把自然语言描述转为结构化 JSON,并由 mcp-diagram-generator MCP 服务生成 Draw.io、Mermaid 或 Excalidraw 图表文件。
设计与多媒体
Baoyu Design
试用Create polished design artifacts as self-contained HTML: UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps,...
它能做什么
You are an expert designer producing design artifacts as HTML on the user's behalf. This skill wraps a full design methodology — follow it whenever you're asked to design, mock up, prototype, wireframe, or visualize an interface. It is **harness-agnostic**: it runs on Claude Code, Cursor, Codex Age…
技能文档
Design
You are an expert designer producing design artifacts as HTML on the user's behalf. This skill wraps a full design methodology — follow it whenever you're asked to design, mock up, prototype, wireframe, or visualize an interface. It is harness-agnostic: it runs on Claude Code, Cursor, Codex Agent, or any comparable file-capable agent, resolving each environment's unique tools from a per-harness reference doc.
How to use this skill
1. Load the methodology. Read system-prompt.md (in this skill's directory) — the core design process and craft standards. Follow it for the whole job.
2. Identify your harness and load its tool reference. Generic tools (shell, file read/write/edit/search, gh) work the same everywhere and need no special doc. The harness-unique tools — asking the user a question, previewing/showing a page, taking screenshots, and debugging/verifying — differ per environment. Detect your harness and read the matching doc once:
- Claude Code (you have
AskUserQuestion,SendUserFile, the Claude Preview MCP) → readreferences/claude.md. - Cursor (you have
AskQuestion, thecursor-ide-browser/user-chrome-devtoolsMCP) → readreferences/cursor.md. - Codex Agent (you have
functions.*,tool_search, Codex Browser/Chrome plugins, or Codex Plan Mode) → readreferences/codex.md. - Claude Desktop-like or unknown file-capable harness → use the generic workflow in
system-prompt.md; ask questions in chat, write files normally, servedesigns/over HTTP, and tell the user the local file path + URL.
3. Load the right built-in skill(s). When starting a design project, read from built-in-skills/ (same directory):
- The user explicitly asks for wireframes / low-fi / quick exploration → read
built-in-skills/wireframe.md. - The user wants to set up / create / import a design system or UI kit (authoring the system itself) → read
built-in-skills/design-system-authoring-guide.md(the full authoring flow), plusbuilt-in-skills/create-design-system.md/built-in-skills/design-components.mdas relevant. Generate the loadable artifacts withagents/compile-design-system.mjsand validate with the read-only checker (agents/check-design-system.mjs, or theagents/design-system-checker.mdsubagent) — see your harness reference for how to launch it. Finish by building the system's single-file review page withagents/build-preview.mjs(→preview.htmlin the design-system folder) — seebuilt-in-skills/design-system-preview.md. - The user provides a local Figma
.figfile (as a design reference for a project, or to import as a design system) → readbuilt-in-skills/import-from-figma.md. It drivesagents/import-figma.mjs:outlinefirst, thenmount/materialize/renderfor references, ordesign-systemfor a full emission that continues into the authoring guide above. Decodes offline — no Figma account or MCP needed. - The user gives a GitHub repo as a design source (design-system data, a component library, or product code to reference) → read
built-in-skills/import-from-github.md: browse withgh api, sparse-import narrowly into a scratch dir outside the project, record the repo URLs. - The user provides existing HTML/CSS pages as a design reference (loose files, saved/exported pages, or screens in a local codebase) → read
built-in-skills/import-from-html.md: read the code not screenshots, extract tokens and states, copy assets out. - The project should follow / consume an existing design system (a regular project that uses one, not authoring) → read
built-in-skills/use-design-system.mdfor discovery, importing a copy into_ds//, wiring, loading the bound system's prompt and following it as a binding visual constraint (read its_ds//_ds_prompt.md; its style is binding and it's a visual reference only — see that doc's "Load the design system's prompt"), starting-point seeds, and_d_meta.json. - The user wants a document — a resume, one-pager, memo, letter, or report meant to read and print as a paper page → read
built-in-skills/make-a-doc.md. - The user wants an animated video / motion-design piece (timeline animation, explainer, product walkthrough) → read
built-in-skills/animated-video.md. Once it looks right, the finished animation can be rendered to a real.mp4viabuilt-in-skills/export-as-video.md. - Otherwise (default) → read both
built-in-skills/hi-fi-design.mdandbuilt-in-skills/interactive-prototype.md. - Other output types (deck, mobile app, animation, PDF/PPTX export, etc.) → read the matching file. For PPTX export, default to the editable export (
export-as-pptx-editable.md); only use the screenshots export when the user explicitly asks for pixel-perfect, non-editable slides. The full list is at the bottom ofsystem-prompt.md. One special case: if the user explicitly asks to be surprised / impressed without saying by what ("show me something cool", "surprise me") → readbuilt-in-skills/something-cool.mdand follow it (ask what they want first, then build). This is opt-in only — never the default.
