Ux Color logo

Ux Color

Organization
Uxcel-Lab
ux-color

Design or critique a product's color palette and system — base hue, harmony, neutrals, semantic colors, tonal scales, and tokens. Applies the always-true core and gates context-dependent decisions (dark mode, brand expressiveness, accessibility trade-offs). Trigger when creating a color palette, choosing UI colors, building a color system, setting up color tokens, or reviewing a palette for issues.

Overview

PublisherUxcel-Lab
Repositoryproduct-skills
Skill nameux-color
Stars
35
Forks
8
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Uxcel-Lab on GitHub. Read the source before you install it.

Installation

Install the Ux Color 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/Uxcel-Lab/product-skills/tree/main/ux/foundations/color
  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/Uxcel-Lab/product-skills.git /tmp/product-skills
mkdir -p .claude/skills
cp -r /tmp/product-skills/ux/foundations/color .claude/skills/ux-color
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ux Color 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 Ux Color 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 Ux Color 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.

Color Palette & System Skill

How this skill behaves (read first)

This is a generative skill. Color has two opposite default failure modes: arbitrary (pick a nice blue, no system, fails contrast) and garish (apply every emotional/cultural association and standout trick → the over-colored "Willy Wonka" palette aesthetics warns about). So this skill gates:

  1. Establish brand, audience, and market — these drive the one set of hue/emotion/culture choices worth making.
  2. Apply the always-true core — a restrained, role-based, tokenized, accessible palette holds for any product.
  3. Make the expressive choices deliberately — surface base-hue/emotion/saturation/dark-mode as gated decisions, not defaults.

Then hand off to the audits: accessibility owns contrast ratios and color-blindness; aesthetics owns harmony and balance.


Step 0 — Establish context before choosing colors

  • Brand & industry — existing brand colors/guidelines? Industry conventions (finance → trust/navy; kids → playful)? Check competitors for the field's visual language.
  • Audience & market — who, and where — color meaning is culture-dependent (see the emotion reference caveat).
  • Personality — premium/refined vs. playful/energetic? This drives saturation and neutrals more than hue.
  • Modes — light only, or dark mode too?

State assumptions if proceeding without answers.


The always-apply core (true for any palette/system)

  • Build on a harmony scheme, then refine. Start from a base color and a scheme — monochromatic/analogous (safe, low-contrast) or complementary (high-contrast, soften with tints/transitional tones) — then adjust saturation/brightness for interest.
  • Neutral-dominant, accent-sparing — the 60-30-10 rule. ~60% primary/neutral surface, ~30% secondary, ~10% accent reserved for elements that must stand out (CTAs). Primary/secondary stay relatively neutral for readability.
  • Define color by role, not just hue. A system needs: primary / secondary / tertiary accents (with on-color pairs), neutral/surface tones, and functional/semantic colors (success, warning, error, info).
  • Keep functional colors distinct from brand. If the brand color is a bright red near the error red, define a separate error family so users don't confuse branding with feedback.
  • Build tonal scales + tokens. Generate consistent tints/shades from each base; expose them as named variables/tokens (functional or numeric naming) so one change propagates and the system stays consistent.
  • Never rely on color alone, and check every text/icon/surface pair for contrast — defer the actual ratios and color-blindness checks to the accessibility audit, but the palette must be built to pass them.

The context-dependent decisions (surface, don't auto-apply)

Present each with its trade-off and a recommendation tied to Step 0. Stacking many saturated hues/associations is the failure mode.

