Color Palette Library logo

Color Palette Library

Community
phazurlabs
color-palette-library

500+ ready-made color palettes with contrast scores, plus OKLCH palette generation, dark-mode luminance mapping, semantic color architecture, and data-viz scales. Use when picking or generating a specific palette. For color theory and hierarchy craft, use ui-visual-design-system.

Overview

Publisherphazurlabs
Repositorysumi
Skill namecolor-palette-library
Stars
58
Forks
11
Bundled files
6
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.

  • 6 bundled files

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

  • Open source

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

Installation

Install the Color Palette Library 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/phazurlabs/sumi/tree/main/skills/color-palette-library
  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/phazurlabs/sumi.git /tmp/sumi
mkdir -p .claude/skills
cp -r /tmp/sumi/skills/color-palette-library .claude/skills/color-palette-library
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Color Palette Library 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 Palette Library 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 Palette Library 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 Palette Library — 500+ Curated Palettes

Mental model

Colour decisions fail in a predictable order: people pick hues first, discover the contrast is illegal, patch the lightness, and end up with a palette whose steps are uneven and whose dark mode is an inversion.

Work the other way round. Fix the lightness ramp first — it is what makes a scale usable — then set chroma, then choose hue last, because hue is the only one of the three that is purely taste.

  • OKLCH, not HSL. In HSL, two colours at the same L can differ in perceived brightness by a factor of three. OKLCH lightness is perceptual, so a ramp built in it looks even without hand-correction.
  • Chroma peaks in the middle. Hold hue, run lightness 0.98 down to 0.18, and let chroma rise toward the mid-steps and fall at both ends. Flat chroma makes the light end muddy and the dark end neon.
  • Semantic names alias primitives. Components consume --color-bg-subtle, never --color-neutral-100. This is what makes a theme swap one file.
  • Dark mode is not inversion. Reduce luminance, desaturate, and raise elevation with lightness rather than shadow.

Constants

Semantic token names — every reference file writes against these. The values live in the palette catalogs.

css
:root {
  --color-bg-base; --color-bg-subtle; --color-bg-raised; --color-bg-overlay;
  --color-text-strong; --color-text-default; --color-text-muted; --color-text-inverse;
  --color-border-subtle; --color-border-default; --color-border-strong;
  --color-brand-subtle; --color-brand-default; --color-brand-strong;
  --color-success; --color-warning; --color-error; --color-info;
}

Scale generation, for reading any catalog entry: hold hue, run lightness from 0.98 to 0.18 across steps 50-950, peak chroma at steps 400-600.

Index

NeedReference
Generate a scale from one brand colouraccessible-palette-generator.md
Check APCA / WCAG contrast properlyaccessible-palette-generator.md
Colourblind-safe categorical seriesaccessible-palette-generator.md
A ready palette for fintech, healthcare, SaaS, e-commerce, socialindustry-palette-catalog.md
Colour psychology by industryindustry-palette-catalog.md
Monochromatic, duotone, neutral+accent, jewel, pastel, neoncolor-combination-recipes.md
Gradient recipescolor-combination-recipes.md
Map an existing light palette to darkdark-mode-color-science.md
Elevation by lightness rather than shadowdark-mode-color-science.md
How Stripe, Linear, Vercel, Notion, Figma, Shopify, GitHub do itbrand-color-systems.md
Extract a palette from an existing brandbrand-color-systems.md

Reference architecture

FileCoversLines
references/industry-palette-catalog.md10 palettes x 10 industries928
references/color-combination-recipes.md12 harmony categories + gradients889
references/brand-color-systems.md20 real brands deconstructed786
references/dark-mode-color-science.mdinversion is wrong; what to do instead685
references/accessible-palette-generator.mdAPCA, OKLCH generation, colourblind586

What every reference file contains

  1. The palette or recipe as OKLCH values, with hex fallbacks
  2. Contrast scores for every foreground/background pair that matters
  3. The semantic mapping — which primitive fills which semantic slot
  4. The dark-mode counterpart, not just the light values
  5. Where the combination fails, and what it should not be used for

Routing

For generating a palette — the APCA contrast algorithm, step-by-step OKLCH generation, and colorblind-safe categorical scales: read references/accessible-palette-generator.md.

For a ready-made palette by industry — ten each for fintech, healthcare, SaaS, e-commerce, social and more: read references/industry-palette-catalog.md.

For combination theory — monochromatic, duotone, neutral-plus-accent, and the rest of the twelve categories including gradients: read references/color-combination-recipes.md.

For dark mode — why it is not inversion, luminance reduction, desaturation rules, and elevation-by-lightness: read references/dark-mode-color-science.md.

For how real products do it — Stripe, Linear, Vercel, Notion, Figma, Shopify and GitHub deconstructed: read references/brand-color-systems.md.

For odds and ends — the patterns that had no home in the files above when this skill was converted to a router: read references/color-supplementary.md.

Cross-References

  • design-token-presets — complete token system templates by industry
  • visual-design-mastery — color scoring on the 10-dimension Awwwards scale
  • sector-style-intelligence — industry-specific color direction
  • accessibility-inclusive-design — WCAG 2.2 + APCA compliance testing
  • data-visualization-mastery — dataviz palette integration
  • platform-visual-standards — iOS 26 Liquid Glass and M3 Expressive color details
  • shadow-elevation-density — elevation-driven color in dark mode
  • typography-pairing-recipes — text color and contrast pairing with type

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 Palette Library AI skill do?

500+ ready-made color palettes with contrast scores, plus OKLCH palette generation, dark-mode luminance mapping, semantic color architecture, and data-viz scales. Use when picking or generating a specific palette. For color theory and hierarchy craft, use ui-visual-design-system.

Why use Color Palette Library on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/phazurlabs/sumi/tree/main/skills/color-palette-library. 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 Palette Library?

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 Palette Library?

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

Is the Color Palette Library AI skill free?

Yes. It is published on GitHub by phazurlabs 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 👇