Tufte logo

Tufte

Community
aref-vc
tufte

Apply Edward Tufte's principles to any data visualization, chart, dashboard, or infographic. Use when the user asks to produce, design, critique, or improve a chart, graph, dashboard, KPI tile, table-with-data, sparkline, small multiple, time series, distribution plot, choropleth, or any other visual that communicates quantitative or categorical information. Also triggers on words like "visualize", "viz", "data viz", "chart", "graph", "dashboard", "infographic", "Tufte". Outputs Tufte-compliant designs in either self-contained HTML/SVG or React (Recharts/D3). Defaults to Tufte rules; user can opt out per chart.

Overview

Publisheraref-vc
Repositorytufte-claude-skill
Skill nametufte
Stars
312
Forks
28
Bundled files
21
LicenseMIT
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.

  • 21 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by aref-vc on GitHub. Read the source before you install it.

Installation

Install the Tufte 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/aref-vc/tufte-claude-skill/tree/main
  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/aref-vc/tufte-claude-skill.git \
  .claude/skills/tufte
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Tufte 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 Tufte 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 Tufte 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.

Tufte — visual display, by the book

This skill turns "make me a chart" into a Tufte-compliant chart. Distilled from The Visual Display of Quantitative Information (1983/2001), Envisioning Information (1990), and Visual Explanations (1997).

What this skill produces

Two output stacks, selected by the user's project context:

  1. Self-contained HTML/SVG — single file, inline SVG, no external deps. For one-offs, embeds, screenshots, slide decks.
  2. React (Recharts + D3 fallback) — for projects that already use React. Recharts where the chart type fits; raw D3-in-React where it doesn't (slopegraph, sparkline-in-table, small multiples).

How to use this skill

When invoked, work through these in order:

  1. Read principles.md — 10 rules, one paragraph each. The whole frame.
  2. Use chart-selection.md to pick the chart type from the user's data and goal. Don't reach for a chart you know; reach for the one this table prescribes.
  3. Apply kill-list.md before rendering — strip the things that don't belong in any Tufte-compliant chart.
  4. Check before-after.html when the user wants to see the difference. Six side-by-side examples covering the cases AI tools default to badly.
  5. Read report-voice.md when the output is a report, recap, or slide with prose around the chart. The writing can ruin a clean chart. Plain business English, no em-dashes, no AI slop.
  6. Run checklist.md before declaring the chart done. Twenty items, takes 30 seconds.

For a quick lookup, cheatsheet.html (and cheatsheet.pdf) is the one-page reference.

Default behavior

Tufte rules apply by default. If the user explicitly requests something on the kill list ("I need a pie chart for this board deck because the CFO wants one"), comply, but note the Tufte alternative in a one-line comment in the code or the response.

Prose around the chart

When the output is a report, recap, or slide, the text matters as much as the chart. Write plain business English: no em-dashes, no drama or theatrics, no hype verbs, no AI-slop jargon. Name every label and caption for the specific case, not a placeholder. First the number, then what it means. See report-voice.md for the full kill/keep list. A clean chart wrapped in slop reads as slop.

The kill list, summarized

These are not in any Tufte-compliant chart unless the user explicitly overrides:

  • 3D effects on any 2D quantity
  • Pie charts (use a sorted bar or a small table)
  • Dual-axis charts (use two small multiples instead)
  • Rainbow color scales for ordered data (use sequential single-hue)
  • Heavy gridlines, frame boxes, tick marks at every minor unit
  • Drop shadows, gradient fills, bevels, glow, "ducks"
  • Legends placed away from data (label data directly)
  • Moiré patterns, cross-hatching, dense stippling
  • Redundant data-ink (bar plus number plus axis plus gridline all showing the same quantity)
  • KPI cards with giant numbers and no context

The keep list

These belong in most Tufte charts:

  • Direct labels on data (no legends)
  • Sparklines next to numbers
  • Small multiples for any cross-cut
  • Range frames (axes only span where data exists)
  • Subtle gridlines (white-on-light, or omit)
  • A single accent color (--accent red), actually applied to the focal data point — not declared and left unused. Minimal ink is not the same as no signal. If nothing carries the accent, the chart is flat; pick the point the reader should look at and color it.
  • Data marks where they aid reading: dots on line endpoints, dot plots in place of bare bars
  • Sorted categories (rarely alphabetical, almost never as-input)
  • Tables when n ≤ ~20 and exact values matter

File index

FilePurpose
principles.mdTufte's 10 rules with practical interpretation
chart-selection.mdData + goal → chart type decision table
kill-list.mdWhat to remove from any chart
before-after.htmlSix side-by-side comparisons (open in browser)
report-voice.mdProse rules for reports/recaps/slides (no slop, no em-dashes)
checklist.md20-item pre-publish check
cheatsheet.htmlOne-page printable reference
cheatsheet.pdfSame, as PDF
presets/html-svg.mdStyle tokens + a working SVG bar chart, line chart, sparkline, small multiple
presets/react.mdRecharts theme + D3 patterns for slopegraph, sparkline-in-table, small multiples

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Tufte AI skill do?

Apply Edward Tufte's principles to any data visualization, chart, dashboard, or infographic. Use when the user asks to produce, design, critique, or improve a chart, graph, dashboard, KPI tile, table-with-data, sparkline, small multiple, time series, distribution plot, choropleth, or any other visual that communicates quantitative or categorical information. Also triggers on words like "visualize", "viz", "data viz", "chart", "graph", "dashboard", "infographic", "Tufte". Outputs Tufte-compliant designs in either self-contained HTML/SVG or React (Recharts/D3). Defaults to Tufte rules; user c...

Why use Tufte on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/aref-vc/tufte-claude-skill/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Tufte?

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 Tufte?

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

Is the Tufte AI skill free?

Yes. It is published on GitHub by aref-vc under the MIT license. 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 👇