Design & UX

Design thinking and decision-making for web UI. Use when designing components, layouts, color schemes, typography, or creating aesthetic interfaces. Teaches principles, not fixed values.

Create distinctive, production-ready frontend interfaces with high visual quality. Use this skill whenever the user asks to build, design, or improve any web UI — including landing pages, dashboards, components, app screens, forms, or interactive widgets. Also trigger when the user says "make this look better", "redesign this", "add polish", "build a UI", "create a page", "style this", or references HTML/CSS/JS, React, Vue, Svelte, or any frontend framework. If the request involves any visibl...

Create museum-quality visual art through design philosophy. Generate original visual designs, posters, and artwork as PDFs or PNGs using sophisticated aesthetic movements and expert-level craftsmanship.

Documentation for Remotion - Video creation in React. TRIGGER when working with Remotion code, video composition, React-based video generation, or user mentions "remotion", "video composition", "create animation", "create video".

Design and implement distinctive, production-ready frontend interfaces with strong aesthetic direction. Use when asked to create or restyle web pages, components, or applications (HTML/CSS/JS, React, Vue, etc.).

Spec CLI surface area before implementation - command tree, flags, exit codes, I/O contract. Use when designing or planning a CLI interface.

Interactive logo & brand design strategist. Runs a strategy workshop, narrows a creative direction, lands a single centralized concept, then outputs a condensed branding table plus 10+ logo ideas with rationale. Use when the user wants to design a logo, develop a brand identity, write a logo brief, brainstorm logo concepts, or run brand strategy before sketching. Triggers include "design a logo", "logo ideas", "brand identity", "help me with my logo", "logo brief", "what should my logo be".

Builds UI components, landing page sections, hero sections, and contact forms. Use when creating front-end visual elements.

Use after making changes to visually validate the app in the iOS Simulator. Builds, installs, launches the app, then uses screenshots and accessibility descriptions to verify the change looks and behaves correctly.

Front-end conventions review for Vue surfaces — the component-usage analog of /a11y, pointed at Nuxt UI 4 + crouton conventions instead of WCAG. Reviews just your diff (or a package/file) for v3 component names, the v4 overlay pattern, Options API, raw-HTML re-implementations, and hardcoded colors; rates findings by severity; and either comments inline on the PR (--comment) or applies the safe fixes for you (--fix). Steers the depth-aware `frontend-review` subagent. Use when asked to "check t...

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Detects and fixes patterns including: inflated symbolism, promotional language, superficial analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

产品图片的图形商标检测与相似度搜索。当用户提到商标检测、图形商标搜索、Logo侵权检查、商标相似度分析、图片商标风险评估、产品图片商标筛查、graphic trademark detection, logo infringement, trademark similarity, trademark risk, image trademark screening, Ruiguan时触发此技能。即使用户未明确说"商标检测"，只要其需求涉及将产品图片与已注册的图形商标进行比对或评估商标侵权风险，也应触发此技能。

基于睿观的产品图片政策合规检测，通过视觉相似度匹配识别潜在违规商品。当用户提到政策合规检查、产品图片合规、违规检测、禁售商品筛查、基于图片的合规审查、上架前风险排查、policy compliance detection, product compliance review, violation detection, image compliance check, product image risk screening, Ruiguan时触发此技能。即使用户未明确说"合规"，只要其需求涉及将产品图片与违规数据库进行比对，也应触发此技能。

品牌基因样式提取原子技能。根据商品图片与用户品牌基因参数（主色、字体、平台、地区、语言），提取统一的品牌视觉语言（Brand DNA），输出结构化 brandGeneJson 供下游原子技能消费。品牌基因提取、brand gene extract、brand DNA、品牌视觉定义、品牌调性提取、brand style extraction、visual identity extraction。被套图编排层（linkfox-aigc-imagegen-cloth / product 套图编排路径）在步骤三中调用；当用户说"提取品牌基因"、"定义品牌风格"、"brand gene"、"品牌视觉"时触发。

对原被告作品进行实质性相似比对与接触可能性评估，输出著作权侵权分析报告。触发：著作权比对/实质性相似/抄袭分析/作品相似/接触可能性/思想表达二分法。不触发：许可协议审查/合理使用判断/专利侵权比对/商标近似判断。

妙搭（Spark/Miaoda）应用开发与托管：应用创建、本地全栈开发、云端生成迭代、创意设计（UI mockup / 可交互原型 / 线框图 / 落地页 / 仪表盘 / 幻灯片 deck / 视觉探索）、AI相关能力和飞书平台能力或者其他外部能力集成、日志/Trace/监控指标/PV/UV 查询、环境变量管理、应用协作者与协作权限设置、应用角色与成员管理、自动化触发器（定时/记录变更/Webhook/飞书审批）。当用户要开发/新建一个系统·工具·平台·应用，或要本地开发 / 云端开发 / 修改 / 部署 / 发布 / 上线 / 拿可分享链接，或用 HTML 做页面·网站·部署到妙搭，或要设计 / design / mockup / prototype / wireframe / 做 PPT / deck / 视觉探索，或提到妙搭/Spark/Miaoda（应用运行时域名形如 *.aiforce.cloud）、应用数据库、应用文件存储、开放 API Key、可见范围、应用协作者/开发权限、应用角色/角色成员、线上日志、接口请求量、错误量、延迟、访问量、环境变量、给妙搭应用配自动化...

