ux-review
Skill0 starsChanged 13 days agoMITView on GitHub
Review a flow, screen, or piece of product copy from the user's point of view. Checks orientation, next steps, friction, error recovery, and leaked internal details, then rewrites the copy in plain words. Use when the user asks to improve UX, review a flow, simplify onboarding, write button or error copy, reduce friction, or asks "is this confusing".
23 other projects use a version of this.
Adopted by
Most recently taken up by
- WilliamEbong/CourseForgetheir own version, first seen Nov 8, 2026
- striderZA/OpenCodeGameStudiostheir own version, first seen Nov 4, 2026
- ngmeyer/skillstheir own version, first seen Nov 1, 2026
- bookchaowalit/platform-agent-skillstheir own version, first seen Oct 20, 2026
- Donchitos/Claude-Code-Game-Studiostheir own version, first seen Oct 19, 2026
- venus2099/codex-game-studiostheir own version, first seen Oct 17, 2026
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 23
- Donchitos/Claude-Code-Game-Studios★ 27ksame name
- gitkraken/vscode-gitlens★ 10ksame name
- striderZA/OpenCodeGameStudios★ 118same name
- cenconq25/claude-code-app-studio★ 40same name
- brianwestphal/glassbox★ 34same name
- parhamb/design-skills★ 21same name
- dawn840705/codex-code-studios★ 17same name
- lilangMax/ClaudeCodeGameStudios★ 8same name
- RoleModel/skills★ 7same name
- hongyuanc/codex-game-studios★ 5same name
13 more not listed
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.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 3 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 21 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Write four short lines before you judge anything:
- Very specific: line 20
Read the real code or open the real page (use verify-ui if you can run it).
- Distinctive: line 25
Do internal details leak? (model names, vendor names, error codes, "Initializing...", "Calling API...")
- Distinctive: line 35
Remove confirmation dialogs for small actions that are easy to undo.
“Common” is measured: kept by at least 6 in 10 of the 21 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
UX review
Core idea: users care about outcomes, not how the system works. Before each label, message, or step, ask: "Is this for the user, or for the engineer?"
1. Frame it
Write four short lines before you judge anything:
- Who: the user and what they already know.
- Job: the one thing they came to do now.
- Where: entry, decision, waiting, success, error, or exit.
- Fear: what could worry them (losing data, cost, a mistake they cannot undo, looking foolish).
2. Walk the flow
Read the real code or open the real page (use verify-ui if you can run it). For each step check:
- Can they tell where they are?
- Can they tell what to do next? Is there one clear main action?
- Does each piece of text help the job?
- Do internal details leak? (model names, vendor names, error codes, "Initializing...", "Calling API...")
- On error, do they know what happened and what to do?
- Is the app asking for effort too early? (account or card before any value, a choice they cannot judge yet)
3. Fix the copy
- Buttons: verb + object. "Save draft", "Send invite". Not "Submit", "Proceed", "OK".
- Status: "Saving..." then "Saved". Name the outcome, not the process: "Getting your results", not "Fetching data".
- Errors: what happened in plain words, then what to do. "We could not save your file. Check your connection and try again."
- Empty states: what will appear here, and one action to start.
- Remove confirmation dialogs for small actions that are easy to undo.
4. Report
List problems by how much they hurt the job (worst first): the step, the problem, the fix, and the new copy. Keep each fix small enough to ship on its own. Do not redesign the whole flow unless the user asks.
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.