UI & UX Design

Verified against ChatGPT · 2026-08-10

Review a mobile UI screen for one-handed thumb reach before it ships

Reviews 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)4 fillable variables

The prompt

Ready to copy — highlighted parts are example details you can swap.

Review this mobile screen specifically for one-handed thumb use. Most mobile UX reviews default to generic "mobile-friendliness" commentary about font sizes and tap targets; I need something narrower and more useful: where does this layout actively fight a user holding the phone in one hand and reaching with their thumb.

SCREEN LAYOUT
Top nav bar with back arrow and settings icon. Middle: scrolling list of saved cards. Bottom-right floating '+ Add card' button. Delete icon appears top-left on swipe.

DEVICE SIZES IN SCOPE
iPhone SE (smallest) through iPhone 15 Pro Max (largest).

PRIMARY ACTION ON THIS SCREEN
Add a new saved payment card.

EXPECTED USE CONTEXT
Standing in a checkout line, phone in one hand, other hand holding groceries.

PHASE 1 — MAP THE SCREEN TO REACH ZONES
Divide the screen into natural, stretch, and unreachable zones for a right-handed thumb on the smallest device size in scope, then note whether the same map holds or shifts for the largest device size. Place every interactive element mentioned in the layout into one of these zones.

PHASE 2 — FLAG REACH CONFLICTS
Identify every case where the primary action sits in a stretch or unreachable zone, and every case where a destructive or hard-to-undo action (delete, remove, cancel-subscription) sits in the natural zone where an accidental thumb tap is most likely. These two conflicts matter more than any other mobile issue on this screen — surface them first.

PHASE 3 — SECONDARY MOBILE ISSUES
Only after phase 2, note anything else mobile-specific worth flagging (tap target sizing below the ~44px comfortable minimum, elements too close together for a thumb to hit reliably). Do not restate desktop-style critique here.

WHAT NOT TO DO
Do not produce a generic mobile checklist unrelated to thumb reach. Do not assume left-handed use unless told to — state clearly that the reach map assumes right-handed use and that a left-handed user mirrors it.

OUTPUT FORMAT
A short reach-zone map (natural / stretch / unreachable, with elements listed under each), then a numbered list of reach conflicts in priority order, then a short secondary-issues list. End with one line stating what would change if you also had to design for left-handed use.

Customize

Optional — swap in your own details for the highlighted parts above.

Why this works

GPT-5.1, asked for a generic "mobile UX review," defaults to a well-worn list of font-size and tap-target advice because that's the most statistically common completion for the phrase "mobile UX" in its training distribution — it's not wrong, but it's also not specific to the actual failure mode of one-handed use, which is about geometric reach, not element size alone. Forcing an explicit reach-zone map before any critique changes the reasoning order: the model has to first commit to a spatial model of where a thumb can and can't comfortably go on the smallest device in scope, and only then evaluate the given layout against that model, which produces genuinely spatial reasoning instead of a recycled checklist. Prioritizing the two specific reach conflicts — primary action out of reach, destructive action in easy reach — matters because these are the two mobile ergonomics failures with the highest real-world cost (a stretch-zone primary action increases task abandonment and one-handed drop errors, while an easy-reach destructive action increases accidental-tap incidents) and a model given an open-ended "what's wrong" prompt will often bury these under less consequential spacing notes. Explicitly stating the right-handed assumption and offering the left-handed mirror as a one-line addendum rather than silently picking one handedness matters because roughly a tenth of users are left-handed and a review that quietly assumes right-handed use without saying so produces recommendations that are wrong for those users without anyone noticing the review made that assumption at all.

What you get back

Reach zones (right-handed, iPhone SE): Natural — bottom third of screen, floating '+ Add card' button. Stretch — middle list area. Unreachable — top nav bar, both icons. Reach conflict #1: the swipe-to-delete icon appears in the natural zone on the left edge of a list row, meaning an accidental one-handed swipe during scrolling could trigger a destructive action; add a confirmation step or move delete behind an explicit menu instead of a swipe gesture.

Verified against

ChatGPT GPT-5.1 · 2026-08-10

Changelog

  • 2026-08-10 Initial publish, verified against ChatGPT GPT-5.1.

Need this built into your business?

If a prompt isn't enough — branding & design, built and maintained for you — that's Scult's day job.

EXPLORE BRANDING & DESIGN
All UI & UX Design prompts

Check your AI visibility

One URL in, a 0–100 score and the exact fixes out.

RUN THE CHECK

Browse all the tools

15 tools across six categories
13 of them never send your data anywhere

Free · No signup · No trial clock

SEE THE DIRECTORY