Design Tokens logo

Design Tokens

Community
julianoczkowski
design-tokens

Generate a design tokens file (CSS variables or Tailwind config) based on a chosen aesthetic philosophy, with light and dark mode palettes, spacing scale, type ramp, and component-level tokens. Use when starting a new project, establishing a visual system, setting up tokens, or mentions "tokens" or "design system".

Overview

Publisherjulianoczkowski
Repositorydesigner-skills
Skill namedesign-tokens
Stars
572
Forks
50
Bundled files
Instructions only
LicenseApache-2.0
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 julianoczkowski on GitHub. Read the source before you install it.

Installation

Install the Design Tokens 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/julianoczkowski/designer-skills/tree/main/design-tokens
  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/julianoczkowski/designer-skills.git /tmp/designer-skills
mkdir -p .claude/skills
cp -r /tmp/designer-skills/design-tokens .claude/skills/design-tokens
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design Tokens 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 Design Tokens 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 Design Tokens 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.

This skill generates the foundational design tokens for a project. Run this after the design brief and before building any components. Every component built after this references these tokens instead of hardcoding values.

Example prompts

  • "Set up design tokens for this project"
  • "Generate a token system based on Dieter Rams"
  • "I need a spacing scale and color palette before I start building"
  • "Create tokens that match our brief"

Process

  1. Check what already exists. Before generating anything, scan the codebase for:

    • CSS variable definitions (:root, [data-theme], custom property files)
    • Tailwind config (tailwind.config.js, tailwind.config.ts) and any theme extensions
    • Theme provider files (Material UI createTheme, Chakra extendTheme, shadcn globals.css)
    • Design token JSON files (Style Dictionary format, Figma token exports)
    • Any tokens.css, variables.css, theme.css, or similarly named files
    • package.json for UI framework dependencies (tailwindcss, @mui/material, @chakra-ui/react, etc.)

    If tokens already exist, extend them rather than replacing. Identify gaps (missing dark mode, incomplete spacing scale, no motion tokens) and fill those.

  2. Read the brief. Look for a design brief at .design/*/DESIGN_BRIEF.md. If multiple subfolders exist, use the most recently modified one, or ask the user which feature they are working on. If a philosophy is named, use the parameters from /frontend-design to derive token values. If no brief exists, ask the user what direction they want.

  3. Generate tokens in the format that matches the project's tech stack:

    • Tailwind project → extend tailwind.config.js and write to globals.css
    • CSS/HTML project → write to a tokens.css file
    • CSS-in-JS project → write to a theme.ts or theme.js file
    • If unclear, default to CSS custom properties (most portable)
  4. Always generate both light and dark mode palettes. Use [data-theme="dark"] or prefers-color-scheme media query. Both palettes should feel intentional for the chosen philosophy, not just inverted values.

Token Categories

Color

css
/* Semantic color tokens, not raw values */
--color-bg-primary:          /* Main background */
--color-bg-secondary:        /* Secondary/card background */
--color-bg-tertiary:         /* Subtle background (inputs, wells) */
--color-bg-inverse:          /* Inverted background */

--color-text-primary:        /* Main text */
--color-text-secondary:      /* Subdued text */
--color-text-tertiary:       /* Placeholder, disabled text */
--color-text-inverse:        /* Text on inverse backgrounds */
--color-text-link:           /* Link color */

--color-border-primary:      /* Default borders */
--color-border-secondary:    /* Subtle borders */
--color-border-focus:        /* Focus ring color */

--color-accent-primary:      /* Primary action color */
--color-accent-primary-hover:
--color-accent-primary-active:
--color-accent-secondary:    /* Secondary action color */

--color-status-success:
--color-status-warning:
--color-status-error:
--color-status-info:

--color-surface-overlay:     /* Modal/dropdown backdrop */

Spacing

Generate a consistent scale. The base unit should match the philosophy:

