Better Colors logo

Better Colors

Community
boraoztunc
better-colors

Color systems for digital products, from building and naming a palette to applying it with meaning and verifying contrast. Use when creating or extending a color palette, naming color tokens, theming light and dark appearances, auditing the colors in a codebase, or reviewing frontend code for color. Triggers on color palette, palette generation, color scale, color ramp, brand color, accent color, neutral palette, gray palette, status colors, design tokens, semantic color tokens, token naming, theming, dark mode colors, contrast ratio, APCA, gamut, display p3, oklch, color conversion, gradients, color meaning, increased contrast.

Overview

Publisherboraoztunc
Repositoryskills
Skill namebetter-colors
Stars
422
Forks
63
Bundled files
7
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.

  • 7 bundled files

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

  • Open source

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

Installation

Install the Better Colors 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/boraoztunc/skills/tree/main/better-colors
  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/boraoztunc/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/better-colors .claude/skills/better-colors
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Better Colors 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 Better Colors 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 Better Colors 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.

Colors

A color system is a small set of ramps, named by role, applied consistently, and verified against the backgrounds they actually render on. Almost every color problem is a system problem: a value picked in isolation, a token borrowed because it looked right, or a pair nobody measured. Contrast requirements belong to better-accessibility; surfaces, shadows, and icon color belong to better-ui.

Quick Reference

CategoryWhen to useReference
StructureWhich ramps a system needs, step roles, neutrals, status colors, auditing an existing palettepalette-structure.md
GenerationBuilding a ramp from a brand color, multi-hue systems, dark modepalette-generation.md
NamingPrimitive and semantic tiers, role inventory, naming grammar, anti-patternstoken-naming.md
UsageOne meaning per color, emphasis, gradients, culture, appearance variantscolor-usage.md
ContrastAPCA and WCAG checks, reporting failures, fixing on requestcontrast.md
FormatsChoosing a notation, converting, gamut and P3 fallbackscolor-formats.md
Review output formatSeverity scale, findings table, verification, verdictreview-output.md

Core Principles

1. Match the Project's Color System

Reuse the project's existing tokens and notation. Introducing a second color representation to fix one value makes the palette harder to reason about, not easier — a consistent hex system beats a hex system with oklch() scattered through it. Notation is not a defect. For a genuinely new system, oklch() is the best default because its numbers behave the way the ramp rules below describe; everywhere else a color library produces the same ramp in whatever the project writes (color-formats.md).

2. A System Is Ramps, Not Colors

One neutral ramp, one accent ramp, and only the status ramps the product actually renders. A warning ramp nothing imports is maintenance for zero pixels, and a second accent hue earns its place only when two things must be distinguishable at a glance.

3. Every Step Has a Job

A ramp is not a gradient to pick from by eye. Each step exists because a role needs it — page background, component hover, border, solid fill, body text — and a step no role consumes should not be generated. Both the Tailwind 50–950 and Radix 1–12 conventions map to those roles (palette-structure.md).

4. Name Primitives by Hue, Semantics by Role

Primitives name a value (--blue-500) and are never applied in a component. Semantic tokens name a job (--color-text-secondary), point at a primitive, and are the only tier components reference. That seam is what makes theming possible; without it, dark mode means auditing every usage to work out which ones meant "the accent" and which just wanted blue (token-naming.md).

5. Use a Token Only in Its Role

Never borrow a token because its value is right today. A separator used as a text color works until borders get lighter, and then the text goes with them. If a role has no token, add the token.

6. Hold the Hue Across the Ramp

Steps step evenly in perceived lightness, hue stays constant end to end, vividness peaks mid-ramp and falls off at both ends, and steps sit denser at the light end than the dark. Both ends stop short of pure black and white, which cannot carry hue at all. Use a color library rather than eyeballing it (palette-generation.md).

7. One Color, One Meaning

Use a color for one purpose across the whole interface, treating anything within 15° of hue as the same color. If the accent means interactive, that hue on static text tells users to click something that is not clickable — and an interactive element rendered neutral is just as misleading. Color is never the only carrier of meaning; better-accessibility owns that requirement.

8. Fill Exactly One Action per View

When filled color encodes primary emphasis, one primary action gets it and peer actions stay neutral. Put the color on the background rather than the label: a filled button reads as primary across the room, while accent-colored text on a neutral button reads as a link. Several colored backgrounds are fine when they encode distinct states or categories rather than competing as peers.

9. Measure the Rendered Pair, Then Report

Measure a foreground against the background it actually renders on, not the page background. When a pair fails, report it — the pair, its measured value, and the threshold it misses — and leave the colors alone. A project's colors are a design decision; change them only when asked, and remeasure after (contrast.md).

10. Pick a Gradient's Interpolation Space

The space is a look, not a correctness setting. in oklab is the best default — even brightness, no hue surprises. in oklch travels around the hue wheel rather than through the middle, staying vivid and sweeping through the hues between the stops: a distinct look, and the fix when a two-hue gradient goes gray in the middle. The sRGB default is the classic, and its darker, muted midpoint is the one most interfaces already look like (color-usage.md).

Common Mistakes

MistakeFix
A raw value where the project has a tokenReuse or add the correct role token in the project's existing notation
An isolated oklch() value dropped into a hex codebasePreserve the established notation unless a color-system migration is in scope
A primitive like --blue-500 used directly in a componentPoint a semantic token at it and use that
Token named for its appearance (--color-blue-button) or first use (--color-sidebar-gray)Name it for its role: --color-accent-solid, --color-bg-surface
--color-primary meaning the brand and --color-text-primary meaning body textReserve accent for the brand; let primary mean "most prominent of its group"
Semantic token used outside its role (separator as text)Add a token for the missing role; never borrow by value
Ramp built by varying HSL lightnessRebuild against perceived lightness with a constant hue
Ramp spaced evenly across the full rangeTighten the light end; 50 and 100 must be distinguishable as two surfaces
Same saturation number reused across huesMatch the same proportion of each hue's own maximum, not the raw value
Status hue that collides with the accent hueMove it until destructive and primary actions are distinguishable side by side
Dark mode made by mechanically reversing the light paletteReverse as a starting point, then reduce vividness, widen the dark end, and recheck every pair
prefers-color-scheme setting some tokens and a .dark class setting othersPick one switching mechanism and use it throughout
Failing contrastReport the pair, its measured value, and the threshold missed; change colors only when asked
Contrast fixed by changing hueChange lightness — it is the channel contrast responds to
P3 color with no sRGB fallbackDeclare the sRGB value first, then override inside @media (color-gamut: p3)
Gradient between opposite hues going gray in the middleSwitch to a polar space (in oklch) or add a mid-stop at a hue between the two
Palette verified only in light modeRecheck every foreground/background pair in both appearances

Reporting

A standalone color review is finished when every confirmed finding is reported in the format in review-output.md, with verification and a verdict. Under better-interface, its format governs instead.

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 Better Colors AI skill do?

Color systems for digital products, from building and naming a palette to applying it with meaning and verifying contrast. Use when creating or extending a color palette, naming color tokens, theming light and dark appearances, auditing the colors in a codebase, or reviewing frontend code for color. Triggers on color palette, palette generation, color scale, color ramp, brand color, accent color, neutral palette, gray palette, status colors, design tokens, semantic color tokens, token naming, theming, dark mode colors, contrast ratio, APCA, gamut, display p3, oklch, color conversion, gradie...

Why use Better Colors on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/boraoztunc/skills/tree/main/better-colors. 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 Better Colors?

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 Better Colors?

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

Is the Better Colors AI skill free?

Yes. It is published on GitHub by boraoztunc 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 👇