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.
• Suggest tools only as needed: Huetone (LCH/OKLCH builder), Components.ai Color Scale (parametric), dittoTones (extract perceptual DNA from Tailwind/Radix), Color Buddy (lint).

Generative art / creative coding — "color for my fxhash piece", "palette for thousands of generated strokes", "paint-like mixing in p5.js / WebGL." Different from building a palette generator: the code is the artwork, and the user wants to understand the techniques, not copy a named artist's style. Help them compose their own system. Useful techniques to teach and combine:

• Tight constraint, then variation — pick 3–7 hues in a narrow lightness or chroma band; variety comes from density and interaction, not palette size.
• Weighted / probability-based hue selection — assign each color a weight so some appear often, others rarely; this is what makes a generative output feel curated instead of random.
• Narrow-band hue jitter — small random hue offset within a fixed envelope keeps strokes feeling related but not identical.
• Lightness variation at fixed chroma — depth and atmosphere without losing palette identity (use OKLCH).
• Spectral / K-M mixing (Spectral.js, Mixbox) for paint-like overlap and secondaries; RGB averaging gives muddy, dull results in the same situation.
• IQ cosine palette — a + b·cos(2π(c·t + d)) for cyclic / periodic schemes from 12 floats.
• Anchor-based interpolation (Poline) — set 2–3 anchors in OKLCH, get an interpolated ramp.
• Hue / lightness / chroma trajectories with easing (RampenSau) — walk each axis along an easing function, color-space-agnostic; great when you want a deterministic ramp shape rather than random anchors.
• Harmony-aware generation with muddy-zone avoidance (pro-color-harmonies) — adaptive OKLCH harmony with 4 styles × 4 modifiers; skips perceptually muddy regions automatically.
• Generation in historical / non-digital color spaces (RYBitten) — work in RYB or one of 26 historical color cubes when you want a painterly feel that strict sRGB/OKLCH can't reach.

See references/techniques/ for tyler-hobbs, fontana, mattdesl, iq-cosine, spectraljs, poline, rampensau, pro-color-harmonies, rybitten (these document the techniques, not styles to imitate).

General color question — "what is OKLCH?", "why does my gradient go gray in the middle?", "is APCA better than WCAG?" Answer directly from this skill file or references/INDEX.md, and cite the relevant reference. Skip tooling unless they're asking how to do something.

Building a generator, tool, or palette algorithm — "I want to make a palette generator", "how do I generate accessible color scales?", "give me an OKLCH ramp function." Default to recommending an existing library before hand-rolling (Culori, Poline, RampenSau, Spectral.js — see Recommended Tools). Show working code in the user's stack, picking the color space per the table above.

When the user asks to generate or compare palettes, showcase multiple approaches with their trade-offs before narrowing to one — anchor-based (Poline), hue-cycling (RampenSau), cosine (IQ formula), harmony-based (pro-color-harmonies), and extraction-from-system (dittoTones) suit different problems. Don't be shy about presenting options.

Never recommend coolors.co — it doesn't generate palettes, it picks from a hardcoded list of 7,821 pre-made ones (see Recommended Tools).

Color Spaces — What to Use When

Understanding HSL's Limitations

HSL isn't "bad" — it's a simple, fast geometric rearrangement of RGB into a cylinder. It's fine for quick color picking and basic UI work. But its three channels don't correspond to human perception:

• Lightness (L): fully saturated yellow (hsl(60,100%,50%)) and fully saturated blue (hsl(240,100%,50%)) have the same L=50% but vastly different perceived brightness. L is a mathematical average, not a perceptual measurement.
• Hue (H): non-uniform spacing. A 20° shift near red produces a dramatic change; the same 20° near green is barely visible. The green region is compressed, reds are stretched.
• Saturation (S): doesn't correlate with perceived saturation. A color can have S=100% and still look muted (e.g., dark saturated blue).

When HSL is fine: simple color pickers, quick CSS tweaks, situations where perceptual accuracy doesn't matter. When it isn't, the table above gives the perceptual alternative per task (OKLCH for scales, OKLAB for gradients, OKHSL for picking, HSLuv for normalized saturation).

