Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Color Theory

ASecurity

Apply color theory with palette building, harmony, psychology, contrast, and accessibility standards.

2 stars
0 votes
0 copies
0 views
Added 9/29/2026
ai-agentsrustgoexpress

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill color-theory --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Color Theory?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Color Theory
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-color-theory/badge)](https://www.skillsdirectory.com/skills/aicodedecode-color-theory)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: color-theory
description: Apply color theory with palette building, harmony, psychology, contrast, and accessibility standards.
category: creative-design
---

## Overview

Color is the fastest emotional signal in design — processed before words, before layout, before
meaning. Used well, it guides attention, encodes meaning, and makes brands unforgettable. Used
carelessly, it confuses and excludes. This skill covers color theory fundamentals, palette
construction, psychological and cultural dimensions, and accessibility requirements.

## When to use

- Building a color palette for a brand or product

- Choosing UI colors (actions, states, feedback, data visualization)

- Fixing color contrast and accessibility issues

- Understanding color psychology for marketing or branding

- Reviewing designs for color harmony and consistency

## Core concepts

- - **The HSB mental model.** Hue (which color), Saturation (intensity), Brightness (light/dark).
  Professionals think in HSB: harmonious palettes share saturation/brightness relationships even
  when hues differ.
- - **Harmony structures.** Complementary (opposites — high energy), analogous (neighbors — calm,
  cohesive), triadic (three equidistant — vibrant but balanced), monochromatic (one hue — elegant,
  safe). Pick one structure per palette; don't mix structures.
- - **The 60-30-10 rule.** 60% dominant neutral/background, 30% secondary, 10% accent. The accent is
  precious — spend it on the one thing that matters most (the CTA, the alert).
- - **Color has jobs.** In UI: brand expression, hierarchy (what's important), state
  (success/error/warning/info), and data encoding. Assign each color a job; a color doing three jobs
  is doing none well.
- - **Psychology is contextual.** Blue = trust (finance, tech), red = urgency (sales, errors), green
  = go/success — but culture and context modulate everything (red means luck in China, mourning in
  parts of Africa). Know your audience.
- - **Accessibility is math.** WCAG: 4.5:1 contrast for normal text, 3:1 for large text and UI
  components. Never encode meaning in color alone — pair with icons, labels, or patterns (8% of men
  have color vision deficiency).

## Practical workflow

1. 1. **Define color's jobs.** List what color must do: brand recognition, primary actions, feedback
   states, data categories, backgrounds. Each job gets a dedicated color family.
2. 2. **Start with neutrals.** Build the grayscale/ramp first — most of any interface is neutrals. A
   refined neutral scale (with subtle warmth or coolness) elevates the whole design.
3. 3. **Choose the primary.** The brand/action color: distinctive in the competitive landscape,
   works at large and small sizes, passes contrast on its backgrounds. Test it as a button, a link,
   and a background.
4. 4. **Build the supporting palette.** Secondary colors, semantic colors
   (success/warning/error/info — test these for CVD distinguishability), and data visualization
   palette (categorical: distinct hues; sequential: single-hue lightness steps).
5. 5. **Check contrast systematically.** Every text/background and UI/background combination against
   WCAG ratios. Fix failures by adjusting lightness, not by hoping.
6. 6. **Test in context.** View the palette applied to real screens, in light and dark mode, and
   through color-blindness simulators (deuteranopia, protanopia, tritanopia). Print a swatch sheet —
   screens lie.
7. 7. **Document with values.** Hex, RGB, and HSL/HSB for each color; usage rules (when to use
   which); don'ts. Name semantically for UI (surface, action, critical) so the palette survives
   rebrands.

## Common pitfalls

- - **Rainbow interfaces.** Too many saturated colors competing. Restraint reads as premium; rainbow
  reads as carnival.
- - **Pure black and pure white.** #000 on #FFF causes halation and eye strain. Use off-blacks
  (#111-#1a1a1a) and let backgrounds breathe.
- - **Color-only meaning.** Red/green status dots with no labels exclude color-blind users. Always
  add a second channel: icon, text, or pattern.
- - **Inaccessible text.** Light gray body text on white — the most common accessibility failure on
  the web. Check every combination, not just the obvious ones.
- - **Gradients as a crutch.** Gradient backgrounds hiding weak composition or low-contrast text.
  Gradients are fine as accents; they're not a substitute for hierarchy.
- - **Ignoring dark mode.** Designing only for light and letting dark mode be an afterthought
  produces muddy, low-contrast dark themes. Design both deliberately from the token level.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698431 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →