Agent skill

Color Palette

by jmagly in jmagly/aiwg

Generate, analyze, compare, export, and suggest color palettes using color theory.

MITAuto-check passedFrontend & Design

Install Color Palette

skills CLI
$ npx skills add jmagly/aiwg --skill color-palette -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install jmagly/aiwg color-palette --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/jmagly/aiwg.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agentic/code/plugins/color-palette/skills/color-palette .claude/skills/color-palette && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
color-palette
GitHub stars
221
Token cost
~3k tokens
SKILL.md length
1,052 words
Files
1
Skills in repo
11
Repo updated
First seen
Licence
MIT

At a glance

Generate, analyze, compare, export, and suggest color palettes using color theory.

  • Works in 2 steps: Parse the seed color into HSL for… → Apply the selected harmony model
  • User asks about colors
  • SKILL.md covers Purpose, When This Skill Applies, Trigger Phrases and Subcommands, plus 3 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Color Palette is an agent skill from jmagly/aiwg. Generate, analyze, compare, export, and suggest color palettes using color theory. Use when user asks about colors, palettes, color schemes, or needs help choosing colors for a project.

Its SKILL.md is about 3k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Frontend & Design, covering Theming and dark mode. It works with Tailwind CSS. The repository describes itself as: Cognitive architecture for AI-augmented software development. Specialized agents, structured workflows, and multi-platform deployment. Claude Code · Codex · Copilot · Cursor ·… The licence is MIT.

When your agent uses it

  • User asks about colors
  • Needs help choosing colors for a project

Example prompts

  • “/color-palette”

Workflow steps

2 steps, taken from the first numbered list in SKILL.md.

  1. Parse the seed color into HSL for manipulation
  2. Apply the selected harmony model

What it can do on your machine

Read from SKILL.md and the folder at commit dda238f. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are css, javascript and json).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Color Palette loads about 3k tokens when it runs. Until then it costs about 50 tokens; SKILL.md has 1,052 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~50
When it runs · the whole SKILL.md, loaded when a task matches
~3k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from jmagly/aiwg at commit dda238f, republished under its MIT licence (© jmagly). 1,052 words, ~3,026 tokens.

Download SKILL.mdSave it as .claude/skills/color-palette/SKILL.md (or your agent's skills folder).
name
color-palette
description
Generate, analyze, compare, export, and suggest color palettes using color theory. Use when user asks about colors, palettes, color schemes, or needs help choosing colors for a project.
namespace
aiwg
platforms
all
version
1.0.0

Color Palette Skill

Purpose

Provide comprehensive color palette tooling: generate palettes from seed colors, analyze existing palettes, compare options, export to development formats, and suggest palettes based on project context.

When This Skill Applies

  • User asks to "generate a color palette" or "pick colors"
  • User provides a color and wants complementary/matching colors
  • User asks to "analyze this palette" or "check these colors"
  • User wants to export colors to CSS, Tailwind, or design tokens
  • User asks to compare two palettes
  • User needs color suggestions for a project type or mood
  • User wants to extract colors from an image

Trigger Phrases

Natural LanguageAction
"Generate a palette from #3498db"Generate palette with seed color
"What colors go with forest green?"Generate complementary/harmony palettes
"Analyze this palette: #1a1a2e, #e94560"Run harmony + contrast + mood analysis
"Compare these two palettes"Side-by-side comparison
"Export my palette as Tailwind config"Format conversion
"Suggest colors for a fintech app"Industry-aware suggestion
"Extract colors from this image"Dominant color extraction
"I need a dark mode version of this palette"Light/dark variant generation

Subcommands

generate

Generate a palette from a seed color, mood, or theme.