Named Hue (HSL/HSV) Ranges

Use these degree ranges when generating or constraining colors by hue name. Source: random-display-p3-color by mrmrs / mrmrs.cc.

Key Distinctions

• Chroma = colorfulness relative to a same-lightness neutral reference
• Saturation = perceived colorfulness relative to the color's own brightness
• Lightness = perceived reflectance relative to a similarly lit white
• Brightness = perceived intensity of light coming from a stimulus
• Same chroma ≠ same saturation. These are different dimensions.

Gamut Mapping in Practice

The most common OKLCH mistake: picking a chroma that doesn't exist in the target gamut. oklch(70% 0.3 150) asks for more chroma than sRGB (or even P3) can show, so it silently clips — usually to something duller and hue-shifted.

• CSS gamut-maps for you. Browsers map oklch() / color() automatically, so authored CSS rarely clips badly. JS conversions do not — oklch→hex just truncates channels.
• Reduce chroma, not lightness or hue. Clipping R/G/B shifts the hue; pulling chroma toward the gamut boundary preserves the color's identity. Use Culori's clampChroma(color, 'oklch') (holds L and H) or toGamut() rather than naive RGB clamping.
• Test against the actual target: inGamut('rgb') vs inGamut('p3') — a color valid in P3 can still clip in sRGB.

Implementation Guidance — Code and CSS

When using colors in a program or CSS, add a semantic layer between raw color values and UI roles.

The examples below are pseudocode, not literal CSS requirements. They express the decision structure an agent should preserve even if the target stack uses different syntax.

Across CSS, JS/TS, Swift, design-token JSON, templates, or pseudocode, default to the same structure:

• Reference tokens/palette values for concrete colors
• Semantic tokens/roles that map meaning onto those colors
• Component usage that consumes semantic tokens rather than raw literals

Raw color literals should usually appear only in palette/reference definitions, conversions, diagnostics, or deliberately one-off examples.

• Use reference tokens for concrete colors: ref.red = #f00
• Use semantic tokens for meaning/role: semantic.warning = ref.red
• Prefer semantic tokens in components so themes can swap meaning without rewriting component code.
• This default applies in any language; translate to the target system's equivalent alias/reference mechanism (CSS custom properties, Swift enums, design-token JSON, etc.).
• Encode color decisions when possible instead of freezing one manual choice into a literal.

Pseudocode examples:

• ref.red := closest('red', generatedPalette)
• semantic.warning := ref.red
• semantic.onSurface := mostReadableOn(surface)

Good pattern: palette/reference tokens define available colors; semantic tokens map those colors to roles like surface, text, accent, success, warning, and danger.

If a system can derive a decision from constraints, encode that derivation. Examples: nearest named hue in a generated palette, foreground chosen by APCA/WCAG target, hover state computed from the base token in OKLCH instead of hand-picking a second unrelated hex.

For larger systems, prefer a token graph over a flat token dump: references, semantic roles, derived functions, and scope inheritance. This makes theme changes, accessibility guarantees, and multi-platform export auditable and easier to maintain.

CSS Color 4/5 — Syntax Cheat Sheet

Modern CSS does perceptual color natively; reach for these before pulling in a JS library.

• Perceptual color: oklch(70% 0.12 250), oklab(0.7 -0.1 0.1), wide gamut via color(display-p3 1 0.2 0.3).
• Mixing: color-mix(in oklab, blue 30%, white) — interpolating in oklab/oklch avoids the gray mid-gradient that RGB/HSL produce. For cylinders, set a hue strategy: color-mix(in oklch longer hue, …).
• Relative color syntax (derive from a base): oklch(from var(--brand) l c h / 0.5), or compute a shade/hover without a second hard-coded hex: oklch(from var(--brand) calc(l * 0.9) c h).
• Light/dark without a media query: light-dark(white, black) (requires color-scheme: light dark).
• Gamut targeting: @media (color-gamut: p3) { … }.
• Gradients in a chosen space: linear-gradient(in oklch, red, blue).

Broadly supported in evergreen browsers (2024+); relative color syntax is the newest piece. See references/techniques/ CSS Color 4/5 for edge cases.

