26 free prompts · all verified
UI & UX Design prompts
Tool-agnostic UI/UX prompts — wireframe briefs, design-system audits, UX-research plans, usability-test scripts — the thinking layer above any specific design tool.
Every prompt lists the exact tool and version it was tested against.
Run a UX audit that ties every flagged issue to a specific funnel drop-off, not a generic heuristics checklistTurns a page-by-page walkthrough of your signup or checkout flow into a prioritized list of UX issues, each one tied to where users actually abandon rather than a generic Nielsen-heuristics scorecard.ChatGPT (GPT-5.1)2026-08-08Get a screenshot critique that separates 'will confuse users' from 'I just don't like it' before a design goes to devCritiques a single UI screenshot against the interaction it's meant to support, sorting findings into what will actually cause user confusion versus aesthetic preference, so dev handoff isn't delayed over subjective taste.ChatGPT (GPT-5.1)2026-08-09Review a mobile UI screen for one-handed thumb reach before it shipsReviews a mobile screen specifically for one-handed, thumb-driven use — flagging any primary action placed outside comfortable reach on common phone sizes rather than a generic mobile-friendliness pass.ChatGPT (GPT-5.1)2026-08-10Turn a WCAG pass into a severity-ranked fix list engineers will actually act onReviews a screen or component against WCAG success criteria and outputs a severity-ranked list of concrete fixes rather than an undifferentiated wall of citations, so accessibility work gets triaged like any other bug backlog.ChatGPT (GPT-5.1)2026-08-11Wireframe a landing page section-by-section, anchored to the one action you want at each scroll depthProduces a text-based wireframe of a landing page, section by section, where every block is justified by the one visitor decision it's meant to move — not a generic hero-features-testimonials-footer template filled in with your product name.ChatGPT (GPT-5.1)2026-08-08Wireframe a dashboard around the three-second glance test, not a grid of equal-weight widgetsDesigns a dashboard's information hierarchy around the single question a user opens it to answer, ranking every widget by whether it earns a place in the first glance, a quick scan, or a click-through.ChatGPT (GPT-5.1)2026-08-09Map a mobile app flow that accounts for the exits and error branches, not just the happy pathMaps out a mobile app user flow as a full branching diagram in text, forcing every error state, permission denial, and abandonment point to be an explicit named screen instead of an implied dead end.ChatGPT (GPT-5.1)2026-08-10Build a user persona from actual research notes instead of inventing demographics that don't affect design decisionsSynthesizes raw interview or survey notes into a lean persona that only includes traits shown to actually change a design decision, rather than a padded demographic template with an invented name, age, and stock photo.ChatGPT (GPT-5.1)2026-08-11Write a Jobs-to-be-Done interview script that surfaces the real switching trigger without leading the witnessWrites a JTBD-style user interview script focused on the specific moment someone decided to switch tools, phrased to avoid leading questions that would just confirm what you already assume.ChatGPT (GPT-5.1)2026-08-12Write user stories that pass the INVEST test instead of restating a feature as a storyRewrites a feature idea into properly scoped user stories that pass the INVEST criteria (independent, negotiable, valuable, estimable, small, testable), flagging any that are actually too large or too vague to be one story.ChatGPT (GPT-5.1)2026-08-12Write acceptance criteria that cover the edge cases a developer will otherwise guess atWrites Given/When/Then acceptance criteria for a user story that explicitly cover boundary and error conditions, instead of only the one happy-path scenario most acceptance criteria stop at.ChatGPT (GPT-5.1)2026-08-13Synthesize raw usability-test notes into themes ranked by how many participants actually hit each oneSynthesizes raw usability-test or interview notes into an affinity-mapped set of themes, each one weighted by how many distinct participants actually surfaced it, rather than a list of interesting quotes presented as if equally representative.ChatGPT (GPT-5.1)2026-08-13Write an unmoderated usability test script that catches silent confusion, not just task completionWrites an unmoderated usability-test script with task prompts and follow-up questions designed to surface confusion a participant powered through silently, since an unmoderated test has no facilitator there to notice a hesitation live.ChatGPT (GPT-5.1)2026-08-14Write microcopy for one flow's buttons, empty states, and confirmations as a single consistent voiceWrites all the microcopy for one flow at once — buttons, empty states, confirmations, and tooltips — as a single consistent voice pass, catching inconsistencies that appear when each string is written in isolation.ChatGPT (GPT-5.1)2026-08-14Rewrite a wall of raw error messages into ones a non-technical user can actually act onRewrites a list of raw, developer-facing error strings into user-facing messages that state what happened, why, and the one thing to do next, without inventing a cause the system doesn't actually report.ChatGPT (GPT-5.1)2026-08-14Design every empty state a dashboard can hit so 'no data yet' never reads like a bugProduces copy, layout, and a next-action for each distinct empty state a product screen can show — first-use, filtered-to-zero, and error — so users never mistake an empty screen for a broken one.ChatGPT (GPT-5.1)2026-08-08Map a first-session onboarding flow around the one action that actually predicts retentionBuilds a step-by-step onboarding sequence anchored to a single activation milestone, cutting every step that doesn't move a new user toward it — with a named fallback for users who stall.ChatGPT (GPT-5.1)2026-08-08Audit a checkout flow step by step for the exact point shoppers are abandoning atWalks a real checkout flow screen by screen against known drop-off data to identify which specific step is causing abandonment and what to change there first, instead of a generic best-practices checklist.ChatGPT (GPT-5.1)2026-08-09Rework a product's navigation before it collapses under its own feature countRedesigns the top-level navigation structure for a product that has outgrown its original nav, deciding what earns a primary slot versus what moves into a secondary or contextual location.ChatGPT (GPT-5.1)2026-08-09Turn a messy content inventory into a sitemap organized around what users actually search forTakes a raw list of existing pages or sections and restructures them into a sitemap grounded in real user search terms and tasks, flagging orphaned or duplicate content along the way.ChatGPT (GPT-5.1)2026-08-10Force a real feature-prioritization call instead of a roadmap where everything is 'high priority'Scores a list of candidate features against effort, impact, and confidence, and produces a ranked shortlist with the trade-offs stated plainly — built to stop a roadmap conversation from ending in a tie.ChatGPT (GPT-5.1)2026-08-10Write a design handoff spec that survives contact with an engineer who wasn't in the design reviewsConverts a finished design into a developer-ready spec covering states, spacing, responsive behavior, and edge cases explicitly — the details that get silently skipped when handoff is just a Figma link.ChatGPT (GPT-5.1)2026-08-11Specify what a layout actually does between breakpoints, not just at three fixed screen widthsDocuments responsive behavior across the full width range a layout will actually be viewed at, including the in-between and edge widths a simple mobile/tablet/desktop spec usually leaves undefined.ChatGPT (GPT-5.1)2026-08-11Tear down a competitor's UX for one specific flow, not their whole productCompares your product against named competitors on a single, specific user flow, producing concrete differences that explain a metric gap rather than a broad, unfocused 'what they do better' review.ChatGPT (GPT-5.1)2026-08-12Review a landing page's UX against the one conversion decision it's actually asking a visitor to makeReviews a landing page's layout, copy hierarchy, and CTA placement against a single named conversion goal, flagging every element competing with that one decision instead of a generic visual critique.ChatGPT (GPT-5.1)2026-08-13Build a design QA checklist specific to what actually broke last time, not a generic pixel-perfect checklistProduces a targeted visual and interaction QA checklist for a specific release, weighted toward the components most likely to regress based on what actually changed and what has broken before.ChatGPT (GPT-5.1)2026-08-14
