Keyboard & Focus Spec — Design System
Specify complete keyboard interaction for a component/flow. Purpose-built for design system contexts.
A structured designer prompt for accessibility & inclusive design: specify complete keyboard interaction for a component/flow, tailored to a component library serving many teams and products. It walks the model through a proven process with an explicit quality bar, and delivers a keyboard spec.
The prompt
Variables to fill in: {{product_area}}{{current_state}}
You are an accessibility specialist who makes products work for everyone without making them worse for anyone. I need your help in the context of a component library serving many teams and products.
TASK: Specify complete keyboard interaction for a component/flow.
DELIVERABLE: Produce a keyboard spec: tab order, key bindings per component state, focus indication requirements, the focus-management rules for dynamic content, and the trap/skip checks.
PROCESS:
1. Review the inputs below. If anything critical is missing or ambiguous, ask me up to three clarifying questions before producing the deliverable.
2. Assess against concrete success criteria (WCAG 2.2 AA as baseline) — 'looks accessible' is not a finding.
3. Prioritize by user impact: blockers for entire groups before polish items.
4. Fix at the pattern level: one corrected component beats a hundred patched instances.
5. Produce the deliverable in a clean, skimmable format I can use directly.
QUALITY BAR:
- Findings cite the specific criterion and the affected user group.
- Fixes are specified for design AND implementation handoff.
- Recommendations improve usability for everyone, not just compliance checkboxes.
INPUTS:
- The screens/flows/components in scope, described or specced: {{product_area}}
- What's known: existing audits, complaints, or compliance requirements: {{current_state}}Try it out
Open in Playground →Run this prompt on a real model without leaving the page. Every run is saved to your history for this prompt.
Fill in the variables
How to use
- 1Fill in the {{product_area}}, {{current_state}} variables with your real details — specifics in, specifics out.
- 2Paste the prompt into ChatGPT, Claude, Gemini, or any capable model.
- 3Answer the clarifying questions it asks; that step is what makes the output fit your situation.
- 4Iterate on the deliverable: ask for alternatives, tighter versions, or a different angle on any section.
Pro tips
- If the output feels generic, add more concrete detail to the inputs — names, numbers, and constraints sharpen everything.
- Works well in a thread: keep the conversation going to refine a keyboard spec.