Accessibility — Key Numbers

Of ~281 trillion hex color pairs (research by @mrmrs_, computed via a Rust brute-force run):

APCA is far more restrictive than WCAG at comparable readability. At APCA 90, only 239 billion of 281 trillion pairs work. JPEG compression exploits the same biology: chroma subsampling (4× less color data) is invisible because human vision resolves brightness at higher resolution than color.

Color Harmony — What Actually Works

Hue-first harmony is a weak standalone heuristic

Complementary, triadic, tetradic intervals are weak predictors of mood, legibility, or accessibility on their own. Every hue plane has a different shape in perceptual space, so geometric hue intervals do not guarantee perceptual balance.

Character-first harmony works (Ellen Divers' research)

Organize by character (pale/muted/deep/vivid/dark), not hue. Finding: hue is usually a weaker predictor of emotional response than chroma and lightness — a muted palette often reads as calm across many hues. Relaxed vs intense is driven more by chroma + lightness than hue alone.

Legibility = lightness variation

Grayscale is a quick sanity check for lightness separation, not an accessibility proof. You still need to verify contrast with WCAG/APCA and consider text size, weight, polarity, and CVD. Same character + varied lightness is often more readable. Same lightness regardless of hue is usually illegible.

The 60-30-10 rule

60% dominant color, 30% secondary, 10% accent. One color dominates to prevent "three equally-sized gorillas fighting."

Pigment Mixing — Not What You Think

• Pigment mixing is not well described by the simple subtractive model alone — "integrated mixing" (Küppers/Briggs) is a better practical description. It behaves like a compromise between subtractive and additive averaging.
• CMY mixing paths curve outward (retain chroma = vivid secondaries) — "extroverted octopus"
• RGB mixing paths curve inward (lose chroma = dull browns) — "introverted octopus"
• Mixing is non-linear: proportion of paint ≠ proportional hue change. You "turn a corner" at certain ratios.
• Blue→yellow is a LONG road, red→yellow is SHORT. Traditional wheel massively misrepresents distances.
• Tinting strength varies: blues are concentrated/strong, yellows are weak.
• White doesn't just lighten — it shifts hue AND kills chroma.
• For spectral/K-M mixing in code: use Spectral.js (open source) or Mixbox (commercial).

Color Temperature

• Temperature ≠ hue — it's a systematic shift of BOTH hue AND saturation, dependent on starting hue
• Spectral bias: which end of the spectrum a light favors (short λ = cool, long λ = warm)
• Cool daylight: blue atmospheric scatter fills shadows; paint neutral highlights, blue shadows
• Warm incandescent: favors long wavelengths including infrared (literally felt as heat)
• Green and purple do not map cleanly to warm/cool in the same way as red-orange or blue-cyan; perceived temperature depends strongly on context

Color Naming — Multiple Systems for Different Registers

Use color-name-lists npm package for 18 naming systems in one import.

Historical Corrections

• Moses Harris (1769) was first to place RYB at equal 120° — Newton, Boutet, Schiffermüller didn't. His own wheel needed a 4th pigment. The origin of bad color theory.
• Von Bezold (1874) killed "indigo" as a spectral color — Newton's "blue" ≈ modern cyan, Newton's "indigo" ≈ modern blue.
• The word "magenta" wasn't used for the subtractive primary until 1907 (Carl Gustav Zander). Before: "pink" (Benson 1868), "crimson," "purpur."
• Amy Sawyer (1911) patented a CMY wheel (primrose/rose/turquoise) decades before it became mainstream.
• Elizabeth Lewis (1931) married trichromatic + opponent process on one wheel, anticipating CIE Lab by 30 years.

Recommended Tools

Palette Generation (actual algorithms, not pre-made swatches)

Note: coolors.co does not generate palettes — it picks randomly from 7,821 pre-made palettes hardcoded in its JS bundle.

