Color Expert

color-expert

A color science skill: OKLCH, APCA and WCAG contrast, design system ramps, palette generation, pigment mixing and color history

SkillLow risk

meodai/skill.color-expert

Install

npx skills add meodai/skill.color-expert

This is third-party code. Review the repository files before installing.

What it does

The skill has three layers. SKILL.md holds the essentials: which color space to use for which task, how to build perceptually even ramps and tokens, how to check contrast, and which libraries and tools to use. INDEX.md helps the agent find the right reference file, and the references folder holds well over a hundred sources: notes on Ottosson's OKLAB articles, Briggs lectures, video transcripts and docs for Culori, Spectral.js, Poline and others. Answers adapt to the mode: a concrete design project, a design system, generative art, a general question or building a palette generator.

Who it is for. For designers, frontend developers and generative artists who take color seriously.

Good fit when

  • You need an accent color ramp for light and dark themes
  • A gradient turns gray in the middle and you want to know why
  • You need to check text and background pairs against APCA or WCAG

Not a fit when

  • You need a finished brand book rather than color guidance
  • The task is photo or video grading in a specific application

Example request

Build a 9-step OKLCH ramp for the #E2561B accent and check text contrast in both themes

Limitations

References are large and the agent reads them selectively, so answer depth depends on which files it opens. Material is in English. The skill carries the author's opinions, such as avoiding coolors.co; they are backed by references but are a stance rather than a standard. CC BY 4.0 licensed.

How to disable. Remove the color-expert folder or symlink from the agent's skills directory.

Security check

  • The skill consists only of instructions and references

README in short

The README tells how the skill grew from notes into a knowledge base and how the author adds sources: video transcripts, converted PDFs and repository docs. It describes the reference structure by section: historical, contemporary science, techniques and tools. It lists the key positions baked into the skill and gives installation via npx skills or a symlink.

SKILL.md

---
name: color-expert
description: Use when working with color naming, color theory, color spaces, color definitions, or any task involving color knowledge - palettes, ramps, gradients, conversions, accessibility, perceptual matching, pigment mixing, print-vs-screen color, CSS color syntax, or historical color terminology. Use this skill whenever the user is choosing, comparing, generating, naming, converting, or explaining colors, even if they do not explicitly ask for "color theory."
---

# Color Expert

A comprehensive knowledge base for color-related work. See `references/INDEX.md` for 140+ detailed reference files; this skill file contains the essential knowledge to answer most questions directly.

## How to Use This Skill

Match the response to the user's explicit request and clearly implied constraints from context. Five common modes:

**Concrete design or art project** — "help me pick colors for my logo / poster / illustration / app." Ask about medium (print, screen, paint, mixed), brand or mood, audience, accessibility needs, and any existing colors to harmonize with. Then propose. Don't lecture about CIE 1931 or OKLCH internals unless asked. Recommend specific tools and palettes that fit the constraints, not generic theory.

**Design system, ramps, or theme tokens** — "build me a 9-step accent scale", "palette for light + dark mode", "Tailwind/Radix-style ramps", "what's the right gray ramp for our brand?" Prioritize in this order:

- Use OKLCH to build perceptually uniform scales (consistent lightness across hues, no muddy mid-tones).
- Build a token graph: reference tokens (palette) → semantic tokens (surface, on-surface, accent, success, warning, danger) → component usage; see *Implementation Guidance* below.
- Verify every text/background pair against APCA or WCAG in both light and dark.

The test for a sequential ramp is **flat perceptual derivative** — plot the perceptual step size between consecutive samples; it should be a horizontal line, in color *and* in grayscale. Bumps are regions where the ramp exaggerates change that isn't in the data (this is jet's core failure, not its ugliness).

## Color Spaces — What to Use When

| Task                            | Use                                    | Why                                                                       |
| ------------------------------- | -------------------------------------- | ------------------------------------------------------------------------- |
| Perceptual color manipulation   | **OKLCH**                              | Best uniformity for lightness, chroma, hue. Fixes CIELAB's blue problem.  |
| CSS gradients & palettes        | **OKLCH** or `color-mix(in oklab)`     | No mid-gradient darkening like RGB/HSL                                    |
| Gamut-aware color picking       | **OKHSL / OKHSV**                      | Ottosson's picker spaces — cylindrical like HSL but perceptually grounded |
| Normalized saturation (0-100%)  | **HSLuv**                              | CIELUV chroma normalized per hue/lightness. HPLuv for pastels.            |
| Print workflows                 | **CIELAB D50**                         | ICC standard illuminant                                                   |
| Screen workflows                | **CIELAB D65** or OKLAB                | D65 = screen standard                                                     |
| Cross-media appearance matching | **CAM16 / CIECAM02**                   | Accounts for surround, adaptation, luminance, and viewing conditions      |
| HDR                             | **Jzazbz / ICtCp**                     | Designed for extended dynamic range                                       |

FAQ

Why OKLCH instead of HSL?

HSL lightness does not match perception, so ramps and gradients come out uneven. OKLCH gives nearly uniform steps.

Is skill quality checked?

The evals folder has prompts that should and should not trigger the skill, plus realistic tasks to review answers.

Editors’ pick

Official Claude Code plugin from the Next.js repo: adopting Cache Components and Partial Prefetching, and verifying changes on a running dev server

PluginMedium risk142.3K
Editors’ pick

Official shadcn/ui skill and MCP server: the agent searches registries, adds components via the CLI and follows the library's rules

SkillMedium risk123.8K
Editors’ pick

A frontend design skill with 23 commands, live browser iteration and 61 detector rules for common AI-generated UI tells

SkillHigh risk68.1K
Editors’ pick

Vercel's skills: React and Next.js performance, UI guideline audits, React Native, component composition and deploys

SkillMedium risk31.2K