DecisionApply whenAvoid / adapt whenDefault recommendation
Base hue / emotional toneMatch hue to the feeling the brand wants (see reference)Picking a hue for taste alone, or chasing every associationOne intentional base aligned to brand + industry
Harmony schemeComplementary for vivid/high-energy; analogous/mono for calm/refinedComplementary at full chroma (too intense)Analogous/mono as the safe default; complementary softened with neutrals
Saturation / vibrancyHigh saturation for playful/energetic brandsPremium/enterprise (use restrained, desaturated tones)Match to personality; neutral anchor for any bold accent
Cultural adaptationGlobal product / specific markets (color meaning differs)Single-market where convention is settledValidate key hues against target markets
Number of accentsOne clear accent; a second only if it earns a roleMany competing accent colors (garish, no focal point)One accent + functional colors; everything else neutral
Dark modeProduct needs/expects itBolting it on by simple inversionDesign semantic colors for both modes (below)

Color → emotion (the gated menu — use sparingly, context decides)

Yellow: happy/warm · Orange: energetic/enthusiastic · Red: stimulating/urgent/passionate (also alarm) · Blue: calming + trustworthy (navy → finance/tech trust) · Green: grounded/natural/success · Purple: creative/spiritual/premium · Pink: soft/nurturing (mind shifting gender connotations) · Brown/earth tones: stable/grounded. Caveat: these are Western-leaning and context-dependent — the same hue means different things by culture and surrounding colors. Pick one intentional association; don't paint with all of them.

Dark mode notes

Define semantic colors (purpose, not literal hue) so they adapt across modes; don't just invert light mode. Maintain contrast in both modes, signal elevation with lighter surfaces (not just shadow) in dark mode, and test in real lighting conditions.


Validate the result (orchestration)

Hand-offs name each lens by its installable skill name. Invoke one only if that skill is installed; if it isn't, this skill's own core already carries these rules — proceed without it rather than blocking.

After defining or revising the palette, hand the result to the audit lenses rather than declaring it done. These are candidate lenses — posture is set by docs/orchestration-policy.md, or route the whole thing through ux-design-review. Here, none are Tier A; accessibility and aesthetics are Tier B (offered) — under an existing design system aesthetics is suppressed and accessibility narrows to usage. If the user invoked this skill for one specific thing, respect that scope.

  • ux-accessibility-audit (Tier B — offer; narrow under a design system) — contrast ratios for every text/icon/surface pair (light and dark mode), and color-blindness safety (don't encode status by red/green alone). The palette must be built to pass this.
  • ux-aesthetics-audit (Tier B — offer; suppress under a design system) — harmony and balance: is it neutral-dominant with a clear accent, or has it tipped into the over-colored, no-focal-point "Willy Wonka" zone?

If accessibility fails a pair or aesthetics flags garishness, return to the 60-30-10 / one-accent core.


Common do/don't patterns

❌ Don't✅ Do
Pick a nice color with no systemDefine roles: primary/secondary/tertiary + neutrals + functional
Equal amounts of several bright colors60-30-10: neutral-dominant, one ~10% accent
Apply every color-emotion associationOne intentional association tied to brand + market
Full-chroma complementary clashSoften with tints/neutrals; analogous/mono as the safe base
Brand red ≈ error redSeparate functional color families from brand
Hardcode hex everywhereTonal scales exposed as named tokens/variables
Encode status by color aloneColor + icon/label (→ accessibility)
Invert light mode for "dark mode"Semantic colors designed for both modes; elevation via lighter surfaces
Ship without contrast checksHand off to accessibility (ratios + color-blindness) and aesthetics

Source lessons (Uxcel)

Frequently asked questions

What does the Ux Color AI skill do?

Design or critique a product's color palette and system — base hue, harmony, neutrals, semantic colors, tonal scales, and tokens. Applies the always-true core and gates context-dependent decisions (dark mode, brand expressiveness, accessibility trade-offs). Trigger when creating a color palette, choosing UI colors, building a color system, setting up color tokens, or reviewing a palette for issues.

Why use Ux Color on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Uxcel-Lab/product-skills/tree/main/ux/foundations/color. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ux Color?

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 Ux Color?

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

Is the Ux Color AI skill free?

Yes. It is published on GitHub by Uxcel-Lab under the MIT 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 👇