Color Scale logo

Color Scale

Community
dylantarre
color-scale

Generates perceptually uniform OKLCH color palettes from brand colors. Use when creating color systems, theme palettes, or converting hex values to 11-step scales. Outputs CSS custom properties, Tailwind config, or JSON tokens.

Overview

Publisherdylantarre
Repositorydesign-system-skills
Skill namecolor-scale
Stars
50
Forks
4
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Color Scale 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/dylantarre/design-system-skills/tree/main/skills/tokens/color-scale
  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/dylantarre/design-system-skills.git /tmp/design-system-skills
mkdir -p .claude/skills
cp -r /tmp/design-system-skills/skills/tokens/color-scale .claude/skills/color-scale
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Color Scale 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 Color Scale 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 Color Scale 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.

Color Scale Generator

Overview

Generate perceptually uniform 11-step color scales (50-950) from any base color. Includes auto-generated neutral and semantic colors harmonized with the brand.

When to Use

  • Starting a new project needing a color system
  • Adding brand colors to an existing palette
  • Building light/dark theme tokens
  • Converting a single hex to a full scale

Quick Reference

StepLightnessTypical Use
5097%Subtle backgrounds
10093%Hover states on light
20087%Borders, dividers
30078%Disabled states
40065%Placeholder text
50055%Primary brand color
60045%Hover on dark
70037%Active states
80027%Headings
90020%Body text
95014%High contrast text

The Process

  1. Get input: Ask for base color (hex preferred) and color name (e.g., "primary")
  2. Ask format: CSS custom properties, Tailwind config, or JSON tokens?
  3. Ask color system (default OKLCH):
    • OKLCH - Perceptually uniform, modern standard (recommended)
    • HSL - Hue, Saturation, Lightness (wide browser support)
    • RGB - Red, Green, Blue (universal compatibility)
    • LCH - Lightness, Chroma, Hue (perceptual, CSS Color 4)
    • HEX - Hexadecimal notation (maximum compatibility)
  4. Generate scale: Create 11 steps with consistent chroma/saturation
  5. Add neutrals: Generate neutral scale using same hue, minimal saturation
  6. Add semantics: Generate success, warning, error, info harmonized with brand
  7. Output: Provide complete token set in requested format

Color Systems

SystemFormat ExampleBest For
OKLCHoklch(55% 0.15 250)Modern browsers, perceptual accuracy
HSLhsl(220 80% 55%)Wide support, intuitive adjustments
RGBrgb(59 130 246)Universal, legacy systems
LCHlch(55% 60 250)Perceptual, CSS Color Level 4
HEX#3b82f6Maximum compatibility

Recommend OKLCH for new projects - it produces more visually consistent scales because lightness and chroma are perceptually uniform.

Output Formats

CSS Custom Properties:

css
:root {
  --primary-50: oklch(97% 0.01 250);
  --primary-500: oklch(55% 0.15 250);
  --primary-950: oklch(14% 0.10 250);
}

Tailwind Config:

js
module.exports = {
  theme: {
    extend: {
      colors: {
        primary: {
          50: 'oklch(97% 0.01 250)',
          500: 'oklch(55% 0.15 250)',
        }
      }
    }
  }
}

JSON Tokens:

json
{
  "color": {
    "primary": {
      "50": { "value": "oklch(97% 0.01 250)" },
      "500": { "value": "oklch(55% 0.15 250)" }
    }
  }
}

Algorithm Details

Lightness stops (L values):

  • 50: 0.97, 100: 0.93, 200: 0.87, 300: 0.78, 400: 0.65
  • 500: 0.55, 600: 0.45, 700: 0.37, 800: 0.27, 900: 0.20, 950: 0.14

Chroma/saturation adjustment at extremes:

  • L > 0.9: reduce to 30% (prevents washed-out pastels)
  • L < 0.2: reduce to 70% (prevents muddy darks)
  • Otherwise: full chroma

Semantic color hues (harmonized 10-15% toward brand):

  • Success: base 145 (green)
  • Warning: base 70 (amber)
  • Error: base 25 (red)
  • Info: base 250 (blue)

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 Color Scale AI skill do?

Generates perceptually uniform OKLCH color palettes from brand colors. Use when creating color systems, theme palettes, or converting hex values to 11-step scales. Outputs CSS custom properties, Tailwind config, or JSON tokens.

Why use Color Scale on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/dylantarre/design-system-skills/tree/main/skills/tokens/color-scale. 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 Color Scale?

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 Color Scale?

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

Is the Color Scale AI skill free?

Yes. It is published on GitHub by dylantarre 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 👇