bundled-skills/ui-review/SKILL.md
Review UI code for design system compliance, accessibility, and best practices
npx skillsauth add FrancoStino/opencode-skills-antigravity ui-reviewInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use this skill when you need review UI code for design system compliance, accessibility, and best practices.
/ss-a11y/ss-audit/ss-lintReview the file: $ARGUMENTS
text-foreground, bg-brand, etc.)p-6 not p-[24px])shadow-[var(--shadow-card)])rounded-md, rounded-lg, rounded-2xl)data-slot attributecn() for className mergingReact.ComponentProps<>className prop overridefocus-visible styles on all interactive elementsaria-* attributes where neededprefers-reduced-motionalt text-webkit-overflow-scrolling: touchleading-none + tracking-[-0.02em]leading-snug + tracking-[-0.01em]leading-normal (no custom tracking)tracking-[0.05em] or tracking-wideline-height: 1.5 on display/heading text (too loose)size-* shorthand instead of w-* h-*ms-*/me-* instead of ml-*/mr-* (logical properties)duration-[var(--duration-fast)])The biggest reason a UI reads as "AI-generated" isn't ugly parts — it's mixed parts. Check that each axis below uses ONE value system-wide; flag a mix as a real issue, not a nitpick.
rounded-none panel with rounded-full buttons).currentColor.inner = outer − padding, not the same radius (which bulges).Provide:
tools
Authorized security assessment of LLM applications and AI agents: prompt injection, tool abuse, RAG exposure, memory poisoning, system-prompt extraction, and agent-compliance engineering per OWASP LLM/ASI Top 10.
development
Builds two parameterized UI modes—流光溢彩白 (iridescent white) and 五彩斑斓黑 (colorful black)—with OKLCH, WebGL/CSS fallback, vision gating, screenshot QA, and total/per-color intensity reports. Use when a UI request names either mode or needs measured color parameters.
tools
Delegate coding tasks to the Kimi Code CLI (`kimi`) only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.
development
Front-end JavaScript reverse engineering: locate signature chains, analyze encrypted request parameters, sample runtime behavior, and reproduce logic locally in Node for evidence-based output.