Parameters:

  • --seed <color> — Starting color (HEX, RGB, or HSL)
  • --harmony <model> — Harmony model (complementary, analogous, triadic, split-complementary, tetradic, monochromatic). Default: analogous
  • --count <N> — Number of colors to generate. Default: 5
  • --mood <text> — Mood descriptor (professional, playful, calm, energetic, luxurious, natural)
  • --temperature <warm|cool|neutral> — Color temperature bias

Process:

  1. Parse the seed color into HSL for manipulation
  2. Apply the selected harmony model:
ModelAlgorithm
ComplementarySeed + (hue + 180 degrees)
AnalogousSeed + (hue +/- 30 degrees)
TriadicSeed + (hue + 120) + (hue + 240)
Split-complementarySeed + (hue + 150) + (hue + 210)
TetradicSeed + (hue + 90) + (hue + 180) + (hue + 270)
MonochromaticSeed at varied lightness (20%, 40%, 60%, 80%) and saturation
  1. Adjust for mood if specified:

    • Professional: reduce saturation 10-20%, medium lightness
    • Playful: increase saturation 10-20%, varied lightness
    • Calm: reduce saturation 20-30%, shift toward blue/green hues
    • Energetic: increase saturation, shift toward warm hues
    • Luxurious: deep tones, add gold (#C9A96E) or dark accent
    • Natural: earth tones, greens, warm browns
  2. Generate tints and shades to fill count if needed

  3. Output the palette with visualization

Output Format:

Palette: Triadic from #2D5A27

  #2D5A27  ██████  Forest Green    (H:113 S:37% L:25%)
  #27355A  ██████  Navy Shadow     (H:220 S:37% L:25%)
  #5A2735  ██████  Burgundy Dark   (H:347 S:37% L:25%)
  #4A8A3F  ██████  Leaf Green      (H:113 S:37% L:39%)  [tint]
  #3F558A  ██████  Steel Blue      (H:220 S:37% L:39%)  [tint]

Harmony: Triadic (120 degree separation)
Temperature: Cool-neutral
Mood: Natural, grounded, trustworthy
analyze

Analyze an existing palette for harmony, contrast, accessibility, and mood.

Parameters:

  • --palette <colors> — Comma-separated color values

Process:

  1. Parse all colors into HEX, RGB, and HSL
  2. Identify the closest harmony model
  3. Calculate all pairwise contrast ratios (WCAG formula)
  4. Determine color temperature (average hue warmth)
  5. Assess color psychology associations
  6. Score overall palette coherence

Output: Uses templates/palette-report.md template.

compare

Compare two or more palettes side-by-side.

Parameters:

  • --a <colors> — First palette
  • --b <colors> — Second palette
  • --criteria <list> — What to compare (harmony, contrast, accessibility, mood, temperature). Default: all

Output:

Palette Comparison

              Palette A              Palette B
Colors:       #264653,#2a9d8f,...    #1a1a2e,#16213e,...
Harmony:      Analogous              Monochromatic
Temperature:  Cool                   Cool
Mood:         Calm, trustworthy      Dark, mysterious
WCAG AA:      4/6 pairs pass         3/6 pairs pass
Avg Contrast: 5.2:1                  4.1:1
Winner:       ← Better accessibility → Stronger mood coherence
export

Export palette in a target development format.

Parameters:

  • --palette <colors> — Colors to export
  • --format <fmt> — Target format: hex, rgb, hsl, css, tailwind, tokens
  • --names <list> — Optional semantic names (primary, secondary, accent, etc.)

Output by format:

CSS Custom Properties
css
:root {
  --color-primary: #264653;
  --color-secondary: #2a9d8f;
  --color-accent: #e9c46a;
  --color-warning: #f4a261;
  --color-danger: #e76f51;
}
Tailwind Config
js
module.exports = {
  theme: {
    extend: {
      colors: {
        primary: '#264653',
        secondary: '#2a9d8f',
        accent: '#e9c46a',
        warning: '#f4a261',
        danger: '#e76f51',
      },
    },
  },
}
Design Tokens (JSON)
json
{
  "color": {
    "primary": { "value": "#264653", "type": "color" },
    "secondary": { "value": "#2a9d8f", "type": "color" },
    "accent": { "value": "#e9c46a", "type": "color" },
    "warning": { "value": "#f4a261", "type": "color" },
    "danger": { "value": "#e76f51", "type": "color" }
  }
}
HEX List
#264653
#2a9d8f
#e9c46a
#f4a261
#e76f51
RGB
rgb(38, 70, 83)
rgb(42, 157, 143)
rgb(233, 196, 106)
rgb(244, 162, 97)
rgb(231, 111, 81)
HSL
hsl(195, 37%, 24%)
hsl(173, 58%, 39%)
hsl(43, 74%, 66%)
hsl(27, 87%, 67%)
hsl(12, 76%, 61%)
from-image

Extract dominant colors from an image.

Parameters:

  • Positional: path to image file
  • --count <N> — Number of dominant colors to extract. Default: 5

Process:

  1. Read the image file
  2. If the platform supports image analysis (multimodal), analyze the image directly to identify dominant colors
  3. Report extracted palette with approximate HEX values
  4. Optionally run analysis on the extracted palette

Note: Accuracy depends on the AI model's visual capabilities. For pixel-perfect extraction, recommend external tools like imagemagick or colorthief.

Show full SKILL.md (478 more words)Show less
suggest

Suggest palettes based on project type, mood, or industry.

Parameters:

  • --industry <name> — Industry vertical (healthcare, fintech, education, food, fashion, tech, legal, nonprofit)
  • --style <name> — Visual style (modern, classic, bold, minimal, organic, retro)
  • --mood <name> — Desired mood (trustworthy, energetic, calm, luxurious, playful, professional)
  • --accessibility <level> — Required WCAG level (A, AA, AAA)
  • --count <N> — Number of suggestions. Default: 3

Process:

  1. Research industry color conventions:
IndustryCommon PalettesReasoning
HealthcareBlues, greens, whitesTrust, cleanliness, calm
FintechNavy, teal, gold accentsTrust, stability, premium
EducationBright primaries, warm accentsEnergy, approachability
FoodWarm reds, oranges, greensAppetite, freshness
FashionBlack, white, bold accentSophistication, contrast
TechBlues, purples, gradientsInnovation, reliability
LegalNavy, burgundy, goldAuthority, tradition
NonprofitGreens, earth tones, warm huesGrowth, community
  1. Apply style modifiers (modern = cleaner tones, retro = muted/dusty, bold = high saturation)
  2. Apply mood adjustments
  3. Verify accessibility compliance if level specified
  4. Generate 3 distinct options with rationale

Output:

Palette Suggestions: Healthcare + Modern + AA

Option 1: "Clinical Trust"
  #1B4965  ██████  Deep Teal
  #5FA8D3  ██████  Sky Blue
  #BEE9E8  ██████  Mint Wash
  #62B6CB  ██████  Ocean
  #CAE9FF  ██████  Ice Blue
  Rationale: Classic healthcare blues with modern teal anchor.
  AA compliant: Yes (all text pairs meet 4.5:1)

Option 2: "Wellness Green"
  #2D6A4F  ██████  Forest
  #40916C  ██████  Sage
  #74C69D  ██████  Mint
  #B7E4C7  ██████  Seafoam
  #D8F3DC  ██████  Whisper Green
  Rationale: Nature-forward palette conveying growth and wellness.
  AA compliant: Yes (dark-on-light pairs meet 4.5:1)

Option 3: "Modern Care"
  #2B2D42  ██████  Charcoal
  #8D99AE  ██████  Cool Gray
  #EDF2F4  ██████  Snow
  #EF233C  ██████  Alert Red
  #D90429  ██████  Emergency
  Rationale: High-contrast modern palette with clear alert hierarchy.
  AA compliant: Yes (strong contrast ratios)

Color Theory Reference

Harmony Models

The color wheel is divided into 360 degrees of hue. Harmony models define mathematical relationships between hues:

