ux-ui-review
Skill0 starsChanged 15 days agoMITView on GitHub
Review and fix the UX and UI of every screen like a demanding designer - 375px and desktop, empty/loading/error states, copy, hierarchy, spacing, contrast, touch targets, keyboard and focus, consistency - with screenshots as evidence and fixes applied, not just listed. Use during /ship after a flow is built, before QA, or whenever asked to make something look and feel good. Pairs with the ui-ux-pro-max skill for style and palette choices.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- ishandutta2007/Awesome-Claude-Skillstheir own version, first seen Nov 8, 2026
- igorpdsantos/ux-ui-reviewtheir own version, first seen Oct 20, 2026
- 95gabor/agentic-workflowtheir own version, first seen Jul 24, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- ishandutta2007/Awesome-Claude-Skills★ 16same name
- 95gabor/agentic-workflow★ 1same name
- igorpdsantos/ux-ui-review★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- hireSkill
- learnSkill
- owner-actionsSkill
- portfolioSkill
- production-readySkill
- product-specSkill
- qa-flowsSkill
- release-gatesSkill
- run-companySkill
- shipSkill
- workspaceSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 27
Dark mode: if the product offers it: both themes checked.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
UX/UI review
You are the designer and you also ship the fix. Every finding is either fixed now or a READINESS row with a screenshot. No "consider improving" lists.
Procedure per screen
- Open the real screen (dev server or production) in the browser at 375 x 812 and at 1440 wide. Screenshot both to
qa/ux/<screen>-<width>.png. - Walk the checklist below. Fix what you can in the same pass. Re-screenshot after fixing; the "after" image is the evidence.
- Record one READINESS row per unfixed defect (
| U<n> | <screen>: <defect> | <surface> | todo | qa/ux/... | |).
Checklist
- First impression: what the screen is for is obvious in 3 seconds; one primary action per screen; the primary action is visually primary.
- States: empty (helpful, with the next action), loading (skeleton or spinner, no layout jump), error (plain words, what to do next, keeps the user's input), success (confirmation that something happened).
- Copy: short, specific, in the product's language; buttons are verbs ("Save list", not "Submit"); no developer words (null, undefined, error 500, token); honest: no favourites, bestseller, review, count or "loved by" claims until real data supports them.
- Layout: nothing overflows or is clipped at 375px; no horizontal scroll; consistent spacing scale; aligned edges; sensible max width on desktop.
- Forms: labels (not placeholders only), inline validation, visible focus, Enter submits, errors next to the field, sensible keyboard types on mobile.
- Touch and keyboard: targets at least 44px; Tab order follows reading order; Escape closes overlays; focus returns after modals.
- Accessibility: contrast at least 4.5:1 for text; images have alt text; icons with labels; headings in order;
prefers-reduced-motionrespected. - Consistency: one font pairing, one palette, one button style, one icon set; same component for the same job everywhere.
- Performance feel: first screen usable under 2 seconds on a throttled phone; no blocking fonts; images sized.
- Dark mode if the product offers it: both themes checked.
Tools
- Claude Code: the built-in browser (
mcp__Claude_Browser__*,resize_windowfor 375/desktop), or Chrome DevTools MCP; iOS simulator for native screens. - Codex: the browser plugin / computer use; the same widths.
- Style decisions (palette, type, component style) come from the ui-ux-pro-max skill when installed; otherwise keep what the product already uses and make it consistent.
- Lighthouse accessibility score (Chrome DevTools
lighthouse_audit) is the gate evidence: at least 90.
Output
Short list in the report: "<screen>: fixed <n>, open <n> (rows U<a>-U<b>)". Screenshots linked from the rows.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.