Color Semantic Systems logo

Color Semantic Systems

Community
Deibler
color-semantic-systems

Use this skill when building or auditing a color system that encodes meaning — status colors (success / warning / error), category colors (department, product line, user segment), brand-role colors (primary, secondary, tertiary). Trigger when designing status badges, picking chart palettes, building a design-system color spec, or fixing inconsistent color use across surfaces. Sub-aspect of `color`; read that first.

Overview

PublisherDeibler
Repositoryuniversal-design-principles
Skill namecolor-semantic-systems
Stars
9
Forks
3
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

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

Installation

Install the Color Semantic Systems 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/Deibler/universal-design-principles/tree/main/plugins/perception-and-hierarchy-principles/skills/color-semantic-systems
  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/Deibler/universal-design-principles.git /tmp/universal-design-principles
mkdir -p .claude/skills
cp -r /tmp/universal-design-principles/plugins/perception-and-hierarchy-principles/skills/color-semantic-systems .claude/skills/color-semantic-systems
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Color Semantic Systems 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 Semantic Systems 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 Semantic Systems 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.

Building semantic color systems

A semantic color system encodes meaning through color: green means success, red means error, blue means primary brand. Done well, users learn the system once and read every surface fluently. Done poorly, the same color means different things in different places, and users learn nothing reliably.

What semantic colors should encode

Three useful categories:

Status / state

Conveys the condition of a thing:

  • Success / completed / passed
  • Warning / pending / caution
  • Error / failed / overdue
  • Info / neutral / draft

Status colors map to specific outcome semantics. Use sparingly: every visible status badge is attention spent.

Category

Conveys what kind of thing this is:

  • Project tags (a small palette of distinct hues for project labels)
  • Department or team
  • Product line
  • User segment

Categories should use perceptually distinct hues; for ≤ 7 categories, color works well. Beyond that, the user can't reliably remember which color means which.

Brand role

Conveys importance or role within the design:

  • Primary brand color → primary CTA
  • Secondary / accent → recommended option, focused state
  • Tertiary → light emphasis (informational badges)

Role colors are about hierarchy more than meaning per se.

Building a status palette

A workable status set:

success:    hsl(142 70% ...)   green
warning:    hsl(38 90% ...)    amber
destructive: hsl(0 75% ...)    red
info:       hsl(220 90% ...)   blue
neutral:    hsl(0 0% ...)      grey

For each, define multiple lightness stops:

  • *-50 — tinted background (used for badges, alerts, subtle treatments)
  • *-300 — border or icon
  • *-500 — primary use (badge color, button color)
  • *-700 — text color (dark, used on tinted backgrounds)
  • *-900 — text on dark backgrounds

The pairing rule: *-50 background + *-700 text gives WCAG AA contrast at body size; *-50 + *-500 gives AA for large text only.

Consistency rules for semantic colors

A semantic color system breaks the moment a color means different things in different places. Rules:

  • One color per role. Don't have "two reds" for "destructive" and "important emphasis." Pick one role per color.
  • Status colors stay status. Don't use the destructive red for marketing emphasis. The user reads it as error.
  • Category colors stay categorical. Don't reuse a project-tag color for a status badge.
  • Document the system. A color-system spec page that lists every color and its role keeps the team honest.

Building a category palette

For project tags, departments, or chart series:

  • 5–7 hues maximum for memorability; beyond that, users can't recall what means what.
  • Distribute around the color wheel so adjacent items are visually distinct.
  • Match lightness and saturation across the set so no one color dominates.
  • Test with colorblind simulation to ensure each hue remains distinct.

A workable 7-color category palette:

hsl(220 70% 55%)    blue
hsl(160 60% 45%)    teal
hsl(40 90% 55%)     amber
hsl(310 60% 55%)    pink
hsl(10 70% 55%)     red-orange
hsl(270 50% 55%)    violet
hsl(85 50% 45%)     olive

Each at similar lightness and saturation; each visually distinct from neighbors.