  • Complementary (180 degrees): Maximum contrast, vibrant when used together
  • Analogous (30 degrees): Harmonious, found in nature, low contrast
  • Triadic (120 degrees): Balanced, vibrant even at low saturation
  • Split-complementary (150/210 degrees): Contrast with less tension than complementary
  • Tetradic (90 degree intervals): Rich palette, works best with one dominant color
  • Monochromatic (single hue): Unified, elegant, relies on value/saturation contrast
Color Psychology
Color FamilyAssociationsCommon Uses
RedEnergy, urgency, passion, dangerCTAs, errors, food brands
OrangeCreativity, enthusiasm, warmthAccents, notifications, food
YellowOptimism, attention, cautionHighlights, warnings
GreenGrowth, health, nature, moneySuccess states, eco brands
BlueTrust, calm, professionalismCorporate, tech, healthcare
PurpleLuxury, creativity, mysteryPremium brands, creative tools
PinkPlayfulness, compassion, romanceFashion, beauty, youth brands
BrownStability, earthiness, warmthOrganic brands, vintage
BlackSophistication, power, eleganceLuxury, fashion, typography
WhiteCleanliness, simplicity, spaceBackgrounds, minimalism
GrayNeutrality, balance, professionalismUI surfaces, text
Contrast Ratio Calculation

The WCAG 2.1 contrast ratio formula:

Relative luminance L = 0.2126 * R + 0.7152 * G + 0.0722 * B
(where R, G, B are linearized: value <= 0.04045 ? value/12.92 : ((value+0.055)/1.055)^2.4)

Contrast ratio = (L1 + 0.05) / (L2 + 0.05)
(where L1 is the lighter color's luminance, L2 is the darker)
Temperature
  • Warm: Hues 0-60 and 300-360 (reds, oranges, yellows, magentas)
  • Cool: Hues 120-270 (greens, blues, purples)
  • Neutral: Hues 60-120 and 270-300 (yellow-greens, violet transitions), or desaturated colors

Terminal Visualization

When displaying palettes in the terminal, use ANSI 24-bit color escape sequences for color blocks:

\033[48;2;R;G;Bm      \033[0m   # Background color block

Display format:

#RRGGBB  ██████  Color Name    (H:xxx S:xx% L:xx%)

If the terminal does not support 24-bit color, fall back to the closest 256-color or 16-color ANSI code.

Light/Dark Mode Variants

When generating light/dark mode variants:

Light mode (from a base palette):

  • Background: lightest color or white
  • Surface: second-lightest or tinted white
  • Text: darkest color or near-black
  • Primary: mid-range saturated color
  • Accent: most vibrant color

Dark mode (from a base palette):

  • Background: darkest color or near-black
  • Surface: slightly lighter than background
  • Text: lightest color or near-white
  • Primary: lighter/more saturated variant of light-mode primary
  • Accent: same hue, increased lightness for visibility

Ensure all text/background pairs meet WCAG AA (4.5:1) in both modes.

© jmagly, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in agentic/code/plugins/color-palette/skills/color-palette of jmagly/aiwg.

Open the folder on GitHubat commit dda238f

Compare with similar skills

Color Palette next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Color Palette compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Color Palette this skilljmagly/aiwg221—~3kAutomated safety check: PassMIT
Tailwindcss Developmentanonaddy/anonaddy4.9k10 repos~865Automated safety check: PassMIT
UI StylingOhh-889/skyroc79513 repos~2.5kAutomated safety check: PassMIT
MCP Developmentcoollabsio/coolify63k1 repos~949Automated safety check: PassMIT
Scalar Design Systemscalar/scalar16k—~2.7kAutomated safety check: PassMIT
DaisyUI 5 Color Rulessaadeghi/daisyui43k—~1.7kAutomated safety check: PassMIT

Similar skills

  • Tailwindcss Development

    anonaddy/anonaddy

    Always invoke when the user's message includes 'tailwind' in any form.

    4.9k GitHub starsUsed in 10 repos~865 tokens
    Frontend & DesignAuto-check passed
  • UI Styling

    Ohh-889/skyroc

    Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs.

    795 GitHub starsUsed in 13 repos~2.5k tokens
    Frontend & DesignAuto-check passed
  • MCP Development

    coollabsio/coolify

    A skill your agent uses for Laravel MCP development. An agent skill from coollabsio/coolify.

