Token导航 LogoToken导航

Agent Skill · 前端设计

ui-ux-polish(用户界面用户体验波兰语)

用于辅助前端页面、组件、样式和交互逻辑的开发与维护。它适合让 Agent 生成或审查 React、Next.js、Vue、Tailwind、CSS 等相关代码,整理组件结构,或定位布局和性能问题。使用时需要结合项目现有设计系统、路由和构建方式,避免只生成孤立片段;涉及页面改动时,应配合本地预览和构建检查确认视觉效果。

ui-ux-polish 是前端设计类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证为 MIT,第三方扫描已通过,按安装量在前端设计类的 10,216 个 Skill 里排第 1,829。

总安装 3,655周安装 157GitHub Stars 63下载 1,281核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:ui-ux-polish(用户界面用户体验波兰语)
来源仓库:https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations
仓库路径:skills/ui-ux-polish
安装命令:
npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill ui-ux-polish
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。不同来源提供的安装方式可能略有差异;本站展示可直接复制的安装命令,安装前请核对来源页面。

skills.shnpx skills
npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_integrations --skill ui-ux-polish

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

用于精细化打磨用户界面细节与交互质感。适合优化微交互动效、视觉层次和文案表达。提供动画曲线、过渡时长和状态反馈建议。需避免过度设计并保持性能开销可控。ui-ux-polish 属于前端设计类 Skill,可作为该场景下的辅助能力补充。主要用于产品上线前的高品质收尾阶段。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/ui-ux-polish

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skil…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

ui-ux-polish 怎么安装?

在终端执行 npx skills add https://github.com/dicklesworthstone/agent_flywheel_clawdbot_skills_and_int…。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

ui-ux-polish 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

ui-ux-polish 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

ui-ux-polish 是免费的吗?

来源标注的许可证是 MIT。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

ui-ux-polish 用的人多吗?

公开数据是累计安装 3,655 次,近一周安装 157 次,下载 1,281 次,GitHub 63 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

ui-ux-polish 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 3 个目录同时收录,说明这个 Skill 流传比较广。
  • 许可证明确为 MIT,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理前端设计类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 需要厂商级技术支持和 SLA 的生产系统。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
ui-ux-polish

用户界面用户体验波兰语 · 本页

3,65563操作浏览器MIT通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

UI/UX Polish — Iterative Enhancement Workflow

When to Use: This is for when your site/app already works and looks decent and you want to improve it. There's a different approach when it looks bad and needs a complete overhaul. Key Insight: Something about asking for agreement from the model ("don't you agree?") somehow motivates it to polish things up better. Also, instructing it to separately think through desktop vs mobile leads to much better outcomes.

The Workflow

Overview

  1. App already works and looks decent
  2. Run the polish prompt
  3. Agent makes incremental improvements
  4. Repeat many times (10+ iterations)
  5. Each pass adds small improvements that compound

Why Multiple Passes Work

  • Each time, it tries to make some incremental improvement, even if it's minor
  • These really add up after 10 iterations!
  • Multiple agents can work on this simultaneously
  • Cumulative effect is dramatic

THE EXACT PROMPT — UI/UX Polish

This prompt is used so frequently it's worth putting on a Stream Deck button:

I still think there are strong opportunities to enhance the UI/UX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI/UX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI/UX and mobile UI/UX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way.  Use ultrathink.

Why This Prompt Works

1. Asks for Agreement

The phrase "don't you agree?" engages the model's reasoning about whether improvements are possible, rather than just executing instructions.

2. Separates Desktop and Mobile

"carefully consider desktop UI/UX and mobile UI/UX separately...
hyper-optimize for both separately to play to the specifics of each modality"

This prevents the model from making compromises that work "okay" on both but great on neither.

3. Sets High Standards

References:

  • "world class"
  • "best practices like those used by Stripe"
  • "makes people gasp at how stunning and perfect it is"

These anchors push the model toward higher quality than generic "make it better" instructions.