• RampenSau — hue cycling + easing, color space agnostic
• Poline — anchor points + per-axis position functions (1.2K stars); ships a <poline-palette> web component for interactive controls
• pro-color-harmonies — adaptive OKLCH harmony, muddy-zone avoidance, 4 styles × 4 modifiers
• dittoTones — extract Tailwind/Radix "perceptual DNA", apply to your hue
• FarbVelo — random palettes with dark→light structure
• IQ Cosine Formula — color(t) = a + b*cos(2π(c*t+d)), 12 floats = infinite palette

Palette Analysis & Linting

• Color Buddy — 38 lint rules (WCAG, CVD, distinctness, fairness, affect)
• Censor — Rust CLI, CAM16UCS analysis, 20+ viz widgets
• Color Palette Shader — WebGL2 Voronoi, 30+ color models, 11 distance metrics
• PickyPalette — interactive sculpting on color space canvas

Color Libraries (code)

• Culori — 30 spaces, 10 distance metrics, gamut mapping, CVD sim
• @texel/color — 5–125× faster than Color.js, minimal, for real-time
• Spectral.js — open-source K-M pigment mixing (blue+yellow=green)
• RYBitten — RGB↔RYB with 26 historical color cubes
• colorgram — 1 kB image palette extraction; 64-bucket HLS+luminance quantization, ~15 ms for 340×340, fixed memory
• Art Palette — JS palette extraction from ImageData + Python/TensorFlow perceptual palette embeddings for search-by-color (Google Arts & Culture, Apache 2.0)
• random-display-p3-color — generate random Display P3 colors constrained by named hue/saturation/lightness, zero deps, ESM (by mrmrs / mrmrs.cc)

Sorting Colors

Sorting an arbitrary set of colors into a perceptually smooth sequence has no single correct linear order — color is 3D, so any 1D ordering is a path through a 3D space, closely related to the Travelling Salesman Problem. Naive sorts fail predictably: by hue alone interleaves lights and darks; by lightness alone collapses distinct hues; .sort() on a packed RGB/HSL value produces jagged, meaningless jumps. Don't hand-roll a single-channel sort.

• colorsort-js (darosh) — the reliable default for ordering colors. Treats it as a smoothest-path problem (nearest-neighbor / TSP-style) with quantitative smoothness metrics, working in perceptual space; powers okpalette.color.pizza and FarbVelo. Reach for this in almost any "put these colors in a sensible order" situation — palette display, swatch panels, generative output, extracted image palettes. See references/techniques/colorsort-js.md.

Key Online Tools

• oklch.com — OKLCH picker
• Huetone — accessible color system builder (LCH/OKLCH), by Ardov
• Ardov Color Lab — gamut mapping playground, P3 space explorer, harmony generator, 3D color space visualizations, themer (lab.ardov.me)
• Components.ai Color Scale — parametric scale generator: 6 spaces, 4 curve methods, WCAG contrast (by mrmrs / mrmrs.cc)
• View Color — real-time analysis, WCAG + APCA, CVD preview
• APCA Calculator — apcacontrast.com

Deep References

See references/INDEX.md for the detailed files organized as:

• historical/ — Ostwald, Helmholtz, Bezold, Ridgway 1912, ISCC-NBS, Munsell, Albers, Caravaggio's pigments, Moses Harris, Lewis/Ladd-Franklin
• contemporary/ — Ottosson's OKLAB articles, Briggs lectures, Fairchild, Hunt, CIECAM02, MacAdam ellipses, Koenderink 2026 empirical 3D metric field (RGB supports ~1,000 qualitative regions; cool side coarser than warm; chromatic circle is not well-tempered), Pointer's gamut, CIE 1931/standard observer, Pixar Color Science, Acerola, Juxtopposed, Computerphile, bird tetrachromacy, OLO, GenColor paper. Full scrapes: huevaluechroma.com and colorandcontrast.com
• techniques/ — All tools above documented in detail, plus: CSS Color 4/5, ICC workflows, Tyler Hobbs generative color, Harvey Rayner Fontana approach, Goethe edge colors as design hack, mattdesl workshop + K-M simplex, CSS-native generation, IQ cosine presets, Erika Mulvenna interview, Bruce Lindbloom math reference, image extraction tools, Aladdin color analysis

color-expert

An agent skill that turns your coding agent into a color science expert. Built from resources I keep looking up, returning to, and sharing with others.