    63k GitHub starsUsed in 1 repo~949 tokens
    Frontend & DesignAuto-check passed
  • Scalar's design system — design tokens, theming (@scalar/themes), CSS variables, and the @scalar/components library.

    16k GitHub stars~2.7k tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • DaisyUI 5 Color Rules

    saadeghi/daisyui

    Rules for using daisyUI 5's semantic color names, such as primary and base-100, so interfaces stay readable across themes.

    43k GitHub stars~1.7k tokensUpdated 2 days ago
    Frontend & DesignAuto-check passed
  • Nuxt UI

    megaarmos/vue-spring-bottom-sheet

    Build UIs with @nuxt/ui v4 — 125+ accessible Vue components with Tailwind CSS theming.

    141 GitHub starsUsed in 1 repo~2.5k tokens
    Frontend & DesignAuto-check passed

More from jmagly/aiwg

All 11 skills in this repo
  • Review editorial phrase patterns and suggest contextual alternatives; legacy name does not imply authorship detection.

    221 GitHub stars~1.5k tokensUpdated 2 days ago
    Auto-check passed
  • Voice Apply

    jmagly/aiwg

    Apply a voice profile to transform content. An agent skill from jmagly/aiwg.

    221 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed
  • Mutation Test

    jmagly/aiwg

    Run mutation testing to validate test quality beyond code coverage.

    221 GitHub stars~3.2k tokensUpdated 2 days ago
    Auto-check passed
  • TDD Enforce

    jmagly/aiwg

    Configure TDD enforcement via pre-commit hooks and CI coverage gates.

    221 GitHub stars~2.1k tokensUpdated 2 days ago
    Auto-check passed
  • Detect project type, AIWG framework state, team configuration, and active work to summarize status and recommend next actions

    221 GitHub stars~2.3k tokensUpdated 2 days ago
    Auto-check passed
  • Manage artifact metadata, versioning, ownership, and review history across the SDLC lifecycle

    221 GitHub stars~1.9k tokensUpdated 2 days ago
    Auto-check passed

Works with

Questions about Color Palette

What does Color Palette do?

Generate, analyze, compare, export, and suggest color palettes using color theory. Color Palette is an agent skill from jmagly/aiwg. Generate, analyze, compare, export, and suggest color palettes using color theory.

When should I use Color Palette?

Color Palette fits situations like: user asks about colors; needs help choosing colors for a project.

How do I install Color Palette in Claude Code?

Run `npx skills add jmagly/aiwg --skill color-palette -a claude-code`. Or copy the skill folder (agentic/code/plugins/color-palette/skills/color-palette in jmagly/aiwg) into .claude/skills/color-palette in your project. Claude Code loads it when a task matches its description.

How do I install Color Palette in Codex?

Run `npx skills add jmagly/aiwg --skill color-palette -a codex`. Or copy the skill folder (agentic/code/plugins/color-palette/skills/color-palette in jmagly/aiwg) into .agents/skills/color-palette in your project. Codex loads it when a task matches its description.

Can I use Color Palette in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jmagly/aiwg --skill color-palette -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/color-palette, .gemini/skills/color-palette, .github/skills/color-palette and .opencode/skills/color-palette in your project.

What does Color Palette need to run?

SKILL.md names no scripts, command-line tools or credentials: Color Palette is instructions for the agent only.

Does Color Palette access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Color Palette safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Color Palette use?

Color Palette is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Color Palette use?

About 3k tokens (SKILL.md is roughly 12k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Color Palette?

Skills that share tags, products or a category with Color Palette: Tailwindcss Development (anonaddy/anonaddy, 4.9k stars), UI Styling (Ohh-889/skyroc, 795 stars), MCP Development (coollabsio/coolify, 63k stars) and Scalar Design System (scalar/scalar, 16k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Color Palette?

jmagly (a GitHub user) maintains it in jmagly/aiwg, which has 221 GitHub stars. The repository holds 11 skills in this directory. The repository was last updated on October 8, 2026.

Source: jmagly/aiwg on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.