Design & UX

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.

Low-fidelity wireframe exploration to test layout and information hierarchy before committing to hi-fi. Produces 3+ layout variants using ASCII art, each annotated with layout strategy, information priority, and content block breakdown.

交付前五道质量检查合为一体：AI 味检测、可访问性审查、层级与节奏审查、交互状态审查、终检汇总。前四项独立检测，第五项引用前四项结果做汇总判定，不重复检测。产出最终 QAReport（含 P0/P1/P2 优先级和交付判定）。

Overlays a floating control panel on the prototype allowing real-time adjustment of color tokens, type scale, font weight, spacing multiplier, radius, and shadow parameters. Changes reflect instantly. On user confirmation, syncs back to DesignSystemManifest.

Generates high-fidelity HTML prototypes strictly following the DesignSystemManifest. Uses defined colors, fonts, spacing, and components. Includes all interaction states, responsive layout, semantic HTML, prefers-reduced-motion support, and real content. Auto-triggers AI-slop detection after generation.

Generates an HTML slide deck following the design system. One core message per slide, max 6 lines, clear visual hierarchy, keyboard navigation, 0.2-0.3s transitions with prefers-reduced-motion support.

Explores variations on an existing prototype. After a prototype exists, generates hi-fi variants along 2-3 design dimensions (warmth vs cold vs playful, loose vs dense density, light vs heavy visual weight). All variants share the same design system, differing only on selected axes. User picks or mixes.

Generates 3-4 distinct aesthetic directions after starter kits have been rejected or when the user explicitly requests custom directions. Each direction has a clear aesthetic thesis, named color palette, font pairing with rationale, layout concept with ASCII wireframe, and a signature element. Rejects AI default aesthetics.

Structured discovery questionnaire for new design tasks. Asks minimum necessary questions covering product, audience, page goal, output format, existing assets, and variant requirements, then compiles answers into a DesignBrief.

从用户提供的截图/URL/代码库/品牌资料中提取设计 Token（配色、字体、间距、圆角、阴影、卡片样式），并细化所有可复用组件的完整规范（变体、状态、尺寸）。一个技能覆盖 Token 抽取与组件细化两个阶段。

10 prebuilt aesthetic templates, each a complete design system. When the user has no brand assets and needs a fast start, show these kits first — selecting one skips ConceptRoutes and generates DesignSystemManifest directly. Falls back to frontend-aesthetic-direction only if none fit.

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics. Trigger scenarios — use when the user mentions any of: - UI design, frontend design, web design,...

71 套品牌级设计系统知识库，覆盖 AI/LLM、开发工具、生产力、金融科技、电商、媒体、汽车等 8 大类别。 每套系统包含 9 段标准结构：视觉主题、色彩、排版、组件、布局、深度、注意事项、响应式、Agent 指南。 触发词：设计系统、选择风格、品牌风格、设计令牌、DESIGN.md、配色方案

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.

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.

交付物生成工具：以假设驱动、证据分级和 Title Storyboard 为上游，使用统一 DeckSpec 与双引擎 Fusion 管线生成可审计的专业咨询 PPT；同时支持 Excel 测算底稿排版。 触发词：把这份分析做成PPT、出一份能直接汇报的演示文稿、产出ppt、帮我把测算结果整理成Excel、生成幻灯片。

AI video generation via Seedance 2.0 and Kling. Use when the user wants to generate a video clip — text-to-video, image-to-video, first/last-frame transitions, reference-guided generation, or generatively editing / extending an existing clip.

Guide for editing videos where the primary content is people talking — talking-head / 口播, interview / 访谈, lecture, tutorial, podcast, course content, and similar talking-driven formats. Use when the user wants speech editing on a talking video (剪口播 / 口播剪辑 / 去口癖 / clean up fillers / smooth speech), motion graphics layered onto talking video (口播加 MG / 加动画), or B-roll on a talking video (加 B-roll / add B-roll). For motion graphics specifically, use this together with the active Motion Graphics s...

AI shader generator for WebGL video effects, transitions, masks, and color grading (LUT / 调色 / 电影感 / film look). Use when the user wants a video effect (滤镜 / 特效), a transition (转场 / crossfade / wipe / cube / 3d), a mask (蒙版 / 遮罩 / reveal), a zoom / push-in (推近 / 推镜头), or a color grade — try the built-in effects (zoom, builtin LUTs) before generating a new shader.

Add, directly author, edit, and place editable Motion Graphics in ChatCut from WorkBuddy using inline JSX, existing library assets, and timeline tools.

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.

Defines and applies a brand's verbal identity — voice, tone, and messaging architecture. Use when establishing brand personality, adapting tone across contexts, or crafting mission/vision/value-proposition/positioning and key messages.

Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.

Audits creative assets and channels for brand consistency across visual identity (logo, color, typography, imagery), voice, and messaging. Use to review deliverables before publishing or to run periodic brand audits.