4. Uses Ultrathink

Extended thinking allows the model to:

  • Analyze the current state thoroughly
  • Consider multiple improvement options
  • Choose the highest-impact changes
  • Think through edge cases

Best Models for This Task

ModelEffectiveness
Claude Code + Opus 4.5Excellent
Codex + GPT 5.2 (High/Extra-High reasoning)Excellent
Gemini CLIGood

Tech Stack Compatibility

This prompt works with:

  • Next.js 16 + React 19 + Tailwind 4
  • Any modern web framework
  • Applications using Framer Motion or similar animation libraries
  • Pretty much anything—it's generic enough to adapt

Iteration Protocol

Single Agent

# First pass
[Run the UI/UX polish prompt]

# Review changes
[Agent makes improvements]

# Second pass
[Run the same prompt again]

# Repeat 10+ times until changes become minimal

Multiple Agents

You can have more than one agent working on UI/UX polish simultaneously:

  • They'll focus on different areas
  • Use file reservations to avoid conflicts
  • Compound improvements faster

When to Use vs. When NOT to Use

USE This Prompt When:

  • App works correctly
  • Basic styling is in place
  • You want to elevate from "decent" to "world-class"
  • Ready for iterative refinement
  • Want to optimize for both desktop and mobile

DON'T Use This Prompt When:

  • App is broken or buggy (fix bugs first)
  • Styling is fundamentally wrong (need complete overhaul)
  • No basic design system in place
  • Starting from scratch

For complete overhauls, use a different approach focused on establishing a design system and component library first.


What the Model Typically Improves

Visual Polish

  • Spacing and padding consistency
  • Typography hierarchy
  • Color contrast and accessibility
  • Shadow and depth effects
  • Border radius consistency
  • Hover/focus states

Interaction Design

  • Button feedback
  • Loading states
  • Transitions and animations
  • Error state handling
  • Empty state design

Mobile Optimization

  • Touch target sizes
  • Responsive breakpoints
  • Mobile-specific navigation
  • Gesture support
  • Performance on mobile devices

Desktop Optimization

  • Keyboard navigation
  • Hover states
  • Multi-column layouts
  • Sidebar navigation
  • Power user shortcuts

Tracking Progress

After each iteration, you might notice:

  • Subtle shadow improvements
  • Better spacing rhythm
  • More consistent typography
  • Smoother animations
  • Better responsive behavior

These small changes compound. An app after 10 passes looks dramatically better than after 1 pass.


Integration with Beads

For systematic UI/UX work, create beads:

br create "Polish homepage UI/UX for desktop" -t enhancement -p 2
br create "Polish homepage UI/UX for mobile" -t enhancement -p 2
br create "Polish dashboard UI/UX for desktop" -t enhancement -p 2
br create "Polish dashboard UI/UX for mobile" -t enhancement -p 2

This lets agents work on UI/UX polish as part of the normal bead workflow.


Complete Prompt Reference

Main Polish Prompt

I still think there are strong opportunities to enhance the UI/UX look and feel and to make everything work better and be more intuitive, user-friendly, visually appealing, polished, slick, and world class in terms of following UI/UX best practices like those used by Stripe, don't you agree? And I want you to carefully consider desktop UI/UX and mobile UI/UX separately while doing this and hyper-optimize for both separately to play to the specifics of each modality. I'm looking for true world-class visual appeal, polish, slickness, etc. that makes people gasp at how stunning and perfect it is in every way.  Use ultrathink.

Alternative: General Scrutiny (from agent-swarm-workflow)

Great, now I want you to super carefully scrutinize every aspect of the application workflow and implementation and look for things that just seem sub-optimal or even wrong/mistaken to you, things that could very obviously be improved from a user-friendliness and intuitiveness standpoint, places where our UI/UX could be improved and polished to be slicker, more visually appealing, and more premium feeling and just ultra high quality, like Stripe-level apps.

Tips

  1. Don't skip iterations — Even when changes seem small, keep going
  2. Review changes — Make sure the model isn't breaking things
  3. Test on real devices — Desktop browser!= mobile experience
  4. Consider accessibility — WCAG compliance matters
  5. Keep performance in mind — Pretty but slow is bad UX

平台分布

Claude Code

27.15%
按下载量换算348

OpenCode

21.38%
按下载量换算274

Gemini CLI

17.46%
按下载量换算224

Antigravity

12.24%
按下载量换算157

Codex

8.13%
按下载量换算104

Cursor

3.48%
按下载量换算45

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。

继续浏览同类 Skills