Token导航 LogoToken导航TokenDH.com
研究检索敏感数据github未标认证来源可访问clear审计未展示

web-design-complete网页设计完成

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

145

周安装

6

GitHub Stars

公开资料未说明

下载量

48
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

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:web-design-complete(网页设计完成)
来源仓库:https://github.com/xiaodong-wu/web-design-studio
仓库路径:skills/web-design-complete
安装命令:
npx skills add xiaodong-wu/web-design-studio --skill "web-design-complete"
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。

AgentSkills.tonpx skills
npx skills add xiaodong-wu/web-design-studio --skill "web-design-complete"

简介

用于发现并安装 AI 代理的技能。

  • 支持在 Codex、Claude、Cursor、Gemini CLI 等宿主环境中使用。
  • 通过 npx 命令添加指定技能,便于扩展 Agent 能力。
  • 安装命令:npx skills add xiaodong-wu/web-design-studio --skill "web-design-complete";需确保 Node.js 环境已配置。
  • 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

This skill combines frontend design expertise with AI image generation to create complete, production-ready web pages with all visual elements included.

When to Use This Skill

Use this skill when the user asks for:

  • Complete websites or landing pages
  • Web dashboards or applications
  • Product pages or portfolios
  • Marketing pages with banners/hero sections
  • Blog or content layouts with featured images
  • Any web interface that needs visual assets

How This Skill Works

This skill performs a two-step process:

Step 1: Frontend Design

Follow the frontend-design aesthetic principles to create a distinctive, production-grade interface:

Design Thinking:

  • Purpose: What problem does this interface solve? Who uses it?
  • Tone: Pick a bold aesthetic direction (minimalist, maximalist, retro-futuristic, organic, luxury, playful, brutalist, etc.)
  • Constraints: Technical requirements (framework, performance, accessibility)
  • Differentiation: What makes this UNFORGETTABLE?

Frontend Aesthetics:

  • Typography: Choose distinctive, beautiful fonts (avoid Inter, Roboto, Arial, system fonts)
  • Color & Theme: Commit to a cohesive aesthetic with CSS variables
  • Motion: Use animations for effects and micro-interactions
  • Spatial Composition: Unexpected layouts, asymmetry, overlap, diagonal flow
  • Backgrounds & Visual Details: Gradient meshes, noise textures, geometric patterns, dramatic shadows

Step 2: Image Generation

Identify all images needed in the design and generate them using the image generation script:

Identify Image Needs:

  • Hero/banner images
  • Product/portfolio images
  • Illustrations or icons
  • Background images
  • Section dividers or decorative elements

Generate Images: Run the image generation script for each image needed:

uv run ~/.claude/skills/web-design-complete/scripts/generate_image.py \\
  --prompt "detailed image description matching the design aesthetic" \\
  --filename "yyyy-mm-dd-hh-mm-ss-descriptive-name.png" \\
  --resolution 1K|2K|4K

Resolution Guidelines:

  • 1K (default) - ~1024px for small images, icons, thumbnails
  • 2K - ~2048px for standard images, product shots
  • 4K - ~4096px for hero banners, large backgrounds

Filename Format: {timestamp}-{descriptive-name}.png

  • Timestamp: yyyy-mm-dd-hh-mm-ss (24-hour format)
  • Name: lowercase descriptive text with hyphens

Step 3: Complete Implementation

After generating all needed images, create the final code with:

  1. All generated images properly referenced
  2. Optimized image attributes (alt text, loading, sizes)
  3. Responsive image handling
  4. Complete styling matching the aesthetic vision

Complete Workflow Example

User Request: "Create a landing page for a coffee shop"

Process:

  1. Design Phase: Choose a warm, organic aesthetic with earth tones, rustic typography
  2. Image Planning: Identify needs for:

- Hero banner with coffee atmosphere - Product shots for coffee cups - Background textures for sections

  1. Generate Images: # Hero banner uv run ~/.claude/skills/web-design-complete/scripts/generate_image.py \\ --prompt "warm rustic coffee shop interior, golden hour lighting, wooden tables, steaming coffee cups, cozy atmosphere, earthy brown tones" \\ --filename "2025-01-24-10-30-15-coffee-shop-hero.png" \\ --resolution 4K # Product shot uv run ~/.claude/skills/web-design-complete/scripts/generate_image.py \\ --prompt "artisan coffee cup on wooden table, latte art, top view, warm lighting, rustic background" \\ --filename "2025-01-24-10-32-45-coffee-cup-product.png" \\ --resolution 2K # Background texture uv run ~/.claude/skills/web-design-complete/scripts/generate_image.py \\ --prompt "subtle coffee bean pattern texture, warm brown gradient, organic feel, seamless" \\ --filename "2025-01-24-10-35-20-coffee-texture-bg.png" \\ --resolution 2K
  2. Create Code: Build complete HTML/CSS with all images integrated

API Key

The script requires a Gemini API key:

  • Pass via --api-key argument if user provides one
  • Otherwise uses GEMINI_API_KEY environment variable

Best Practices

  1. Design First, Images Second: Plan the complete design before generating images
  2. Match Aesthetics: Ensure generated images match the chosen design aesthetic
  3. Optimize Resolution: Use appropriate resolution for each image's purpose
  4. Descriptive Prompts: Write detailed, aesthetic-specific prompts for better results
  5. Organize Filenames: Use clear, descriptive filenames matching the design context

Output

  • Complete, production-ready HTML/CSS/JS code
  • All needed images generated and saved to current directory
  • Images properly referenced in the code
  • Responsive, functional, and visually stunning result

Remember: The goal is to create COMPLETE web experiences where every visual element is thoughtfully designed and generated - no placeholder images, no "image goes here" sections. Real, finished work.

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

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

windsurf

33.73%
按下载量换算16

trae

24.81%
按下载量换算12

OpenCode

17.07%
按下载量换算8

Cursor

10.1%
按下载量换算5

Claude Code

5.19%
按下载量换算2

安全审计

暂无安全审计结果可展示。

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

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