps 2 & 4) - do not skip
- 生成失败时自动重试1次 | 敏感人物使用卡通替代
- 使用用户确认的语言偏好 | 保持风格一致性
- 必须完成两次确认(步骤2和4) - 不得跳过
Extension Support
扩展支持
Custom configurations via EXTEND.md. See Step 0 for paths and supported options.
通过EXTEND.md进行自定义配置。路径和支持选项请参考步骤0。