html-visual

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Input

输入

text
$ARGUMENTS
text
$ARGUMENTS

Instructions

说明

Visualize the user's request as an interactive single HTML file. First, read
references/common-rules.md
to review common rules.
将用户的请求生成为交互式单HTML文件。 首先阅读
references/common-rules.md
以查看通用规则。

Type Determination

类型判定

Determine the type from the first argument (
$0
).
ArgumentTypeFilename Pattern
mockup
UI mockup (high-fidelity)
mockup-{name}.html
wireframe
Wireframe (low-fidelity, hand-drawn style)
wireframe-{name}.html
erd
ERD
erd-{name}.html
flow
Flowchart / Sequence diagram
flow-{name}.html
chart
Data chart
chart-{name}.html
slides
Presentation
slides-{name}.html
arch
Architecture diagram
arch-{name}.html
dashboard
Composite dashboard
dashboard-{name}.html
timeline
Timeline / Gantt chart
timeline-{name}.html
mindmap
Mindmap
mindmap-{name}.html
kanban
Kanban board
kanban-{name}.html
table
Interactive data table
table-{name}.html
No match: Infer the type from the request content. If unable to infer, ask the user. When inferred, use
visual-{name}.html
as the filename.
根据第一个参数(
$0
)确定类型。
参数类型文件名格式
mockup
UI原型(高保真)
mockup-{name}.html
wireframe
线框图(低保真,手绘风格)
wireframe-{name}.html
erd
ERD(实体关系图)
erd-{name}.html
flow
流程图/时序图
flow-{name}.html
chart
数据图表
chart-{name}.html
slides
演示文稿
slides-{name}.html
arch
架构图
arch-{name}.html
dashboard
复合仪表盘
dashboard-{name}.html
timeline
时间线/甘特图
timeline-{name}.html
mindmap
思维导图
mindmap-{name}.html
kanban
看板
kanban-{name}.html
table
交互式数据表
table-{name}.html
无匹配项:从请求内容中推断类型。如果无法推断,请询问用户。 推断类型后,使用
visual-{name}.html
作为文件名。

Input Handling

输入处理

  • File path provided: Read and analyze the file, then visualize. e.g.,
    /html-visual erd schema.prisma
    → Analyze the Prisma schema to auto-generate ERD
  • Existing HTML modification: Read and modify the existing file. Do not recreate from scratch.
  • Natural language only: Infer the type, then generate.
  • 提供文件路径:读取并分析文件,然后进行可视化。 例如,
    /html-visual erd schema.prisma
    → 分析Prisma schema以自动生成ERD
  • 修改现有HTML:读取并修改现有文件,不要从头重新创建。
  • 仅自然语言:推断类型,然后生成。

Context Gathering

上下文收集

  • Description is sufficient: Generate immediately (e.g., "simple login form mockup")
  • Project code reference needed: Read code/schema/API first (e.g., "our project's ERD", "current payment flow")
  • Criterion: If the request contains project context references like "our", "current", "project's", read the code first.
  • 描述足够:立即生成(例如,"简单登录表单原型")
  • 需要项目代码参考:先读取代码/ schema / API(例如,"我们项目的ERD"、"当前支付流程")
  • 判断标准:如果请求包含"我们的"、"当前"、"项目的"等项目上下文参考,请先读取代码。

Type-Specific Guides

类型特定指南

mockup

mockup(UI原型)

  • Device frame: Actual device frame shape for mobile/tablet UI
  • Multiple screens: Side-by-side layout + screen labels
  • Placeholder data: Realistic data matching project context
  • Tab/swipe for screen transitions
  • 设备框架:为移动/平板UI使用真实设备框架形状
  • 多屏幕:并排布局 + 屏幕标签
  • 占位数据:符合项目上下文的真实数据
  • 标签页/滑动切换屏幕

wireframe

wireframe(线框图)

  • Hand-drawn (sketch) style: Slightly irregular lines, hand-drawn feel
  • Black-and-white or grayscale. Minimal color
  • Text areas shown as gray blocks (no "Lorem ipsum")
  • Focus on layout and information structure, exclude visual details
  • 手绘(草图)风格:略带不规则线条,手绘质感
  • 黑白或灰度,极少使用颜色
  • 文本区域显示为灰色块(不使用"Lorem ipsum")
  • 专注于布局和信息结构,排除视觉细节

erd

erd(实体关系图)

  • Entity boxes with attribute lists. Distinguish PK/FK
  • Relationship lines: 1:1, 1:N, N:M notation. Auto-track on node drag
  • Include relationship type legend
  • 带有属性列表的实体框,区分主键(PK)/外键(FK)
  • 关系线:1:1、1:N、N:M标记,节点拖动时自动跟踪
  • 包含关系类型图例

flow

flow(流程图)