Brand role palette

The minimum useful set:

  • Primary: filled CTA, focused state, brand emphasis. One hue, used sparingly.
  • Secondary: optional alternative emphasis (often used for "recommended" highlight).
  • Accent / tertiary: micro-emphasis (informational icons, soft highlights).

Most products need only primary plus neutrals; secondary and accent are optional.

Worked example: a complete semantic system

css
:root {
  /* Brand */
  --brand-primary: hsl(220 90% 50%);
  --brand-primary-fg: white;
  --brand-primary-hover: hsl(220 90% 45%);

  /* Neutrals (tinted toward brand) */
  --neutral-50: hsl(220 6% 98%);
  --neutral-100: hsl(220 6% 96%);
  --neutral-200: hsl(220 6% 92%);
  --neutral-300: hsl(220 6% 85%);
  --neutral-400: hsl(220 6% 65%);
  --neutral-500: hsl(220 6% 50%);
  --neutral-600: hsl(220 6% 40%);
  --neutral-700: hsl(220 6% 27%);
  --neutral-800: hsl(220 6% 18%);
  --neutral-900: hsl(220 6% 9%);

  /* Status */
  --success-bg: hsl(142 70% 95%);
  --success-fg: hsl(142 70% 22%);
  --success-border: hsl(142 60% 70%);

  --warning-bg: hsl(38 95% 95%);
  --warning-fg: hsl(38 90% 25%);
  --warning-border: hsl(38 80% 70%);

  --destructive-bg: hsl(0 80% 95%);
  --destructive-fg: hsl(0 75% 32%);
  --destructive-border: hsl(0 60% 70%);

  --info-bg: hsl(210 80% 95%);
  --info-fg: hsl(210 80% 30%);
  --info-border: hsl(210 60% 70%);
}

Every status pair (bg + fg) clears WCAG AA contrast. The neutrals are tinted toward the brand for cohesion.

Anti-patterns

  • Brand color reused as primary semantic. If the brand is red and red also means "destructive," every CTA looks dangerous.
  • Decorative status color. A red border around a card with no actual error. Users learn to dismiss the cue.
  • Inconsistent saturation across statuses. Bright green success, muted yellow warning, vivid red error. The visual hierarchy jumps; nothing reads coherently.
  • Too many statuses. A system with 8 distinct status colors no user can remember.
  • Categories that compete with statuses. A "project" category color happens to be the same red as your destructive status. Users get confused.

Heuristics

  1. The "what does each color mean?" audit. List every color in your design system. Can you name a single specific role for each? If yes, the system is coherent. If a color has multiple roles, conflicts are inevitable.
  2. The grayscale test. Convert to grayscale. Does the visual hierarchy still work? If yes, color is enhancing, not carrying. If no, you're depending on color alone.
  3. The colorblind test. Simulate deuteranopia. Are status colors still distinct? Categories?
  4. The cross-surface check. Open three different pages of the product. Does the same status look the same color across all three?

Related sub-skills

  • color (parent).
  • color-accessibility-and-mode — accessibility and dark-mode considerations for semantic systems.
  • hierarchy-color-and-tone — color as a hierarchy axis.
  • consistency (cognition) — semantic color is a consistency discipline.

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 Semantic Systems AI skill do?

Use this skill when building or auditing a color system that encodes meaning — status colors (success / warning / error), category colors (department, product line, user segment), brand-role colors (primary, secondary, tertiary). Trigger when designing status badges, picking chart palettes, building a design-system color spec, or fixing inconsistent color use across surfaces. Sub-aspect of `color`; read that first.

Why use Color Semantic Systems on TypingMind?

Because you install it once and use it with any model. Color Semantic Systems 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 Semantic Systems in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Deibler/universal-design-principles/tree/main/plugins/perception-and-hierarchy-principles/skills/color-semantic-systems. 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 Semantic Systems?

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 Semantic Systems?

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

Is the Color Semantic Systems AI skill free?

It is published on GitHub by Deibler. Check the repository for licensing terms. 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 👇