Reviews layout density, theme adherence, typography, spacing, search-chrome placement, accessibility modes, and visual consistency. Use during visual layout or CSS adjustments.
85%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Use this skill when auditing UI styling, colors, layout structures, spacing rules, and
search-chrome placement. For a full live page sweep (routes, breakpoints, interactive
behaviour), prefer the Cursor agent at .cursor/agents/design-review.md — this skill is the
compact checklist; that agent owns the journey protocol.
Follow AGENTS.md review throttling and docs/codex-review-protocol.md before starting. Do not review opportunistically or mutate files during pure review. After a completed PR review, post one Review record comment on the PR (see Records); never edit the frozen docs/branch-review-ledger.md table.
Read docs/search-chrome-behaviour.md and docs/wiring-conventions.md before judging search chrome or controls. Run npm run ensure before browser work; confirm /api/local-project-id matches this project. Do not call OpenAI, Supabase, GitHub/hosted CI, or provider-backed gates without explicit approval.
# Search chrome behaviour.0rem content reserve.npm run ensure and capture screenshots at phone (~390) and desktop (~1280).BigSimmo/PsychSift
0d5a97a
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.