<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ui on Vibe Coding</title><link>https://vibecoding.rest/tags/ui/</link><description>Recent content in Ui on Vibe Coding</description><generator>Hugo</generator><language>en</language><atom:link href="https://vibecoding.rest/tags/ui/index.xml" rel="self" type="application/rss+xml"/><item><title>Canvas Design</title><link>https://vibecoding.rest/skills/canvas-design/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/skills/canvas-design/</guid><description>&lt;p&gt;The Canvas Design skill packages visual design judgment: spacing systems, typographic hierarchy, color restraint, and layout composition — the kind of taste that&amp;rsquo;s easy to describe but hard to consistently apply prompt by prompt.&lt;/p&gt;</description></item><item><title>v0</title><link>https://vibecoding.rest/tools/v0/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/tools/v0/</guid><description>&lt;p&gt;v0 generates production-ready frontend code from a prompt, a rough sketch, or a screenshot. It leans on Tailwind CSS and shadcn/ui, so the output looks polished by default and drops straight into a Next.js project.&lt;/p&gt;</description></item><item><title>Frontend Design</title><link>https://vibecoding.rest/skills/frontend-design/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/skills/frontend-design/</guid><description>&lt;p&gt;The Frontend Design skill packages a design-lead mindset for building web UI: pin down the subject and its audience, build a compact token system — palette, type pairing, layout concept, one signature element — then critique that plan against known AI-generic defaults before writing any code.&lt;/p&gt;</description></item><item><title>Figma</title><link>https://vibecoding.rest/mcp-servers/figma/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/mcp-servers/figma/</guid><description>&lt;p&gt;Figma&amp;rsquo;s Dev Mode MCP server exposes a selected frame or component&amp;rsquo;s structure, styles, and metadata directly to a coding agent, from either the Figma desktop app or a hosted endpoint. It lets an agent generate frontend code grounded in the real design file instead of a screenshot or description of it.&lt;/p&gt;</description></item><item><title>shadcn/ui Skill</title><link>https://vibecoding.rest/skills/shadcn-ui-skill/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/skills/shadcn-ui-skill/</guid><description>&lt;p&gt;The shadcn/ui skill gives Claude Code direct context on shadcn/ui&amp;rsquo;s components and enforces consistent usage patterns across a project.&lt;/p&gt;&#10;&lt;h2 id="why-a-skill-for-this"&gt;Why a skill for this&lt;/h2&gt;&#10;&lt;p&gt;shadcn/ui ships as copyable component source rather than an installed package, so consistency depends on the model actually knowing each component&amp;rsquo;s intended API. A skill scoped to shadcn/ui keeps generated UI code matching the library&amp;rsquo;s real patterns instead of guessing.&lt;/p&gt;</description></item><item><title>anydesign</title><link>https://vibecoding.rest/skills/anydesign/</link><pubDate>Mon, 01 Jan 0001 00:00:00 +0000</pubDate><guid>https://vibecoding.rest/skills/anydesign/</guid><description>&lt;p&gt;anydesign analyzes any image, URL, or Figma file and produces a structured design.md capturing the full design system and component inventory, portable to other AI builders.&lt;/p&gt;&#10;&lt;h2 id="why-a-skill-for-this"&gt;Why a skill for this&lt;/h2&gt;&#10;&lt;p&gt;Design systems usually live implicitly in a Figma file or an existing site rather than as a portable spec. Extracting that into a structured document means the design system can travel with the project instead of staying locked in one tool.&lt;/p&gt;</description></item></channel></rss>