  • Tight philosophies (Brutalist, Swiss): 4px base
  • Balanced philosophies (Rams, Scandinavian): 4px or 8px base
  • Spacious philosophies (Japanese Minimalism, Editorial): 8px base with larger multipliers
css
--space-0:   0;
--space-1:   /* base * 0.25 */
--space-2:   /* base * 0.5 */
--space-3:   /* base * 0.75 */
--space-4:   /* base * 1 */
--space-5:   /* base * 1.5 */
--space-6:   /* base * 2 */
--space-7:   /* base * 3 */
--space-8:   /* base * 4 */
--space-9:   /* base * 6 */
--space-10:  /* base * 8 */
--space-11:  /* base * 12 */
--space-12:  /* base * 16 */

Typography

css
--font-family-display:       /* Headline/display font */
--font-family-body:          /* Body text font */
--font-family-mono:          /* Code/monospace font */

--font-size-xs:
--font-size-sm:
--font-size-base:
--font-size-md:
--font-size-lg:
--font-size-xl:
--font-size-2xl:
--font-size-3xl:
--font-size-4xl:             /* Hero/display size */

--font-weight-normal:
--font-weight-medium:
--font-weight-semibold:
--font-weight-bold:

--line-height-tight:         /* Headings: 1.1-1.3 */
--line-height-normal:        /* Body: 1.4-1.6 */
--line-height-relaxed:       /* Spacious body: 1.6-1.8 */

--letter-spacing-tight:      /* Display type */
--letter-spacing-normal:
--letter-spacing-wide:       /* All-caps, labels */

Layout

css
--max-width-content:         /* Max reading width (65-75ch equivalent) */
--max-width-wide:            /* Wide content area */
--max-width-page:            /* Full page max width */

--border-radius-sm:
--border-radius-md:
--border-radius-lg:
--border-radius-full:        /* Pill/circle */

--shadow-sm:
--shadow-md:
--shadow-lg:
--shadow-focus:              /* Focus ring shadow */

Motion

css
--duration-instant:   50ms;
--duration-fast:      150ms;
--duration-normal:    250ms;
--duration-slow:      400ms;
--duration-slower:    600ms;

--easing-default:     cubic-bezier(0.4, 0, 0.2, 1);
--easing-in:          cubic-bezier(0.4, 0, 1, 1);
--easing-out:         cubic-bezier(0, 0, 0.2, 1);
--easing-bounce:      cubic-bezier(0.34, 1.56, 0.64, 1);

Responsive Breakpoints

css
--breakpoint-sm:   375px;    /* Mobile */
--breakpoint-md:   768px;    /* Tablet */
--breakpoint-lg:   1024px;   /* Small desktop */
--breakpoint-xl:   1280px;   /* Desktop */
--breakpoint-2xl:  1536px;   /* Wide desktop */

Dark Mode

Always generate dark mode tokens alongside light mode. Rules:

  • Do not simply invert colors. Dark backgrounds should be warm or cool depending on the philosophy.
  • Reduce contrast slightly in dark mode (pure white text on pure black is harsh).
  • Shadows should use darker, more transparent values in dark mode, not the same shadows as light.
  • Accent colors may need lightness adjustments to maintain contrast ratios.
  • Include a prefers-color-scheme media query AND a [data-theme="dark"] attribute selector so the user can support both system preference and manual toggle.
css
:root {
  /* Light mode tokens */
}

[data-theme="dark"] {
  /* Dark mode overrides */
}

@media (prefers-color-scheme: dark) {
  :root:not([data-theme="light"]) {
    /* System-preference dark mode, unless user explicitly chose light */
  }
}

Output

Save the tokens file in the appropriate location for the project's tech stack. State which philosophy the tokens are derived from and note any deviations or choices made.

Frequently asked questions

What does the Design Tokens AI skill do?

Generate a design tokens file (CSS variables or Tailwind config) based on a chosen aesthetic philosophy, with light and dark mode palettes, spacing scale, type ramp, and component-level tokens. Use when starting a new project, establishing a visual system, setting up tokens, or mentions "tokens" or "design system".

Why use Design Tokens on TypingMind?

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

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

Which AI models can use Design Tokens?

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 Design Tokens?

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

Is the Design Tokens AI skill free?

Yes. It is published on GitHub by julianoczkowski under the Apache-2.0 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 👇