Skip to main content
prompt GP ChatGPT

Design System taste — ChatGPT prompt: what it does, how to install

Design System taste — a prompt for ChatGPT that enforces pragmatic design system standards, tokens, accessibility, and component architecture.

CC0-1.0 ★ 178,201 updated 2026-10-24

Open on GitHub

What Design System taste does

This system prompt defines the mindset of a pragmatic design systems engineer to generate design tokens, components, and architecture guidelines. The instructions cover semantic tokens for color, spacing, typography, and motion, light and dark theme switching, WCAG 2.2 AA contrast compliance, and building on headless primitives like Radix UI or React Aria. It also regulates visual regression testing, semantic versioning, and keeping Figma in sync with code.

The prompt runs in ChatGPT, Claude.ai, and Claude Code. To install in Claude Code, place the file at .claude/commands/prompts.csv.md. The guidelines require naming tokens by purpose rather than raw values and keeping component APIs compact with minimal boolean props.

What it helps with

  • define design tokens for color and spacing
  • support light and dark themes via semantic tokens
  • meet WCAG 2.2 AA contrast requirements
  • document components in Storybook with usage examples

Example prompts for the agent

  • Apply the Design System taste prompt to generate semantic design tokens
  • Review component architecture using the Design System taste guidelines
  • Set up accessibility checks based on the Design System taste standards

How to install Design System taste

How to use

Paste the text at the start of a chat or into project instructions

Questions about Design System taste

How to install Design System taste in Claude Code?

Copy the command file to .claude/commands/prompts.csv.md in your project root.

What does Design System taste do?

It acts as a system prompt providing rules for designing UI tokens, building accessible React components, and organizing testing workflows.

What standards are enforced by the prompt?

The instructions mandate WCAG 2.2 AA contrast compliance, headless UI primitives, and strict component deprecation policies.

Source text

prompts.csv · CC0-1.0
# Design System taste of a pragmatic design systems engineer
- Define design tokens for color, spacing, typography, radius and motion in one source file, and generate CSS variables and platform outputs from it. Confidence: 0.90
- Name tokens by purpose, such as color-text-muted or space-inset-md, not by raw value like gray-500 or 16px. Confidence: 0.85
- Support light and dark themes by swapping semantic token values, never by overriding individual component styles. Confidence: 0.90
- Build components on accessible headless primitives such as Radix UI or React Aria instead of re-implementing focus and keyboard logic. Confidence: 0.85
- Meet WCAG 2.2 AA contrast for every token pairing and check it automatically when tokens change. Confidence: 0.90
- Keep the component API small: a few well-named variants and sizes beat dozens of boolean props. Confidence: 0.85
- Prefer composition with slots or children over configuration objects for complex components like dialogs and menus. Confidence: 0.80
- Forward refs and spread remaining props onto the root element so components work with forms, tooltips and tests. Confidence: 0.85
- Never hard-code colors, spacing or font sizes inside components; lint for raw values with Stylelint or an ESLint rule. Confidence: 0.85
- Document every component in Storybook with usage guidance, do and don't examples, and live controls. Confidence: 0.85
- Run visual regression tests with Chromatic or Playwright screenshots on every pull request. Confidence: 0.80
- Run automated accessibility checks with axe in component tests, and still test keyboard and screen reader flows by hand before release. Confidence: 0.85
- Publish the library as a versioned package with semantic versioning and a changelog generated by Changesets. Confidence: 0.90
- Treat a renamed prop or removed variant as a breaking change, and ship codemods for large migrations. Confidence: 0.75
- Deprecate before removing: mark the old API, log a development-only warning, and remove it in the next major version. Confidence: 0.85
- Ship ESM with tree-shakeable per-component entry points and mark CSS files as side effects correctly. Confidence: 0.80
- Respect prefers-reduced-motion and keep motion tokens short and purposeful. Confidence: 0.80
- Keep icons as a separate package of optimized SVG components with consistent size and stroke tokens. Confidence: 0.75
- Use logical CSS properties like margin-inline-start so components work in right-to-left layouts. Confidence: 0.75
- Keep Figma components and code components in sync by sharing token names and reviewing drift every release. Confidence: 0.70
- Measure adoption by scanning product repositories for library imports and one-off overrides. Confidence: 0.65
- Accept contributions through a short proposal template that covers the use case, API and accessibility before any code. Confidence: 0.70

© f · CC0-1.0 · f/prompts.chat

Similar prompts

All prompts for Design →

From the same set218

The whole set →
Load Testing taste The Load Testing taste prompt for ChatGPT sets performance testing standards and reliability engineering principles. It is applied when designing load test scenarios and analyzing backend capacity. GP ChatGPT ★ 178,201repo stars Neovim Config taste The Neovim Config taste ChatGPT prompt sets out a terminal-first style for building a Neovim configuration in Lua. It covers plugin loading, language tools, formatting, and key bindings. GP ChatGPT ★ 178,201repo stars API Client SDK taste API Client SDK taste — a prompt for ChatGPT that defines developer-experience standards for building API client SDKs. It runs during API architecture design, OpenAPI code generation, and error-handling setup. GP ChatGPT ★ 178,201repo stars dbt Analytics Project taste dbt Analytics Project taste — a prompt for ChatGPT sets conventions for dbt models, tests, documentation, and CI. Use it while shaping an analytics project or revising its model structure. GP ChatGPT ★ 178,201repo stars Unity Game Project taste Unity Game Project taste — a prompt for ChatGPT that sets engineering guidelines for Unity game projects. It covers code structure, assets, testing, and builds. GP ChatGPT ★ 178,201repo stars Ansible Playbook taste Ansible Playbook taste — a prompt for ChatGPT, Claude.ai, and Claude Code setting standards for infrastructure code. It aligns Ansible roles with best practices and ensures task idempotency. GP ChatGPT ★ 178,201repo stars Embedded Firmware taste Embedded Firmware taste — a prompt for ChatGPT that enforces reliability-minded engineering standards for embedded firmware development. GP ChatGPT ★ 178,201repo stars WebAssembly Module taste WebAssembly Module taste — a system prompt for ChatGPT, Claude.ai, and Claude Code that establishes architectural standards for WebAssembly development. It guides developers on performance and safety best practices. GP ChatGPT ★ 178,201repo stars

Project sponsors

Companies that keep this analytics open