Use when users need visual direction, interface hierarchy, layout decisions, design specifications, or prototypes before implementing a Web or mini program UI.

图生 UI（截图/设计稿 → 画布设计稿）。将参考图片转化为可编辑的 ardot 设计稿。四阶段流水线：设计风格提取 → 结构化精细描述 → 反思校验 → Agent Teams 画布绘制。触发场景：上传截图/线框图/草图要求生成设计稿、还原界面、复刻页面、参照图片设计。

This skill should be used for any design-related tasks involving creating, editing, or modifying visual designs, UI screens, pages, layouts, or components, as well as converting designs to frontend code. Trigger phrases include: generate/create/design a page, design a screen, create a landing page, make a dashboard, design a login screen, modify the design, update the layout, change colors, add a component, edit design file, create wireframe, design a form, build a UI, generate homepage, crea...

Use this skill any time a PowerPoint .pptx or legacy .ppt file is involved as input, output, or both. This includes creating decks; reading or extracting slide content; editing presentations; combining or splitting slides; and working with templates, layouts, speaker notes, comments, charts, actions, or fonts. Trigger whenever the user mentions a deck, slides, presentation, PPT, or a .ppt/.pptx filename. Normalize legacy .ppt input before using PPTX workflows.

产品设计套件 Validate 阶段。当用户是设计师想做可用性测试（验证已有设计或原型是否好用）—— 从测试方案设计、任务剧本编写、现场观察记录、到严重度评级与修复优先级输出时启动的 Skill。与 Probe（探索性用研，设计前）形成阶段互补 —— Probe 挖"用户是谁、为什么"，Test 验"这个设计能不能用、卡在哪"。与 Check（设计师自查走查）的区别：Check 不需要真实用户，Test 必须真实用户操作。 本 Skill 覆盖可用性测试三阶段全流程：① Plan（测试目的 / 类型选择 / 招募 / 环境 / 设备）→ ② Script（3-7 个任务剧本 + 主持人脚本 + Think-Aloud 协议 + 反偏见提示）→ ③ Analyze（任务级数据汇总 / Nielsen 0-4 级严重度评级 / 频次矩阵 / 修复优先级 / 设计回流建议）。核心差异化：每条 finding 都附"任务 ID + 严重度 + 频次 + 原话 + 截图时间戳 + 建议修复方向"的证据链；输出 task_success_rate 等量化基线，直接喂给 Metric 做上线...

站点地图（IA 骨架）。基于 /设计简报（业务目标 / 用户）+ /用户故事（功能拆解 + 设计触点）输出可被 Flow Web/Mobile 直接消费的站点结构——主导航 + 页面层级 + 路由命名 + 关键 flow 概览。设计师不必从零拉树状图，AI 从上游字段直接生成 IA 骨架，再让设计师调整。 触发关键词：站点地图、sitemap、信息架构、IA、页面结构、路由设计、导航结构、有哪些页面、页面层级、Flow 之前的 IA 骨架。 排除（反向）：单屏内的交互流程（用 /Web页面设计 / flow-mobile）、视觉风格（用 board）、用户旅程（用 /用户旅程）、原型详细稿（直接用 flow-web/mobile）。

设计验收（Design QA / 还原度核查）。前端工程师或 coding agent 完成实现后，对照设计源（/设计简报 设计标准 + Flow Web/Mobile 输出）逐项核查实现还原度——按 9 个维度（间距 / 颜色 / 字体 / 圆角阴影 / 图标 / 交互态 / 状态完整性 / 响应式 / 可访问性）找出"实现 vs 设计源"的具体差异，输出可修复的 deviations 列表。 触发关键词：设计验收、Design QA、还原度、还原核查、UI 走查、对比设计稿、检查实现、QA、视觉回归、实现差异、间距不对、颜色不对。 排除（反向）：设计稿自身走查（用 /设计走查）、可用性测试（用 test）、完整无障碍审计（用 /无障碍检查）、性能 / 兼容性测试（开发自测）。

动效设计原则与策略层。基于 Three Pillars（情感意图 / 视觉叙事 / 动效工艺）+ 四大 Motion Personality 档位（Playful / Premium / Corporate / Energetic）+ Duration & Easing 表 + Disney 12 原则 + 1/3 编舞规则，为项目定义一套可被工程实施直接消费的「动效规范」：Personality 锚点 + 签名缓动 + Duration palette（quick/standard/slow）+ 入场范式 + per-element specs（property / duration / easing / stagger / 迪斯尼原则）+ 编舞预算 + prefers-reduced-motion 降级。 触发关键词：动效规划、动效规范、动效调性、motion design、motion personality、动效策略、入场动画、过渡动画、微交互、loading 状态、滚动触发、品牌动效、动效定调。 排除（反向）：不写 React/Vue/CSS 代码（用 /动效开发）...