Article Illustrator logo

Article Illustrator

Community
bozhouDev
article-illustrator

为文章生成配图。分析文章结构,判断哪些位置需要什么类型的插图(infographic/flowchart/comparison/framework/timeline/scene),生成 prompt 并调用 image-gen 生成图片,最后插入文章。当用户说"配图"、"给文章加插图"、"生成文章插图"、"illustrate this article"时触发。即使用户只说"帮这篇文章配个图"也应该触发。

Overview

PublisherbozhouDev
Repositorybozhou-skills
Skill namearticle-illustrator
Stars
78
Forks
7
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by bozhouDev on GitHub. Read the source before you install it.

Installation

Install the Article Illustrator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/bozhouDev/bozhou-skills/tree/main/article-illustrator
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/bozhouDev/bozhou-skills.git /tmp/bozhou-skills
mkdir -p .claude/skills
cp -r /tmp/bozhou-skills/article-illustrator .claude/skills/article-illustrator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Article Illustrator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Article Illustrator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Article Illustrator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Article Illustrator

分析文章内容,智能匹配插图类型和位置,生成配图并插入文章。

视觉风格

风格不预设,由你(调用 skill 的 AI)根据文章内容自主选择最匹配的视觉风格,然后在 prompt 中具体、明确地描述给图片生成模型。图片生成模型只负责执行你的 prompt,不做风格判断。

你的职责:读完文章后,判断这篇文章适合什么视觉风格(配色、渲染方式、氛围),在 prompt 里写清楚。不同文章可以用完全不同的风格。

底线要求(用户偏好,从参考图中提取):

维度底线
背景干净,白色或浅色为主,不要花哨纹理
布局卡片/面板式容器组织信息,区域划分清晰
图形扁平矢量或简化图标,不要写实照片风格
连接箭头连接模块,流向一目了然
文字大粗标题醒目,数据指标突出,标签简短
色彩主色不超过 2-3 个,和谐不杂乱
整体信息优先,专业但亲切

在这些底线之上,你自由选择具体风格。比如:

  • AI/技术文章 → 蓝紫科技感、深色面板+亮色数据
  • 对比类内容 → 左右分色对比(如蓝vs橙)
  • 教程/流程 → 卡片步骤+编号圆圈+弧形箭头
  • 叙事/个人向 → 暖色调、插画感更强

选好后在 prompt 里写明配色方案、渲染风格、氛围,让图片生成模型精准执行。

用法

bash
# 基本用法
/article-illustrator path/to/article.md

# 指定类型
/article-illustrator path/to/article.md --type infographic

# 指定密度
/article-illustrator path/to/article.md --density rich
选项说明
--type <name>指定类型:infographic / flowchart / comparison / framework / timeline / scene / mixed
--density <level>密度:minimal(1-2) / balanced(3-5) / per-section / rich(6+)

工作流程

1. 分析文章 → 2. 确认设置 → 3. 生成大纲 → 4. 写 prompt → 5. 生成图片并上传 R2 → 6. 插入远程图片 URL

Step 1:分析文章

读完文章后做四项分析:

分析项说明
内容类型Technical / Tutorial / Methodology / Narrative
配图目的信息传达 / 概念可视化 / 氛围想象
核心论点提取 2-5 个需要可视化的要点
配图位置哪些段落加图能帮助理解

提取核心论点时关注:主论点、关键概念、对比/对照、框架/模型。

关键:比喻要可视化底层概念,不要画字面意思。比如文章说"书桌满了纸掉下去",配图应该画"上下文窗口"的概念,不是画一张真的书桌。


Step 2:确认设置

用 AskUserQuestion 确认,最多 3 个问题:

Q1:插图类型(必问)

根据分析推荐,选项包含推荐项 + 其他可选类型。

Q2:配图密度(必问)

密度数量场景
minimal1-2 张短文,核心概念
balanced3-5 张中等长度
per-section每章节 1 张长文(推荐)
rich6+ 张全面覆盖

Q3:输出目录(如果从参数或上下文无法推断)

常见选项:{article-dir}/imgs/{slug}/、{article-dir}/、独立 illustrations/ 目录。


Step 3:生成大纲

为每张图写一个条目,保存为 outline.md:

yaml
---
type: mixed
density: per-section
image_count: 5
---

## Illustration 1
**Position**: [章节/段落]
**Purpose**: [为什么需要这张图]
**Type**: [infographic/flowchart/comparison/framework/timeline/scene]
**Visual Content**: [画什么]
**Filename**: 01-{type}-{slug}.png

Step 4:写 Prompt

为每张图创建 prompt 文件 prompts/NN-{type}-{slug}.md,使用对应类型的结构模板。

6 种类型模板

Infographic(数据、指标、概念解释):

[标题]

Layout: [grid/radial/hierarchical]

ZONES:
- Zone 1: [具体数据点和数值]
- Zone 2: [对比和指标]

LABELS: [文章中的实际数字、术语]
ASPECT: 16:9

Flowchart(步骤、流程、操作):

[标题]

Layout: [left-right/top-down/circular]

STEPS:
1. [步骤名] - [简述]
2. [步骤名] - [简述]

CONNECTIONS: [箭头、决策节点]
ASPECT: 16:9

Comparison(vs、优劣、方案对比):

[标题]

