What problem does it solve? Reviewing a user interface consistently across accessibility, layout, copy, typography, color, and visual polish is hard to do in one pass, and findings often end up scattered, duplicated, or ranked by taste rather than evidence. This Skill consolidates those domain reviews into a single ranked, evidence-based report. ## Core Features & Use Cases - Cross-domain orchestration: Routes the interface through each better-* domain skill (accessibility, layout, writing, typography, colors, UI) and merges results into one ranked findings table capped at 15 findings. - Evidence-based severity ranking: Applies a shared HIGH/MEDIUM/LOW severity scale with explicit escalation triggers, such as missing accessible names, keyboard traps, contrast failures, and destructive actions without confirmation. - Change-scoped review handoff: Delegates branch, pull request, or uncommitted-change reviews to interface-review, then applies its own severity, ranking, cap, and verdict to introduced and regressed findings. - Use Case: Before shipping a new settings page, ask for an interface review and receive a coverage table per domain, a consolidated findings table with file:line citations and before/after fixes, verification results, and a Block or Approve verdict. ## Quick Start Review the interface of the current screen or flow across accessibility, layout, writing, typography, color, and UI polish, and give me a ranked findings report with a verdict.
