Token导航 LogoToken导航TokenDH.com
研究检索只读github未标认证来源可访问clear审计通过

ui-designer用户界面设计师

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

8,387

周安装

346

GitHub Stars

956

下载量

2,740
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

3

许可证

MIT

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-designer(用户界面设计师)
来源仓库:https://github.com/daymade/claude-code-skills
仓库路径:skills/ui-designer
安装命令:
npx skills add https://github.com/daymade/claude-code-skills --skill ui-designer
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/daymade/claude-code-skills --skill ui-designer

简介

ui-designer 用于辅助界面设计、视觉规范与交互体验优化,支持从参考图提取设计系统并生成实现级 UI 方案。

  • 它能分析色彩、排版与组件结构,输出设计文档与 PRD,确保多页面风格一致且符合用户任务流程。
  • 使用时需结合品牌资产与现有设计系统,避免堆砌装饰元素,并通过截图或预览检查响应式表现。
  • 安装前应确认是否涉及真实页面修改,建议配合浏览器工具验证文本溢出与对齐问题。
  • 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。

SKILL.md

UI Designer

Overview

This skill enables systematic extraction of design systems from reference UI images through a multi-step workflow: analyze visual patterns → generate design system documentation → create PRD → produce implementation-ready UI prompts.

When to Use

  • User provides UI screenshots, mockups, or design references
  • Need to extract color palettes, typography, spacing from existing designs
  • Want to generate design system documentation from visual examples
  • Building MVP UI that should match reference aesthetics
  • Creating multiple UI variations following consistent design principles

Workflow

Step 1: Gather Inputs

Request from user:

  • Reference images directory: Path to folder containing UI screenshots/mockups
  • Project idea file: Document describing the product concept and goals
  • Existing PRD (optional): If PRD already exists, skip Step 3

Step 2: Extract Design System from Images

Use Task tool with general-purpose subagent, providing:

Prompt template from assets/design-system.md:

  • Analyze color palettes (primary, secondary, accent, functional colors)
  • Extract typography (font families, sizes, weights, line heights)
  • Identify component styles (buttons, cards, inputs, icons)
  • Document spacing system
  • Note animations/transitions patterns
  • Include dark mode variants if present

Attach reference images to the subagent context.

Output: Complete design system markdown following the template format

Save to: documents/designs/{image_dir_name}_design_system.md

Step 3: Generate MVP PRD (if not provided)

Use Task tool with general-purpose subagent, providing:

Prompt template from assets/app-overview-generator.md:

  • Replace {项目背景} with content from project idea file
  • The template guides through: elevator pitch, problem statement, target audience, USP, features list, UX/UI considerations

Interact with user to refine and clarify product requirements

Output: Structured PRD markdown

Save as variable for Step 4 (optionally save to documents/prd/)

Step 4: Compose Final UI Implementation Prompt

Combine design system and PRD using assets/vibe-design-template.md:

Substitutions:

  • {项目设计指南} → Design system from Step 2
  • {项目MVP PRD} → PRD from Step 3 or provided PRD file

Result: Complete, implementation-ready prompt containing:

  • Design aesthetics principles
  • Project-specific color/typography guidelines
  • App overview and feature requirements
  • Implementation tasks (multiple UI variations, component structure)

Save to: documents/ux-design/{idea_file_name}_design_prompt_{timestamp}.md

Step 5: Verify React Environment

Check for existing React project:

find . -name "package.json" -exec grep -l "react" {} \;

If none found, inform user:

npx create-react-app my-app
cd my-app
npm install -D tailwindcss postcss autoprefixer
npx tailwindcss init -p
npm install lucide-react

Step 6: Implement UI

Use the final composed prompt from Step 4 to implement UI in React project.

The prompt instructs to:

  • Create multiple design variations (3 for mobile, 2 for web)
  • Organize as separate components: [solution-name]/pages/[page-name].jsx
  • Aggregate all variations in showcase page

Template Assets

assets/design-system.md

Template for extracting visual design patterns. Includes sections for:

  • Color palette (primary, secondary, accent, functional, backgrounds)
  • Typography (font families, weights, text styles)
  • Component styles (buttons, cards, inputs, icons)
  • Spacing system (4dp-48dp scale)
  • Animations (durations, easing curves)
  • Dark mode variants

Use this template when analyzing reference images to ensure comprehensive design system coverage.

assets/app-overview-generator.md

Template for collaborative PRD generation. Guides through:

  • Elevator pitch
  • Problem statement and target audience
  • Unique selling proposition
  • Platform targets
  • Feature list with user stories
  • UX/UI considerations per screen

Designed for interactive refinement with user to clarify requirements.

assets/vibe-design-template.md

Final implementation prompt template combining design system and PRD. Includes:

  • Aesthetic principles (minimalism, whitespace, color theory, typography hierarchy)
  • Practical requirements (Tailwind CSS, Lucide icons, responsive design)
  • Task specifications (multiple variations, component organization)

This template produces prompts ready for UI implementation without further modification.

Best Practices

Image Analysis

  • Read all images before starting analysis
  • Look for patterns across multiple screens
  • Note both explicit styles (colors, fonts) and implicit principles (spacing, hierarchy)
  • Capture dark mode if present in references

Design System Extraction

  • Be systematic: cover all template sections
  • Use specific values (hex codes, px sizes) not generic descriptions
  • Document the "why" for design choices when inferable
  • Include variants (hover states, disabled states)

PRD Generation

  • Engage user interactively to clarify ambiguities
  • Suggest features based on problem understanding
  • Ensure MVP scope is realistic
  • Document UX considerations per screen/interaction

Output Organization

  • Save design system with descriptive filename (based on image dir name)
  • Save final prompt with timestamp for version tracking
  • Keep all outputs in documents/ directory for easy reference
  • Preserve intermediate outputs for iteration

Example Usage

User provides:

  • reference-images/saas-dashboard/ (5 screenshots)
  • ideas/project-management-app.md (project concept)

Execute workflow:

  1. Read 5 images from reference-images/saas-dashboard/
  2. Use Task tool → design-system.md template → analyze images
  3. Save to documents/designs/saas-dashboard_design_system.md
  4. Use Task tool → app-overview-generator.md with project concept
  5. Refine PRD through user interaction
  6. Combine design system + PRD using vibe-design-template.md
  7. Save to documents/ux-design/project-management-app_design_prompt_20251025_153000.md
  8. Check React environment, inform user if setup needed
  9. Implement UI using final prompt

Notes

  • This is a high freedom workflow—adapt steps based on context
  • Templates provide structure but encourage thoughtful analysis over rote filling
  • User interaction during PRD generation is critical for quality
  • Final prompt quality directly impacts UI implementation success
  • Preserve all intermediate outputs for iteration and refinement

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

04

需要参考平台分布和安装热度时

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

补充不同宿主或平台的使用分布数据

能力 5

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

Claude Code

28.33%
按下载量换算776

OpenCode

23.85%
按下载量换算653

Antigravity

20.25%
按下载量换算555

Gemini CLI

14.5%
按下载量换算397

Cursor

7.87%
按下载量换算216

Codex

3.69%
按下载量换算101

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。

来源信息

继续浏览同类 Skills