Design System Component Specification
Specifies a reusable design-system component covering anatomy, variants, states, tokens, behavior, and accessibility.
Prompt
ROLE: You are a design systems architect who writes component specs that designers and engineers implement identically. CONTEXT: We are adding the component [COMPONENT_NAME] to the [DESIGN_SYSTEM_NAME] system. It will be used for [USE_CASES]. Existing tokens/foundations: [TOKENS_AND_FOUNDATIONS]. Platforms: [PLATFORMS]. TASK: Write a complete component specification. 1. Define the component's purpose and when to use it vs. when NOT to (point to alternatives). 2. Describe anatomy (named parts) and required vs. optional slots. 3. Enumerate variants (type, size, emphasis) and all interaction states (default, hover, focus, active, disabled, loading, error). 4. Map every visual property to a design token (color, spacing, radius, type) — no hard-coded values. 5. Specify behavior: keyboard interaction, focus order, and responsive/truncation rules. 6. Define accessibility requirements (roles, names, ARIA, contrast, target size). 7. Provide do/don't usage examples. OUTPUT FORMAT: Structured spec sections (Purpose | Anatomy | Variants | States | Tokens table | Behavior | Accessibility | Do/Don't), plus a props/API table for engineering. CONSTRAINTS: Every visual value references a token, not a raw number. Cover all interaction states. Accessibility is mandatory, not optional. Keep the API minimal and composable — avoid one-off props.
How to use this prompt
- 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
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
Run it, then refine. Ask the model to critique and improve its own answer with self-critique prompting.
Techniques in this prompt
Assigns the model an expert persona so it adopts the right vocabulary, depth, and standards for the task.
Learn this techniquePins the response to a defined structure so it drops straight into your workflow.
Learn this techniqueForces explicit intermediate reasoning instead of jumping to a conclusion, which improves accuracy on hard tasks.
Learn this techniqueRecommended models
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.
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.
User Persona From Research Signals
Synthesizes raw research signals into one evidence-backed persona with goals, pains, behaviors, and design implications.
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.
Onboarding Flow Designer For Activation
Designs a first-run onboarding flow that drives users to the activation moment fast while minimizing drop-off.