UX & Product Design5.0 · 0 ratings

Design Tokens And Theming Foundation

Defines a scalable design-token architecture spanning primitives, semantic aliases, and theming for light/dark and brands.

Role-BasedStructured-OutputStep-by-Step

Prompt

ROLE: You are a design systems engineer who architects token systems that scale across themes and platforms.

CONTEXT: We are formalizing design tokens for [PRODUCT/SYSTEM]. Themes required: [THEMES] (e.g., light, dark, high-contrast). Brands/sub-brands: [BRANDS]. Platforms consuming tokens: [PLATFORMS]. Current ad-hoc values: [CURRENT_STATE].

TASK: Design the token architecture.
1. Define a three-tier model: primitive tokens (raw values), semantic tokens (purpose-named aliases), and component tokens (where justified).
2. Establish naming conventions (category-property-variant-state) and show examples for color, spacing, typography, radius, elevation, and motion.
3. Map how semantic tokens re-point per theme (light/dark/high-contrast) without changing component code.
4. Handle brand theming via the alias layer; specify what is shared vs. overridden.
5. Define contrast and accessibility rules tokens must satisfy.
6. Specify the source of truth, distribution format, and a deprecation/versioning policy.

OUTPUT FORMAT: A tier diagram (primitives -> semantic -> component), a naming-convention spec with examples, a per-theme alias table for key tokens, and a governance/versioning note.

CONSTRAINTS: Components reference semantic tokens, never primitives directly. Theming must work by re-pointing aliases, not editing components. Every color pairing must pass contrast. Keep the token set as small as possible while covering needs. Avoid one-off component tokens unless justified.

How to use this prompt

  1. 1

    Copy the prompt above and paste it into ChatGPT, Claude, or Gemini — or open it in the visual Studio to edit each part on a canvas and run it with your own key.

  2. 2

    Replace any bracketed placeholders with your specifics. The more concrete your context and constraints, the sharper the result — see the 5-part prompt structure.

  3. 3

    Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.

Techniques in this prompt

Role-Based

Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.

Learn this technique
Structured Output

Pins the response to a defined structure so it drops straight into your workflow.

Learn this technique
Step-by-Step

Forces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.

Learn this technique

Recommended models

claudegpt-4ogemini

Build on this prompt

Open it in the visual Studio to wire it into a full workflow with your own API key — or learn the craft behind prompts like this.

Open in Studio How to prompt AI correctly

More in UX & Product Design

Heuristic Evaluation Of A UI Screen

Runs a Nielsen-style heuristic evaluation of a screen, scoring each issue by severity and proposing concrete fixes.

Read prompt

User Persona From Research Signals

Synthesizes raw research signals into one evidence-backed persona with goals, pains, behaviors, and design implications.

Read prompt

User Journey Map With Emotion Curve

Produces a stage-by-stage journey map covering actions, thoughts, emotions, pain points, and opportunities for a target scenario.

Read prompt

Onboarding Flow Designer For Activation

Designs a first-run onboarding flow that drives users to the activation moment fast while minimizing drop-off.

Read prompt