AgentSkillsCN

html-design-workflow

多智能体 UI/UX 设计流程,可将图像一键转换为 HTML/Tailwind 代码。适用于用户希望从 UI 截图生成 HTML/CSS、依据视觉设计制作 PRD 文档、将线框图转化为可用代码,或从原型图构建响应式网页的场景。该流程会依次调用 4 个专业智能体,协同完成任务。

SKILL.md
--- frontmatter
name: html-design-workflow
description: >
  Multi-agent UI/UX design workflow that converts images to HTML/Tailwind code.
  Use when users want to generate HTML/CSS from UI screenshots, create PRD documents
  from visual designs, convert wireframes to working code, or build responsive web
  pages from mockups. Orchestrates 4 specialized agents sequentially.

HTML Design Workflow

A 4-stage automated pipeline that transforms design images into production-ready HTML/Tailwind code.

Required Inputs

Create these files before running:

  • files/inputs/target_image.png - The UI design image
  • files/inputs/topic.txt - Topic/context description (e.g., "个人主页")

Workflow Stages

The pipeline runs sequentially - each stage depends on the previous:

Stage 1: PRD Architect

Stage 2: Structure Sketch Designer

Stage 3: Hierarchy Logic Mapper

Stage 4: UI Art Director

Orchestrator

For automated pipeline management, see: references/orchestrator.md

The orchestrator:

  • Verifies inputs exist
  • Spawns agents sequentially
  • Validates each stage output before proceeding
  • Reports completion status

Technical Stack

  • HTML5 + Tailwind CSS 2.2.19
  • Font Awesome 6.0.0
  • Google Fonts: Noto Serif SC, Noto Sans SC

Quick Start

bash
mkdir -p files/inputs files/workspace
cp your-design.png files/inputs/target_image.png
echo "个人主页" > files/inputs/topic.txt

Then follow the orchestrator workflow or run each agent stage manually.