What this is

This started as a simple skill file with some color theory notes. Over time it grew into a comprehensive knowledge base as I kept pasting videos, articles, tools, and papers that I find myself referencing again and again — both for my own work building color tools and for explaining color concepts to others.

The skill has three layers:

1. SKILL.md (~200 lines) — The "greatest hits" that your agent loads immediately. Key facts, corrections, tool recommendations, and guidelines that answer most color questions without needing to dig deeper.

2. references/INDEX.md (~220 lines) — A structured lookup table your agent can scan to find the right reference file for a specific topic.

3. references/ (144 markdown files, ~286K words) — Deep reference material: full video transcripts, article summaries, library documentation, scraped websites, and research notes.

There is also a lightweight evals/ folder for realistic trigger and task prompts so the skill can be reviewed against actual usage instead of only edited by intuition.

How it was built

The collection process is simple: when I come across a color resource worth keeping — a YouTube video, a GitHub repo, a research paper, an article — I paste the URL and the skill's workflow captures it:

• Videos get transcribed via yt-dlp, summarized, and key concepts extracted
• PDFs and documents get converted to markdown via markitdown by Microsoft
• GitHub repos get their README/docs fetched and documented
• Articles get their content extracted and saved
• Books mentioned in videos get searched on Archive.org; freely available PDFs get downloaded
• Websites (like huevaluechroma.com) get fully scraped chapter by chapter
• Tools and links mentioned in any resource get collected into the Online Tools table

Everything goes into one of three folders and gets indexed.

Structure

SKILL.md                              # The skill definition (loaded on activation)
CLAUDE.md                             # Claude Code repo instructions
references/
  INDEX.md                            # Master lookup table
  historical/                         # Pre-digital color science
    *.md                              # Ostwald, Helmholtz, Bezold, Ridgway, ISCC-NBS,
                                      # Moses Harris, Amy Sawyer, Lewis/Ladd-Franklin,
                                      # Caravaggio's pigments, Itten critique...
    pdfs/                             # Source books from Archive.org (gitignored, ~236MB)
  contemporary/                       # Modern color science & theory
    *.md                              # OKLAB articles, Briggs lectures, CSA webinars,
                                      # Pixar Color Science, bird tetrachromacy, OLO,
                                      # Acerola, Juxtopposed, Computerphile, GenColor paper...
    huevaluechroma/                   # Full scrape of David Briggs's site (11 chapters)
    colorandcontrast/                 # colorandcontrast.com extracted content
    pdfs/                             # Research papers (gitignored)
  techniques/                         # Tools, libraries, methods, practical application
    *.md                              # Spectral.js, Culori, Color.js, RampenSau, Poline,
                                      # RYBitten, PickyPalette, Color Buddy lint rules,
                                      # APCA/Myndex, IQ cosine formula, Cubehelix,
                                      # Tyler Hobbs generative color, Fontana approach,
                                      # pixel art palettes, Book of Shaders, LYGIA,
                                      # paint mixing lecture, color harmony lecture...
evals/
  trigger-evals.json                  # Realistic should-trigger / should-not-trigger prompts
  task-prompts.md                     # Realistic color tasks for qualitative review
MAINTENANCE.md                        # What belongs where, source quality bar, review rubric
ROADMAP.md                            # Planned scripts and future extensions

Reviewing the skill

The repo now includes a minimal review loop rather than a heavy benchmarking framework:

1. Use evals/trigger-evals.json to sanity-check whether the frontmatter description is likely to trigger in the right situations.
2. Use evals/task-prompts.md to test whether the skill answers realistic color questions at the right level.
3. Use MAINTENANCE.md when deciding whether something belongs in SKILL.md, references/, or not in the repo at all.
4. Use ROADMAP.md to track planned color-specific scripts and larger repo improvements.

