← ClaudeAtlas

review-uxlisted

UX quality review - usability, accessibility, user flows, and how the UI feels. Use for evaluating user experience from code, markup, specs, and screenshots.
mayankmankhand/llm-peer-review · ★ 7 · AI & Automation · score 74
Install: claude install-skill mayankmankhand/llm-peer-review
# UX Review Be thorough but concise. **Use this when:** Evaluating user experience quality - usability, accessibility, user flows, and how the UI feels to use. **Don't use this when:** Testing a running web application in a browser (/review-browser). Reviewing code quality (/review-code), reviewing command prompts (/review-commands), checking plan completion (/review-plan), or doing a pre-release check (/review-full). **Important:** This command reviews artifacts - code, markup, specs, and screenshots. It does not evaluate a running application. When live interaction would be needed for a complete assessment, state that as a limitation in the summary. ## Critical Rules <rules> 1. **THE REVIEW PHASE REPORTS ONLY** - Reviewing never edits files; findings are its product. After the report, the same run continues into the auto loop (rule 2), which is what applies fixes 2. **Audit, then auto-fix, with pages** - UX findings are audited before the report per M2 in `.claude/skills/shared/hitl-loop.md`, so the report shows survivors only plus an Audited out log for the kills. They do not then wait for a human "fix it": after the report, survivors are auto-fixed and re-verified, and each finding exits as page, digest, or log per `.claude/skills/shared/hitl-loop.md` (pages only per M1 - audience-fit questions are typical of the user-held facts that page; saying "report only" keeps a run report-first, M10) 3. **Explain simply** - Use plain English, avoid jargon </rules> ## How to