OpenAI

ChatGPT Color Design System Rules

Export a structured ai-color-rules.md file with your brand's 46 semantic color tokens, CSS variables, Tailwind mappings, and WCAG accessibility data — optimized for ChatGPT.

ChatGPT Universal markdown prompt with color tokens for ChatGPT custom instructions
ai-color-rules.md
Select a color to generate AI skill preview

Setup Guide for ChatGPT

Get your AI color rules working in under 2 minutes.

1

Export your skill file

Go to your palette → Export → AI Coding Rules → ChatGPT. Copy the generated markdown.

2

Add to ChatGPT Custom Instructions

Go to ChatGPT Settings → Personalization → Custom Instructions. Paste the color rules into "How would you like ChatGPT to respond?"

3

Prompt for UI code

Ask ChatGPT to generate components. It will reference your color tokens and maintain brand consistency.

Project Structure
ChatGPT Settings
└── Personalization
    └── Custom Instructions
        └── "How would you like ChatGPT to respond?"
            ← Paste color rules here

How ChatGPT Uses Color Design System Rules

When you place a ai-color-rules.md file in your project, ChatGPT reads it as part of its context window. This means every code suggestion, component generation, and refactoring task references your exact color tokens instead of guessing.

The exported file includes all 46 semantic color roles (brand, surface, text, status, border), their hex/RGB/HSL values, CSS custom properties, Tailwind class mappings, and WCAG contrast ratios. ChatGPT uses this data to:

  • Generate React/Vue/Svelte components with correct color tokens
  • Suggest accessible color pairs that meet WCAG AA/AAA standards
  • Apply consistent theming across light and dark modes
  • Write CSS/Tailwind code using your design system variables
  • Maintain visual consistency across your entire codebase

Export Your ChatGPT Color Rules Now

Create your brand palette, then export AI coding rules from the Export tab. ChatGPT will produce on-brand code from day one.