Infographic logo

Infographic

Community
PM-Shawn
infographic

生成精美的纯 HTML+CSS 信息图 — 时间线、流程、对比分析、SWOT、金字塔、漏斗、数据卡片、组织架构等。无需外部依赖,在沙箱 iframe 中渲染。适合将结构化信息以海报级视觉效果呈现。

Overview

PublisherPM-Shawn
RepositoryAbu-Cowork
Skill nameinfographic
Stars
380
Forks
86
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 PM-Shawn on GitHub. Read the source before you install it.

Installation

Install the Infographic 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.
  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/PM-Shawn/Abu-Cowork.git /tmp/Abu-Cowork
mkdir -p .claude/skills
cp -r /tmp/Abu-Cowork/builtin-skills/infographic .claude/skills/infographic
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Infographic 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 Infographic 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 Infographic 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.

你现在帮用户生成 精美的 HTML+CSS 信息图。直接在回复中输出 ```html 代码块,前端会在安全沙箱 iframe 中自动渲染。

重要规则

  • 不要调用 generate_image 工具,HTML 代码块就是最终输出
  • 不要调用文件写入工具——这是对话内的可视化展示
  • 只输出一个 ```html 代码块——一张完整的信息图,不要拆成多个
  • 纯 CSS 实现——不要用 <script>、不要引入外部 CDN、不要用 <canvas>
  • 输出 HTML 片段(不含 <!DOCTYPE><html><head><body>),顺序:<style> → HTML 内容

设计体系

核心美学:克制、留白、呼吸感。 信息图是一张海报,不是一个网页。每个元素都要有存在的理由,宁少勿多。

审美原则

  1. 做减法:不加装饰性 emoji/icon,不加渐变背景,不加阴影。需要强调时用色彩和字重,不用堆砌视觉元素
  2. 留白即设计:区块之间 32-48px 间距,内容不要挤在一起。留白是最重要的设计元素
  3. 信息层级清晰:通过字号递减 + 色彩深浅建立 3 层视觉层级——标题 / 正文 / 辅助
  4. 色彩克制:整张图只用 1 种强调色 + 灰度色阶。多数据系列时才启用色板
  5. 对齐与网格:所有元素对齐到 4px 网格,间距只用 4 的倍数

配色

CSS 变量(已预注入 iframe)

变量用途
--abu-primary#d97757唯一强调色——用于编号、标签、线条、高亮
--abu-text#29261b标题 & 正文
--abu-text-muted#888579副标题、描述、脚注
--abu-bg#ffffff页面底色
--abu-bg-secondary#f5f3ee卡片 / 区块底色
--abu-border#e5e2db分割线、边框、轨道

数据色板(仅在多数据系列对比时使用): #4F46E5 · #0891B2 · #10B981 · #F59E0B · #EF4444 · #7C3AED

语义色(仅在明确表达趋势/状态时使用):

  • 正向:#059669 文字 + #ecfdf5
  • 负向:#DC2626 文字 + #fef2f2

禁止

  • ❌ 深色/黑色背景
  • ❌ 大面积饱和色块(只允许小面积点缀:编号圆、标签、进度条)
  • ❌ 多于 2 种强调色同时出现
  • ❌ 渐变做装饰(唯一例外:头部区域极轻微的 #f8f6f3 → #fff

字体

font-family: system-ui, -apple-system, "PingFang SC", "Microsoft YaHei", sans-serif;

只用两种字重400(正文)和 600(标题/数字)。禁用 300/500/700/800。

角色字号字重颜色
主标题24px600--abu-text
副标题14px400--abu-text-muted
区块标题16-18px600--abu-text
正文13-14px400--abu-text
标签/脚注11-12px400/600--abu-text-muted
大数字(KPI)28-36px600--abu-text
步骤编号11px600--abu-primary

排版规则

  • 行高:标题 1.3,正文 1.5-1.6
  • 中英文 / 中文与数字之间加半角空格:GDP 总量 101.4 万亿
  • 数字等宽对齐:font-variant-numeric: tabular-nums

间距(4px 网格)

所有间距必须是 4 的倍数。禁止 5px、7px、15px 等非标值。

用途
元素内微间距4px
紧密行间8px
组内元素12px
卡片内边距 / 段落间16px
卡片间距12-16px
区块间距32-48px
头部上下 padding32px

圆角

元素
小元素(标签、编号)4-6px
卡片8-10px
大容器12px

一张信息图内最多 2 种圆角值。

装饰手法(仅用这些,不要发明新的)

  • 分割线1px solid var(--abu-border),用于步骤之间、头部与正文之间
  • 编号圆width: 28px; height: 28px; border-radius: 50%; background: var(--abu-primary); color: #fff; font-size: 13px;
  • 空心圆点border: 2px solid var(--abu-primary); background: #fff;(时间线节点)
  • 实心小圆点width: 5px; height: 5px; border-radius: 50%;(列表标记)
  • 竖线width: 1.5px; background: var(--abu-border);(时间线轴)
  • 左色条border-left: 3px solid var(--abu-primary); padding-left: 12px;(引用 / 重点段落)
  • 浅色标签padding: 2px 8px; border-radius: 4px; font-size: 11px; background: #f0f0ff; color: #4338CA;
  • 进度条height: 6px; border-radius: 3px; background: var(--abu-border); + 内填充