  • Node types: Start/End (circle), Process (rectangle), Decision (diamond)
  • Directional arrows. Auto-track on node drag
  • Display branch conditions on connection lines
  • 节点类型:开始/结束(圆形)、流程(矩形)、决策(菱形)
  • 有向箭头,节点拖动时自动跟踪
  • 在连接线上显示分支条件

chart

chart(数据图表)

  • Auto-select appropriate chart type for the data (bar, line, pie, scatter, etc.)
  • Axis labels + units, hover tooltips, legend
  • Use Chart.js or D3.js
  • 根据数据自动选择合适的图表类型(柱状图、折线图、饼图、散点图等)
  • 坐标轴标签+单位、悬停提示框、图例
  • 使用Chart.js或D3.js

slides

slides(演示文稿)

  • Reveal.js CDN-based
  • Slide transition animations
  • Code block highlighting (highlight.js)
  • Speaker notes support (toggle with S key)
  • 基于Reveal.js CDN
  • 幻灯片切换动画
  • 代码块高亮(highlight.js)
  • 支持演讲者备注(按S键切换)

arch

arch(架构图)

  • Separate system components by layer/zone (Frontend / Backend / DB / External)
  • Label communication lines with protocols (HTTP, gRPC, pub/sub, etc.)
  • Zoom/pan support
  • D3.js force-directed or direct SVG generation
  • 按层/区域分离系统组件(前端/后端/数据库/外部系统)
  • 在通信线上标注协议(HTTP、gRPC、pub/sub等)
  • 支持缩放/平移
  • 使用D3.js力导向图或直接生成SVG

dashboard

dashboard(仪表盘)

  • Arrange multiple charts/metrics in grid layout
  • KPI cards at the top (numbers + change rates)
  • Cross-chart interaction: Click one → filter others
  • 以网格布局排列多个图表/指标
  • 顶部放置KPI卡片(数字+变化率)
  • 跨图表交互:点击一个图表→过滤其他图表

timeline

timeline(时间线)

  • Horizontal or vertical timeline
  • Event nodes + date labels
  • Zoom/scroll for period navigation
  • Use Mermaid gantt or D3.js
  • 水平或垂直时间线
  • 事件节点+日期标签
  • 支持缩放/滚动查看时间段
  • 使用Mermaid甘特图或D3.js

mindmap

mindmap(思维导图)

  • Radial expansion from center node
  • Node collapse/expand
  • Use Mermaid mindmap or direct SVG generation
  • 从中心节点放射状展开
  • 节点可折叠/展开
  • 使用Mermaid思维导图或直接生成SVG

kanban

kanban(看板)

  • Columns: TODO / In Progress / Done (customizable)
  • Drag and drop cards between columns
  • Display labels/tags on cards
  • 列:待办/进行中/已完成(可自定义)
  • 卡片可在列间拖拽
  • 在卡片上显示标签

table

table(交互式数据表)

  • Sort by clicking column headers (ascending/descending)
  • Search/filter at the top
  • Pagination or virtual scroll
  • Cell highlight, row selection
  • 点击列标题排序(升序/降序)
  • 顶部提供搜索/过滤功能
  • 分页或虚拟滚动
  • 单元格高亮、行选择

Procedure

步骤

  1. Identify type + target. Ask if ambiguous. Read the file if a path is provided.
  2. Context gathering decision. Determine if project context is needed. If so, read relevant code/docs.
  3. Read
    references/common-rules.md
    . Review common principles, aesthetics, CDN, and error prevention rules.
  4. Read
    references/html-boilerplate.md
    . Start from the base HTML template.
  5. Generate HTML following the type-specific guide.
  6. Validate: Review the generated HTML.
    • No smart quotes (curly quotes) in HTML attributes
    • No unclosed tags
    • No overlapping nodes/elements
    • If issues found, fix and re-validate
  7. Instruct to
    open {filename}
    .
  1. 确定类型+目标:如果有歧义请询问。如果提供了文件路径,请先读取文件。
  2. 判断是否需要收集上下文:确定是否需要项目上下文。如果需要,先读取相关代码/文档。
  3. 读取
    references/common-rules.md
    :查看通用原则、美学规范、CDN和错误预防规则。
  4. 读取
    references/html-boilerplate.md
    :从基础HTML模板开始。
  5. 根据类型特定指南生成HTML
  6. 验证:检查生成的HTML。
    • HTML属性中不使用智能引号(弯引号)
    • 没有未闭合的标签
    • 没有重叠的节点/元素
    • 如果发现问题,修复后重新验证
  7. 提示执行
    open {filename}