LEFT SIDE - [选项A]:
- [要点]

RIGHT SIDE - [选项B]:
- [要点]

DIVIDER: [视觉分隔]
ASPECT: 16:9

Framework(架构、模型、原理):

[标题]

STRUCTURE: [hierarchical/network/matrix]

NODES:
- [概念1] - [角色]
- [概念2] - [角色]

RELATIONSHIPS: [连接关系]
ASPECT: 16:9

Timeline(历史、演变、进展):

[标题]

DIRECTION: [horizontal/vertical]

EVENTS:
- [时间点1]: [里程碑]
- [时间点2]: [里程碑]

MARKERS: [视觉标记]
ASPECT: 16:9

Scene(故事、情感、氛围):

[标题]

FOCAL POINT: [主体]
ATMOSPHERE: [光线、氛围]
MOOD: [情绪]
ASPECT: 16:9
Prompt 质量要求

每个 prompt 必须做到:

  1. 先写布局:构图、区域划分、方向
  2. 用文章原文数据:实际数字、术语、指标,不用占位符
  3. 描述元素关系:怎么连接、怎么对比
  4. 语义化颜色:颜色有含义(红=问题、绿=好的),但不锁定具体色号
  5. 注明宽高比

不要:模糊描述、画比喻字面意思、缺少标注、泛泛的装饰。

图中文字要大且醒目,只放关键词。默认使用中文标注,包括标题、标签、说明文字全部用中文。只有专有名词(品牌名、产品名如 Claude Code)可保留英文。

如果图中有人物,用简化的风格化剪影或卡通图标,不要写实人像。

每个 prompt 必须包含明确的风格描述:在 Step 1 分析完文章后,你应该已经决定了这组配图的视觉风格。在每个 prompt 中写清楚具体的配色方案(如 "deep indigo #3F3D9E as primary, soft lavender #B8B5E8 as secondary")、渲染方式(如 "clean flat vector with card-based panels")和氛围(如 "professional tech dashboard feel")。图片生成模型不会自己选风格,你的 prompt 写什么它就画什么。


Step 5:生成图片并上传 R2

用 image-gen skill 逐张生成,并且默认上传到 R2:

bash
npx -y bun <image-gen-skill-path>/scripts/main.ts \
  --prompt "<prompt内容>" \
  --image "<临时输出路径>/NN-{type}-{slug}.png" \
  --ar 16:9 \
  --r2 \
  --r2-key "images/articles/{article-slug}/NN-{type}-{slug}.png"

image-gen skill 路径:优先检查项目级 .claude/skills/image-gen/,其次 .agents/skills/image-gen/。R2 配置读取 vault 根目录 .env.r2。

封面图:除了文章内插图外,默认额外生成一张封面图(cover.png),使用 --ar 2.35:1 比例(公众号封面尺寸)。封面图也必须上传 R2,使用类似 images/articles/{article-slug}/cover.png 的 key;插入文章 frontmatter 之后、正文之前的是 R2 公开 URL。

每张生成并上传后记录 R2 URL,报告进度:"Generated + uploaded X/N"。生成失败或上传失败都重试一次,仍失败则跳过并记录。


Step 6:插入远程图片 URL

在对应段落后插入 R2 公开 URL:

markdown
![简要描述](https://your-r2-domain/images/articles/{article-slug}/NN-{type}-{slug}.png)

alt text 用简洁的中文描述,与文章语言一致。不要把长期图片链接写成本地 imgs/... 路径;本地文件只作为临时缓存。

完成后输出摘要:

配图完成!
文章:[path]
类型:[type] | 密度:[level]
图片:X/N 张生成并上传成功

位置:
- 01-xxx.png → R2 URL → "章节名" 之后
- 02-yyy.png → "章节名" 之后

内容信号 → 类型匹配速查

内容信号推荐类型
数据、指标、数字infographic
知识、概念、教程infographic
技术、AI、编程infographic
步骤、流程、操作flowchart
架构、模型、原理framework
vs、优劣、方案对比comparison
故事、情感、经历scene
历史、时间线、演变timeline

一篇文章可以 mixed 使用多种类型。

该配 vs 不该配

该配:核心论点(必配)、抽象概念、数据对比、流程。

不该配:比喻字面画面、纯装饰、泛泛通用插画。

输出结构

{output-dir}/
├── outline.md
├── prompts/
│   ├── 01-{type}-{slug}.md
│   └── 02-{type}-{slug}.md
├── 01-{type}-{slug}.png
└── 02-{type}-{slug}.png

Frequently asked questions

What does the Article Illustrator AI skill do?

为文章生成配图。分析文章结构,判断哪些位置需要什么类型的插图(infographic/flowchart/comparison/framework/timeline/scene),生成 prompt 并调用 image-gen 生成图片,最后插入文章。当用户说"配图"、"给文章加插图"、"生成文章插图"、"illustrate this article"时触发。即使用户只说"帮这篇文章配个图"也应该触发。

Why use Article Illustrator on TypingMind?

Because you install it once and use it with any model. Article Illustrator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Article Illustrator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/bozhouDev/bozhou-skills/tree/main/article-illustrator. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Article Illustrator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Article Illustrator?

As many as you like. As long as a model supports skills, you can use Article Illustrator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Article Illustrator AI skill free?

It is published on GitHub by bozhouDev. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