Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add xushuodasd/VIBE-Claude-Plugin --skill vibe-ui-beautifygit clone --depth 1 https://github.com/xushuodasd/VIBE-Claude-PluginWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/xushuodasd/vibe-claude-plugin/vibe-ui-beautify)<a href="https://agentmods.dev/skills/xushuodasd/vibe-claude-plugin/vibe-ui-beautify"><img src="https://agentmods.dev/badge/skills/xushuodasd/vibe-claude-plugin/vibe-ui-beautify/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/xushuodasd/vibe-claude-plugin/vibe-ui-beautify"><img src="https://agentmods.dev/badge/skills/xushuodasd/vibe-claude-plugin/vibe-ui-beautify.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00074 | $0.07369 |
| Opus 5 | $0.00037 | $0.03684 |
| Sonnet 5 | $0.00015 | $0.01474 |
| Haiku 4.5 | $0.00007 | $0.00737 |
Grade A, and why
vibe-ui-beautify scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 642 lines — stays where its author put it; the contents beside it link to each section on GitHub.
前端美化与动效工作流 (Motion & Polish)
0. 身份强制声明 (Persona Injection)
【警告】当你进入此工作流时,你不再是一个"能用就行"的功能开发者! 你现在的身份是:高级动效设计师 (Motion Designer)。 你的唯一职责是:把 vibe-ui-design 立下的"视觉宪法"中的动效部分变成现实——让每一个按钮、卡片、模态框都有"机械般"的物理反馈,每一次点击都有"果汁感 (Juicy)"的阻尼,让用户指尖愉悦。但你的克制同样重要:禁止满屏乱飞的动画、禁止每次 hover 都触发 1 秒的过渡。动效是调味料,不是主菜。
1. 文档目的
为 VIBE 全自动开发流水线提供"动效注入层"。在 vibe-test 与 vibe-security 通过之后、vibe-api-docs 之前介入,给业务组件加上微交互、过渡动画、3D 视效。基础视觉规范由 vibe-ui-design 定义,本技能专注"如何动起来"。
2. 工作流结构
- 前置步骤:读取
vibe-ui-design的 motion tokens → 识别可动效化的组件 → 选择动效库 - 执行步骤:微交互 → 过渡 → 列表/页面切换 → 3D 视效 → 性能验证
- 熔断机制:连续 3 个动效在低端机测试掉帧 → 标记
[Blocked]跳过 - 输出成果:动效代码 + 性能测试报告 + tasks.md 打勾
3. 核心法则 (The Three Laws of Motion)
🎯 L1 物理直觉:动效要符合现实世界的物理(重力、阻尼、惯性)
🎯 L2 节制美感:动效是调味料,1 秒以上的动画全屏不超过 1 个
🎯 L3 性能底线:必须 60fps,掉帧的动效不如没有动效
反直觉但正确:
- "加更多动画" ≠ "更好看"。一个 200ms 的弹性按钮比满屏粒子特效有用得多
- "动画好看就行" → 但 30fps 的卡顿比静态页面还让人难受
- "用 transition: all" → 性能灾难。永远只 transition transform 和 opacity
4. 动效库选型决策树
需要复杂物理弹簧?
├─ 否 → CSS @keyframes + transition(首选,性能最好)
└─ 是 → React/Vue 框架?
├─ React → framer-motion(首选)/ react-spring
├─ Vue 3 → @vueuse/motion / motion-v
└─ 复杂时间线编排(多元素协调)→ GSAP(最强但最重)
需要 3D / WebGL?
└─ Three.js + React Three Fiber(Vue: TresJS)
只需要简单涟漪/波纹?
└─ 原生 CSS(伪元素 + animation)
首选组合:CSS transition/animation(70%)+ Framer Motion(25%)+ GSAP/Three.js(5% 关键场景)
5. 微交互配方库 (Micro-interaction Recipes)
5.1 按钮按下反馈(最常用,所有 primary 按钮必备)
// Framer Motion 版本
import { motion } from 'framer-motion'
<motion.button
whileHover={{ scale: 1.02, y: -1 }}
whileTap={{ scale: 0.97, y: 1 }}
transition={{ type: 'spring', stiffness: 400, damping: 17 }}
className="bg-brand-500 text-white px-4 py-2 rounded-md"
>
提交
</motion.button>
关键参数解释:
whileHover.scale: 1.02— 轻微放大,不要超过 1.05(变浮夸)whileTap.scale: 0.97— 按下收缩,模拟"被压下去"stiffness: 400, damping: 17— 弹簧硬度+阻尼,类似真实物体
5.2 卡片悬停抬起 + 霓虹光晕
<motion.div
whileHover={{
y: -4,
boxShadow: '0 0 30px rgba(0, 191, 255, 0.3), 0 10px 30px rgba(0,0,0,0.5)',
}}
transition={{ type: 'spring', stiffness: 300, damping: 20 }}
className="bg-bg-surface border border-border-default rounded-lg p-4"
>
{/* 卡片内容 */}
</motion.div>
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 642 lines · 74 tokens per session scan A a4476cd88ef6
vibe-ui-beautify is a skill published in the GitHub repository xushuodasd/VIBE-Claude-Plugin (4 stars, last pushed 2mo ago), licensed MIT. It adds 74 tokens to every session and 7,369 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
frontend-ui-ux
Designer-turned-developer expertise for crafting stunning UI/UX even without design mockups.
frontend-design
Produce intentional, responsive, accessible UI work and perform visual QA instead of generic component assembly.
design-system
Builds and maintains the design system a product is assembled from — tokens for color, type, spacing and elevation, component contracts, and the rules that keep them coherent as the product grows. Use this when starting a new interface, when screens have drifted apart visually, when the same component exists three…
interface-craft
Raises the visual and interaction quality of an interface — layout, hierarchy, type, spacing, density, and the details that separate a considered product from a generic one. Use this when a screen works but looks unfinished or default, when a layout feels crowded or arbitrary, when a page has no clear focal point, or…
interface-redesign
Upgrades an existing interface to a higher standard without rebuilding it — auditing what is there, identifying what reads as generic or unfinished, and sequencing changes by impact. Use this when a product works but looks dated or default, when a redesign is being considered, when deciding whether to restyle or…
design-context-extract
Extract design DNA from app screenshots, live URLs, or screen recordings using Google Stitch — color palettes, typography, spacing tokens, component patterns, and motion specs as design-tokens.json or Tailwind config. Use when the user points to a screenshot, URL, or video and asks to extract or audit the design…