禁止

  • ❌ box-shadow(任何阴影)
  • ❌ emoji 作为 icon(不要用 🔍 🎨 💻 🚀 等)
  • ❌ border 做卡片轮廓(用背景色区分即可)
  • ❌ 多彩渐变
  • ❌ text-transform: uppercase(中文信息图不需要)

页面结构

每张信息图遵循固定骨架:

html
<style>
  .ig { max-width: 600px; margin: 0 auto; }
  .hd { padding: 32px 0 24px; text-align: center; }
  .hd h1 { font-size: 24px; font-weight: 600; color: var(--abu-text); margin: 0 0 6px; }
  .hd p { font-size: 14px; color: var(--abu-text-muted); margin: 0; }
  /* 正文区块样式 */
  .ft { padding: 20px 0 4px; text-align: center; font-size: 11px; color: var(--abu-text-muted); border-top: 1px solid var(--abu-border); margin-top: 32px; }
</style>

<div class="ig">
  <div class="hd">
    <h1>标题</h1>
    <p>副标题 / 说明</p>
  </div>

  <!-- 正文内容 -->

  <div class="ft">Abu Infographic</div>
</div>
  • .ig 容器:max-width: 600px; margin: 0 auto; — 控制最大宽度,居中
  • .hd 头部:居中标题 + 副标题,简洁干净,不要加背景色或装饰
  • .ft 页脚:固定文案 Abu Infographic,细字灰色,上方一条分割线

布局类型参考

根据内容结构选择最合适的布局。可以在一张信息图中组合多种布局(如头部 KPI 卡片 + 中部时间线)。

时间线

左侧竖线 + 圆点 + 右侧内容。适合:发展历程、版本演进、里程碑。

  • 竖线用 ::before 伪元素,1.5px 宽,var(--abu-border)
  • 节点用空心圆(2px border),首个节点实心
  • 每个节点:上方小字标签(日期/阶段,11px,--abu-primary)+ 标题 + 描述

流程步骤

纵向列表,编号圆 + 标题 + 描述,步骤间用分割线分隔。适合:操作流程、开发流程。

  • 编号圆:28px,--abu-primary 底白字
  • 步骤之间 border-bottom: 1px solid var(--abu-border) 分隔

卡片网格

2-3 列网格,每格一张浅底卡片。适合:SWOT、特性对比、分类展示。

  • 卡片底色用极浅的语义色(#f0f0ff#edfcf4#fffceb#fef5f5
  • 卡片标题用对应深色的小标签

KPI 数据

大数字 + 标签 + 趋势。适合:经营数据、统计概览。

  • 3-4 列网格,var(--abu-bg-secondary)
  • 数字 28-36px,tabular-nums
  • 趋势用 / + 语义色标签

排名列表

横向行卡片,左侧序号 + 中间内容 + 右侧数值。适合:Top N、榜单。

  • 前 1-3 名序号用强调色,其余用 var(--abu-border)
  • 行间距 8px,行内 padding 14px

对比(双栏)

左右两列,各有色彩标题头 + 内容列表。适合:方案对比、Before/After。

金字塔 / 漏斗

自上而下宽度递增(或递减),每层一个色条。适合:层级模型、转化漏斗。

进度条

横向进度条 + 标签 + 百分比。适合:完成度、占比分布。

  • 轨道 6px 高,var(--abu-border) 底,填充用 --abu-primary

注意事项

  • 只输出一个 html 代码块,所有内容合在一张信息图中
  • class 命名用简短有意义的缩写(.ig .hd .ft .st),不要用 .infographic-header-title-wrapper
  • 信息图 vs 技术图表:信息图侧重「精美展示」,技术图表用 mermaid
  • 信息图 vs 交互组件:信息图是静态海报,需要交互的用 html-widget
  • 内容多时组合使用多种布局,不要一列到底变成纯文本长列表
  • 中文排版,变量名 / class 名用英文

Frequently asked questions

What does the Infographic AI skill do?

生成精美的纯 HTML+CSS 信息图 — 时间线、流程、对比分析、SWOT、金字塔、漏斗、数据卡片、组织架构等。无需外部依赖,在沙箱 iframe 中渲染。适合将结构化信息以海报级视觉效果呈现。

Why use Infographic on TypingMind?

Because you install it once and use it with any model. Infographic 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 Infographic in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/PM-Shawn/Abu-Cowork/tree/main/builtin-skills/infographic. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Infographic?

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 Infographic?

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

Is the Infographic AI skill free?

It is published on GitHub by PM-Shawn. 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 👇