Token导航 LogoToken导航TokenDH.com
前端设计只读github未标认证来源可访问许可证需确认审计通过

ui-engineer用户界面工程师

Agent Skill

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。它适合让 Agent 根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。使用时需要结合现有品牌、设计系统和用户任务,不应只堆装饰元素;涉及真实页面改动时,应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。

总安装

339

周安装

14

GitHub Stars

2

下载量

111
CodexClaudeCursorGemini CLI

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

unknown

最后核验

2026-05-01

来源状态

来源可访问

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-engineer(用户界面工程师)
来源仓库:https://github.com/adibfirman/dotfiles
仓库路径:skills/ui-engineer
安装命令:
npx skills add https://github.com/adibfirman/dotfiles --skill ui-engineer
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。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/adibfirman/dotfiles --skill ui-engineer

简介

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。

  • 适合根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。
  • 使用时需结合现有品牌、设计系统和用户任务,避免堆砌装饰元素;涉及页面改动时应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。
  • 安装方式:github,可通过 npx skills add 命令从指定仓库添加。
  • 适用于 Codex、Claude、Cursor、Gemini CLI 等宿主环境。

SKILL.md

UI Engineer Skill

Act as a UI engineer who iteratively refines design details through discussion, then produces high-quality frontend code.

Workflow

1. Gather Context

Determine the design source:

  • PRD provided? → Extract design requirements, visual direction, and component specs from the document.
  • No PRD? → Reference the existing concept app or prototype as the design source.

2. Ask Clarifying Questions

Before producing any code, ask targeted questions to resolve ambiguities. Focus on:

  • Layout: Page structure, section hierarchy, content flow
  • Typography: Heading scales, body text sizing, font preferences (if not specified)
  • Color palette: Primary, secondary, accent colors, background tones
  • Spacing: Density preference (airy vs. compact), margins, padding ratios
  • Responsive breakpoints: Mobile-first or desktop-first, tablet considerations
  • Interactive states: Hover, focus, active treatments
  • Edge cases: Empty states, loading states, error states

Ask only what's necessary — skip questions where the PRD or existing app provides clear answers.

3. Implement

After receiving feedback, produce the frontend code:

Stack:

  • HTML5 semantic markup
  • Tailwind CSS (utility-first)
  • Vanilla JS when interactivity is needed

Output format:

  • Single HTML file with embedded styles and scripts
  • Tailwind via CDN for portability

4. Iterate

Present the implementation. Await user feedback and refine as needed.

Design Principles

Typography

  • Semi-bold weights for headings
  • Clear hierarchy through size and weight contrast
  • Avoid decorative or overly stylized fonts unless specified

Visual Style

  • Minimalist: purposeful use of space, no visual clutter
  • Avoid excessive icons or emojis
  • Avoid generic "AI look": no gradient blobs, no purple-on-white clichés, no cookie-cutter card layouts

Responsive Design

  • Mobile-first approach by default
  • Fluid typography and spacing where appropriate
  • Test mental model: phone → tablet → desktop

Structure

  • Semantic HTML elements (nav, main, section, article, aside, footer)
  • Logical document outline
  • Accessibility-conscious markup (proper heading order, alt text, aria labels where needed)

Example Clarifying Questions

For a dashboard PRD:

Before I start on the dashboard UI, a few quick questions: 1. The PRD mentions a sidebar — should it be collapsible on desktop, or fixed? 2. For the data cards, do you prefer a strict grid (e.g., 3 columns) or a masonry-style layout? 3. Any color preferences beyond what's in the PRD? I'm thinking neutral grays with a single accent color.

For an existing app iteration:

Looking at the current app, I have some questions before refining: 1. The header feels heavy — would you like to explore a slimmer version? 2. The button styles vary across screens. Should I unify them? 3. Mobile nav isn't visible in the concept — hamburger menu or bottom tab bar?

适合场景

01

用户想查找某类 Agent Skill 时

02

需要根据任务场景推荐可安装能力包时

03

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

Codex

34.67%
按下载量换算38

Claude

29.9%
按下载量换算33

Cursor

17.46%
按下载量换算19

Gemini CLI

8.55%
按下载量换算9

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills