Design & UX

子 skill — 设计系统与组件展示。当用户要从 repo 提取 design tokens 做团队 reference、或要把一个组件的所有 variant 平铺在一张 contact sheet 上 review 时使用。包含设计系统参考（design-tokens.html）和组件变体陈列两种范式。当父 skill 路由命中"设计系统/design tokens/组件变体/展示组件库"类请求时加载。

Use when the user asks to create, revise, review, prompt, art-direct, style-match, or make consistent BaseCamp illustrations and image-generation assets. Trigger for requests mentioning illustration prompts, image prompts, visual style guide, house style, style lane, taste, art direction, poster, cover art, comic panels, patient-education visuals, workshop/presentation visuals, OpenAI Image 2.0, generated images, visual examples, reference images, or rejected/accepted image outputs where cons...

阶段 4 视觉锚定三件套的主 skill——在写第一行代码前，用 Moodboard（A） + 完整网页示意图（B） + 动效帧序列（C） 三种图像级锚点把视觉方向钉死。探索前移在 Moodboard 阶段（A）以 2-3 张让用户选的方式执行，B/C 是单线生成。资产生成走双路径：主路径 baoyu-imagine skill 自动出图，兜底路径打开 prompt 文件让用户复制到网页端。产出写入 knowledge/design-docs/visual-anchors/ 目录，并在 design.md §12/§13/§14 回填引用。触发：design.md 初稿完成、后轮采访定稿后、用户说"出几张方向图让我选""做 moodboard""生成页面示意图""动效帧序列图"。不用于调研（那是 frontend-design-research）、不用于动效微观代码级 prompt（那是 frontend-motion-prompt-writer）、不用于写 DESIGN.md（那是 frontend-design-writer）。

前端项目二开 / 增量改进的入口路由器——已定稿 design.md 的项目要加新页面 / 新 section / 微改 token 时，先读老资产（design.md + visual-anchors/ + motion-prompts/），按三档 tier 判定（T1 新页面 / T2 新 section / T3 微改）输出本轮最小流程路径，阻止模型"假装新项目"把已定风格冲掉。本 skill 只做路由和前置防呆，不自己执行具体阶段——执行仍委给 dualround / visual-reference / design-writer / design-review 等原 skill。触发：用户说"加个新页面""在首页加一个 section""改一下这个按钮颜色""design.md 已经有了，现在要扩展 X""新路由 /blog / /pricing"。不用于全新项目从零启动（那是阶段 1-7 完整流程，走 frontend-interview-dualround 前轮）、不用于整站视觉重写（全站重写需要回阶段 2-4 重跑）、不用于纯 bug 修复（那是开发实现剧本）。

产品设计师视角的双轮深度采访横切——前轮（阶段 1 需求后）建产品边界 + 主语言收敛，后轮（阶段 3 Moodboard 选定后）拔架构 + section + 文案调性 + 交互路径。五类引导式提问：前轮是定位/用户/反向/资源/时间；后轮是架构/section/文案调性/交互路径/反向细节。角色显式从"前端设计师"切到"产品设计师"，选择题优先+开放题兜底，一次问 3-5 个不批量甩 20 个。产出反写回 design.md。触发：新项目启动 brief 模糊、六维调研完成但未定稿、用户说"帮我问清楚这个产品""我脑子里有个想法但说不清"。不用于代码后纠偏（那是 frontend-design-review 的三段式追问）、不用于需求判定机械门禁（那是 req-suite:requirement-clarifier）。

阶段 2 试吃——对 4-5 个该领域设计优秀的真实网站跑六维机械拆解（形 / 色 / 字 / 构 / 质 / 动），综合成本项目 design.md 初稿。六维是上位骨架，DOM 量化工作流 + 动效采访 5 类是落地肌肉。每次一站，保护上下文。不做前轮/后轮深度采访（那是 frontend-interview-dualround）、不做视觉锚定三件套（那是 frontend-visual-reference）、不写最终交付的 design.md（那是 frontend-design-writer）、不做组件库 / 动效资产库选型（那部分由 frontend-design-writer 的 §11 Resources 段 + 项目级 components.json 决定）。触发：新项目六维调研、整站重做、前端方向大迭代。

代码已经跑起来后（阶段 7 迭代微调）的设计评审横切——用户看到具体页面涌现审美反馈时使用：三段式追问（定位→对标→量化）把"感觉不对"翻译成可执行改动项，"选择题化"让用户做选择题而不是填空题，参数外显 Tweaks 让不确定的参数暴露成可调旋钮，所有修正反写回 design.md。覆盖 design-review（视觉对标）、design-content（文案与信息层级）、design-harden（边缘状态加固）三种子模式。**仅用于代码已生成后**——代码前的"感觉"引导走 frontend-interview-dualround 的后轮采访；纯调研走 frontend-design-research；写 design.md 走 frontend-design-writer。

Design meaningful interactions, microinteractions, animations, state machines, gesture patterns, error prevention, and product behavior. Specify how products respond to user input across all states and contexts using established interaction design principles.

Comprehensive design elevation system that automatically transforms functional visual outputs into polished, professional designs. Use when creating ANY visual output including presentations (pptx), spreadsheets (xlsx), dashboards, reports, HTML artifacts, PDFs, web pages, or data visualizations. Applies systematic design thinking grounded in Tailwind CSS as the canonical design token system. Structures decisions through functional patterns (what users interact with) and perceptual patterns (...

Creative Designer skill. Takes a post concept, a client product photo, or a real lifestyle photo and produces on-brand social media visuals using the client's brand style guide. Four modes — Generate (AI image from concept), Composite (client product photo anchored in an AI-generated scene), Brand (apply text overlay treatment to a real client photo), Stop-Motion Reel (6-frame action sequence exported as MP4). Reads brand-style.md, builds prompts, generates/edits images via Nano Banana MCP, o...

Creates executive-facing visual artifacts using Canva (presentations) and Figma (design annotations). Transforms Strategy findings into polished visual deliverables for leadership review.

Set up design / IA / UX / a11y / visual-quality discipline for a project. Authors a tailored kit of design audit agents, IA skills, and design-token rules — derived from the project's actual UI surfaces, the user's named design benchmarks, and past design failure modes. Invoke /dotclaude:design in any project root that has a human-facing surface.

Use when the user asks for a Windows app, Win11 UI, XAML, Fluent design, WinUI, WPF, PowerToys-style tool, Microsoft Store app, music/photo/creative app, Tauri desktop, Electron desktop, or any Windows desktop deliverable. Builds Windows 11/12 apps across system-like WinUI 3, branded WinUI 3, Tauri 2, and Electron. ALWAYS ask which track first. SKIP when the user explicitly wants only Apple, Android, or web-in-browser.

Use for web apps, landing pages, dashboards, React/Next/Vite/Tailwind frontends, web UI reference planning, animation, motion, scrolling, GSAP, Motion, Lenis, command palettes, split panes, and frontend interaction decisions. Builds web surfaces with the right surface type, visual direction, hierarchy, motion, layout, copy, assets, and anti-slop discipline. ALWAYS choose surface type and ask which aesthetic direction first. SKIP when the target is a native desktop/mobile app.

Use when the user asks for UX, product flow, user journey, wireframes, usability, conversion, onboarding, checkout, signup, navigation, forms, state design, dashboard workflows, or making an app easier to use over time. Designs and audits user experience flows, information architecture, forms, onboarding, dashboards, settings, empty/loading/error states, activation, retention, and repeated-use product ergonomics before visual polish. Pair with platform UI skills after the UX flow is clear.

Use when the user asks for design tokens, translate these tokens, export tokens, make a Compose color scheme from a Figma palette, audit tokens, or share a single token source across web and native. Generates, audits, and translates W3C DTCG tokens to Tailwind v4 @theme, Compose Material3 ColorScheme and Typography, SwiftUI Color/Font extensions, and WinUI ResourceDictionary. SKIP when no token work is involved.

Use when the user asks to build, design, mock up, scaffold, audit, or improve any interface, flow, screen, page, component, app, UX, onboarding, checkout, dashboard workflow, or product flow and the target platform or flow is ambiguous. Routes to ux-design, web, Windows, Apple, Android, cross-platform, or design-token skills. SKIP when the request explicitly names one platform and no UX flow work is implied.

Use when the user wants one codebase across web, iOS, Android, Windows, and Mac, asks for the same app on all platforms, or names Compose Multiplatform, Tauri 2, React Native, Flutter, .NET MAUI, Avalonia, or Uno Platform. Builds cross-platform UI by translating each surface into the host platform's native idiom rather than pixel-cloning. SKIP when only one platform is targeted.

Build apps for iOS 26 / iPadOS 26 / macOS 26 (Tahoe) / watchOS 26 / visionOS 26 across all common stacks — system-like SwiftUI, branded SwiftUI (HIG + custom identity), React Native, Flutter Cupertino, and Electron/Tauri 2 for macOS. Use when the user asks for SwiftUI, an iOS app, iPad app, Mac app, Apple Watch app, visionOS app, an App Store deliverable, or anything Apple-platform deliverable. ALWAYS ask the user which track first — do not default to SwiftUI. SKIP when the target is only And...

Use when the user asks for an Android app, Compose UI, Material 3, Material You, Pixel-style app, foldable adaptive layout, React Native Android, Flutter Android, Compose Multiplatform, or any Android deliverable. Builds Android 16+ apps across system-like Compose, branded Compose, React Native, Flutter, and Compose Multiplatform. ALWAYS ask which track first. SKIP when the target is only iOS, Windows, or web-in-browser.

Use when the user mentions stark, anti-slop UI, polished UI, UX, product flow, user journey, frontend design quality, design audits, design translation, asset planning, image generation for UI, visual references, animation, motion, scrolling, interaction techniques, or non-generic app/website design. Routes the agent to UX, web, Windows, Apple, Android, cross-platform, asset-selection, interaction, and design-token skills before generic frontend implementation.

UI components and utilities for AndroidBooster. Use when building XML/DataBinding list screens, image loading, dialogs, snackbars, or display/unit conversions. For Compose lazy list components, use androidbooster-ui-compose.

Compose lazy list components for AndroidBooster. Use when building Compose list UIs with ComposeDataColumn or ComposeDataRow, DataItem models, pull-to-refresh, initial loading, endless pagination, or custom progress indicator colors.

Build premium, dark-themed hero sections and landing pages with cinematic video backgrounds, liquid glass morphism, editorial typography, and pixel-perfect specifications. Based on the Viktor Oddy methodology of detailed design prompts that produce agency-quality results from AI code generation. Use when building hero sections, landing pages, or any premium dark UI.