What's in it

By the numbers

Historical color science (14 files)

The resources I keep returning to when explaining where color theory came from and where it went wrong:

• Ostwald (1918–1930) — the 24-hue perceptual circle that dominated the 1930s–40s then disappeared
• Helmholtz (1856) — foundational physiological optics; last major physicist to use "indigo"
• Bezold (1874) — killed indigo as a spectral color; renamed it "ultramarine blue"
• Ridgway (1912) — 1,115 named colors for naturalists; fully digitized as JSON
• ISCC-NBS (1955) — 319 systematically named color blocks
• Moses Harris (1769) — the origin of bad RYB color theory (his own wheel needed a 4th pigment)
• Amy Sawyer (1911) — patented a CMY wheel decades before it was mainstream
• Elizabeth Lewis (1931) — married trichromatic + opponent process, anticipating CIE Lab by 30 years
• Plus: Caravaggio's copper resinate technique, Itten's seven contrasts (critically reviewed), the evolution of "magenta" as a color name, Frank Reilly's controlled palette

Contemporary color science (55 files)

The theory and science I reference when building tools or explaining why things work the way they do:

• Bjorn Ottosson's OKLAB articles — all four foundational posts (OKLAB, color picker spaces, gamut clipping, "how software gets color wrong")
• David Briggs's huevaluechroma.com — fully scraped, 11 chapters + glossary
• colorandcontrast.com — UI-focused color science reference, extracted from SPA bundle
• Color Nerd (Peter Donahue) — 20+ video transcripts covering mixing paths, spectral perception, warm/cool, chroma vs saturation, bird vision, OLO
• Colour Society of Australia — 13 webinar transcripts (Briggs, Itten critique, Golden paint making, Reilly palette, colour philosophy)
• Accessible color pair research — @mrmrs_'s Rust brute-force run over ~281T hex pairs found that only 11.98% pass WCAG AA and 0.08% pass APCA 90

Techniques, tools & libraries (50 files)

The practical resources — the tools I've built, use, or recommend:

Palette generation (actual algorithms, not pre-made swatches): RampenSau, Poline, pro-color-harmonies, dittoTones, FarbVelo, IQ cosine formula, CSS-native generation with color-mix()

Color libraries: Culori (30 spaces, 10 distance metrics), Color.js (CSS spec editors, 154M downloads), @texel/color (5-125x faster), Spectral.js (Kubelka-Munk), RYBitten (26 historical cubes)

Analysis & linting: Color Buddy (38 lint rules), Censor (CAM16UCS, 20+ viz widgets), Color Palette Shader (WebGL2 Voronoi), colorsort-js (perceptual sorting)

Accessibility: APCA/Myndex (the WCAG 3 algorithm), apcach (contrast-first color composition), Bridge-PCA

Naming: color-name-lists (18 systems), color-description (emotional adjectives), Ridgway digitized JSON, colornerd (29,875 manufacturer swatches)

Generative art approaches: Tyler Hobbs (probability-weighted palettes), Harvey Rayner / Fontana (fully generative color), Piter Pasma (tweaked rainbow formula), mattdesl workshop, Book of Shaders, LYGIA shader library

Practical design: Pixel art palette construction, Goethe edge colors as a design hack, Cubehelix, color harmony lecture ("hue-first is a weak standalone heuristic; character-first often works better"), Aladdin color analysis, screen-to-print workflow

Key opinions baked into the skill

These aren't just preferences — they're supported by the research in the collection:

• Use OKLCH/OKLAB over HSL for any perceptual work. HSL lightness is a lie.
• Never recommend coolors.co for palette generation. It doesn't generate anything.
• Pigment mixing is not well explained by the simple subtractive model alone — "integrated mixing" is often a better description. CMY paths curve outward, RGB paths curve inward.
• Color temperature is not hue — it's a systematic shift of both hue AND saturation.
• Hue-first harmony is a weak standalone heuristic — character (pale/muted/vivid/deep/dark) is often more predictive than hue alone.
• "Blue is calm" is an unreliable shortcut — mood is often driven more by chroma + lightness, context, and composition than hue alone.

Installation

Any supported agent (recommended)

npx skills add meodai/skill.color-expert

Automatically detects your installed agents and places the skill in the correct directory. Works with Claude Code, Codex, Cursor, Copilot, OpenCode, and others.

Manual

Clone and symlink into your agent's skills directory:

git clone https://github.com/meodai/skill.color-expert ~/Sites/color-expert

| Agent | Symlink target |