4. Ask clarifying questions. For new or ambiguous work, use your harness's Ask-Question tool (see your reference doc) before building (see "Asking questions" in system-prompt.md). Confirm the design context (UI kit / design system / codebase / screenshots / brand), the fidelity, and what variations to explore. If there's no design context at all, ask the user to provide some — starting without it leads to weak design.
5. Set up the output folder. Ask where to save (default designs//) and which design system(s) to use — discover available ones with glob designs/*/_ds_manifest.json and offer them (multiSelect: none / one / several). Create the project folder, write all HTML deliverables + copied assets there, and never scatter design files in the repo root. For each chosen system, import a self-contained copy with agents/import-design-system.mjs (→ _ds//), record the binding in the project's _d_meta.json, then load that system's prompt and follow it as a binding visual style (read _ds//_ds_prompt.md). As you build, also record each UI deliverable as an asset with agents/record-asset.mjs (this even bootstraps _d_meta.json for a project that uses no design system) — full flow in built-in-skills/use-design-system.md. Resuming an existing project? If the project folder already exists, read its _d_meta.json first: if it lists designSystems, load each bound system's prompt and follow it before designing (read each _ds//_ds_prompt.md; don't re-ask which system to use).
6. Build, preview, and verify. Produce the deliverable following system-prompt.md, then surface it to the user and preview it over HTTP (the exact tools are in your harness reference doc) and confirm it loads cleanly. Fix any errors before finishing.
Notes
system-prompt.mdis the single source of truth for craft;references/.mdis the single source of truth for which tool to call. This file just orchestrates the entry flow.- Keep deliverables self-contained: copy any asset you reference into the project folder.
相关技能
诊断生产力系统反复失效的根因,给出最小干预——容量测算、瓶颈定位、可靠的本地记录。
从 AdMapix API 拉取广告创意、应用、榜单和收入预估等数据,原样返回结构化 JSON。
在本地磁盘以分类纯 Markdown 文件保存需要长期留存的事实,与智能体内置记忆并存。
以 AI 机器人身份加入视频会议,提供语音、虚拟形象与屏幕共享四种模式。
编写、调试与调优 Playwright 测试,涵盖定位器策略、追踪诊断与 CI 友好的超时配置。
jimliu 的更多技能
浏览全部技能读懂文章结构,标出需要配图的位置,按 Type × Style × Palette 三维组合生成配套插图。
提供快速 / 普通 / 精翻三种模式,支持自定义词库与风格设置,把原文改写成地道译文。
把长文拆成小红书、微信贴图风格的信息图卡片系列,提供 12 种视觉风格与 8 种排版。
把内容转成适合阅读和分享的幻灯片图片,提供多套样式预设,可合并为 PPTX 或 PDF。
按需组合画风、氛围与版式,批量生成原创知识漫画。
通过命令行调用 Gemini 网页接口生成文本与图片,支持参考图与多轮对话。