infographic-creator

infographic-creator is a skill for Claude Code from antvis/Infographic. It costs 25 tokens per session (4,272 once invoked), scanned A, original, MIT.

An information-graphic creation guide that turns written information into a visual layout using AntV Infographic, a description language for rendering infographics.

In plain words
What is it for?
Use it to create infographic descriptions with titles, lists, sequences, themes, colors, and icons.
Why use it?
It helps organize complex information into a format that readers can understand quickly, while keeping the output language consistent with the input.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the Infographic plugin — 5 skills shipped together

Good fit Use it to create infographic descriptions with titles, lists, sequences, themes, colors, and icons.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/antvis/infographic/infographic-creator
About the project

AntV Infographic is a declarative framework that turns structured descriptions into editable, high-quality SVG infographics. Developers and AI agents use its syntax, templates, themes, editor, and rendering tools to create visual explanations, while the listed skills help agents generate infographic structures and files.

antvis/Infographic · 6,602 stars · on GitHub · infographic.antv.vision

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add antvis/Infographic --skill infographic-creator
Clone the repo
git clone --depth 1 https://github.com/antvis/Infographic

Made for: Claude Code.

Or install Infographic, the plugin that ships this one along with the rest of its 5 skills.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for infographic-creator

README.md
[![agentmods](https://agentmods.dev/badge/skills/antvis/infographic/infographic-creator.svg)](https://agentmods.dev/skills/antvis/infographic/infographic-creator)
Your own site
<a href="https://agentmods.dev/skills/antvis/infographic/infographic-creator"><img src="https://agentmods.dev/badge/skills/antvis/infographic/infographic-creator.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,272 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00025 $0.04272
Opus 5 $0.00013 $0.02136
Sonnet 5 $0.00005 $0.00854
Haiku 4.5 $0.00003 $0.00427

Measured 8d ago against content hash 00d0f5da0d7f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

infographic-creator scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/infographic-creator/SKILL.md · 485 lines

How it starts

The opening of the file, as written. The whole thing — 485 lines — stays where its author put it; the contents beside it link to each section on GitHub.

信息图(Infographic)将数据、信息与知识转化为可感知的视觉语言。它结合视觉设计与数据可视化,用直观符号压缩复杂信息,帮助受众快速理解并记住要点。

Infographic = Information Structure + Visual Expression

本任务使用 AntV Infographic 创建可视化信息图。

在开始任务前,需要理解 AntV Infographic 语法规范,包括模板列表、数据结构、主题等。

Language Lock

  • Prompt 的书写语言和示例语言不能决定最终输出语言。
  • 如果用户输入英文,则生成的 titledesclabel 等文案必须保持英文,不要自动翻译成中文。
  • 如果用户输入中文,则生成的 titledesclabel 等文案必须保持中文,不要自动翻译成英文。

规范

AntV Infographic 语法

AntV Infographic 语法是一种自定义 DSL,用于描述信息图渲染配置。它使用缩进表达结构,适合 AI 直接生成并流式输出。核心信息包括:

  1. template:用模板表达信息结构。
  2. data:信息图数据,包含 titledesc 和主数据字段。
  3. theme:主题配置,包含 palette、字体、风格化等。

例如:

infographic list-row-horizontal-icon-arrow
data
  title Title
  desc Description
  lists
    - label Label
      value 12.5
      desc Explanation
      icon document text
theme
  palette #3b82f6 #8b5cf6 #f97316

硬性语法规则

  • 第一行必须是 infographic <template-name>
  • 模板列表里只写模板名本身;真正输出时首行必须显式写出 infographic 前缀。
  • 使用 data / theme 块,块内统一使用两个空格缩进。
  • 键值对写法是 键 空格 值;对象数组使用 - 作为条目前缀。
  • icon 可以使用精确图标 ID,例如 mingcute/server-line,也可以使用语义关键词短语,例如 star fill
  • 如果使用语义关键词短语,多个关键词之间使用空格分隔,不要使用短横线;例如写 rocket launch,不要写 rocket-launch
  • listssequencesnodesitems 以及 compares/children 下的语义型数据项,默认应补充 icon;不要因为字段是可选就省略。
  • 如果模板名或视觉样式明显依赖图标,则每个主要数据项都应包含 icon
  • 如果不确定精确图标 ID,也要优先写一个简洁的语义关键词,例如 rocketshielddatabaseuserschart line,而不是省略 icon 字段。
  • 仅在纯图表类数据点、纯数值序列,或用户明确要求极简文本版时,才可以省略 icon
  • value 尽量使用纯数值;数值单位优先放在 labeldesc 中表达。
  • palette 推荐使用行内简单数组写法,例如 palette #4f46e5 #06b6d4 #10b981
  • palette 中的颜色值是裸值,不加引号,不加逗号。
  • data 只放一个与模板匹配的主数据字段,避免同时混用 listssequencescomparesvaluesrootnodes

主数据字段选择规则:

  • list-*lists
  • sequence-*sequences,可选 order asc|desc
  • sequence-interaction-*sequences + relations
    • sequences 表示泳道列表
    • 每个泳道必须包含 label
    • 每个泳道的 children 表示节点列表
    • children 下的每一项都必须写成对象条目,并包含 label
    • 节点可选 idiconstepdescvalue
    • step 用于表示时间层级;相同 step 处于同一高度
  • compare-*compares
    • compare-binary-* / compare-hierarchy-left-right-*
      • compares 第一层必须且只能有两个根节点,分别表示对比双方
      • 两个根节点都应包含 children
      • 真正的对比项写在各自的 children
      • children 下的每一项都必须写成对象条目,并包含 label
      • 即使每一侧只有 1 个指标,也要写成 children 内含 1 个对象条目
    • compare-swot
      • compares 可直接放多个根节点
      • 每个根节点下可选 children
    • compare-quadrant-*
      • compares 直接放 4 个象限根节点
  • hierarchy-structureitems
  • hierarchy-* → 单一 root,通过 children 递归嵌套
  • relation-*nodes + relations
    • 简单关系也可直接用箭头语法表达关系
  • chart-*values
    • chart-line-plain-text / chart-bar-plain-text / chart-column-simple 都使用单条有序 values
    • 每个数据点使用 label 表示类目,使用 value 表示数值
    • 折线图的顺序由 values 中条目的排列顺序表达
  • 结构无法明确判断时,再用 items 兜底

Read the full file on GitHub · 485 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 485 lines · 25 tokens per session scan A 00d0f5da0d7f

Subscribe to this mod's changes

infographic-creator is a skill published in the GitHub repository antvis/Infographic (6,602 stars, last pushed 17d ago), licensed MIT. It adds 25 tokens to every session and 4,272 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.