
Claude Skills by nexu-io
github.com/nexu-ioSemantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
SwiftUI 前端设计 skill — anti AI-slop rules, design direction advisor, brand asset protocol, and five-dimension review. Works with Claude Code, Cursor, Codex, and OpenCode.
Swiss-inspired creative-mode presentation template skill with bold editorial typography, high-contrast geometric cards, interactive slide navigation, theme switching, hotspot overlays, and palette choreography in a single-file HTML artifact. Use when users ask for a premium presentation-style landing, a Swiss/brutalist deck look, or a creative launch page with rich interactions.
Swiss-style user-research narrative template in warm-paper editorial aesthetics. Use when users ask for a premium research deck or story-first live artifact with minimalist typography, high-clarity layout, subtle motion, donut breakdowns, and keyboard/click navigation across slides in a single HTML file.
The original v1 taste-skill, preserved for projects depending on its exact behavior. The current default is `design-taste-frontend` (v2 experimental), which is a substantial rewrite. Use this v1 install name only if you need exact backward compatibility.
Anti-slop frontend skill for landing pages, portfolios, and redesigns. The agent reads the brief, infers the right design direction, and ships interfaces that do not look templated. Real design systems when applicable, audit-first on redesigns, strict pre-flight check.
Apply professional font and color themes to artifacts including slides, docs, reports, and HTML landing pages. Ships 10 pre-set themes.
Three.js skills for creating 3D elements and interactive experiences in the browser — scenes, materials, controls, and post-processing.
Opinionated, evolving constraints to guide agents when building interfaces. Useful for keeping output coherent across many small UI pieces.
Catalog-only UI/UX Pro Max entry. The full upstream templates, data, and search workflow are not bundled in OpenDesign.
Music generation queueing, retrieval, and completion endpoints via Venice.ai. Suited for jingles, background loops, and prototype scoring.
Text-to-speech models, voices, formats, and streaming via Venice.ai. Useful for narration, voiceover, and conversational agent voices.
Image edits, upscaling, and background removal via the Venice.ai API.
Image generation endpoints and available styles via the Venice.ai API.
Video generation and transcription workflows via the Venice.ai API.
Cursor light trail, chromatic rays, and directional flares for word-by-word quote reveals in video intros.
Download videos from YouTube and other platforms for offline viewing, editing, or archival with support for various formats and quality options.
Hyperframes / Remotion-compatible continuous frame animation with autoplay support.
Build complex claude.ai HTML artifacts with React and Tailwind. Anthropic's reference workflow for shipping rich, embeddable artifacts.
网站复刻 / 克隆方法论。USE WHEN 用户说 复刻网站、克隆网站、clone website、抄个站、仿站、 照着这个站做一个、reproduce site、还原某个网页效果、把这个站搬下来改成我的、 复刻某个交互/WebGL/Canvas/Three.js 效果。提供「先拿真源码 → 判路径 → 逆向拆解 → 搭工程 → 替换内容」的可移植决策树,覆盖静态站 / React-Vue-Next 内容站 / WebGL-Canvas 重前端站三大分支,并强制核对任何 AI 二手分析里的可执行代码。
Review UI code for Web Interface Guidelines compliance by the Vercel engineering team. Covers layout, typography, color, motion, and accessibility for product UI.
WeRead-inspired HyperFrames video template for vertical annual reading reports, personal reading dashboards, book-note recaps, and shareable year-in-review stories. Use when users want a 9:16 HTML-to-MP4 reading report with warm paper texture, editorial Chinese typography, book-page metaphors, data highlights, and deterministic motion.
WordPress Design System. Apply WordPress's official design tokens, typography, and component patterns to themes and sites.
Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style", "audit prose", "review docs voice and tone", or "check this page against the writing handbook".
YouTube clip generation and editing with automated workflows — pull source video, slice highlights, add captions, and export.
A small deck template fixture.
First fixture skill with a runnable demo.
Instruction-only fixture skill.
Short-form video generation skill — 3-10 second clips for product reveals, motion teasers, ambient loops. Defaults to Seedance 2 but works the same with Kling 3 / 4, Veo 3 or Sora 2. Output is one MP4 saved to the project folder. When the workspace also ships an interactive-video / hyperframes skill, prefer composing several short shots into a single timeline rather than one long monolithic clip.
Prepare required media inputs within an existing OD Next plan. Reuse capability evidence, acquire and measure assets efficiently, and resolve asynchronous jobs without removing required content or weakening quality standards.
Substack / Medium 高级感长文排版, 适合公众号、博客发布
杂志感长文, 含 masthead、hero、figures、pull quote、作者署名
推特金句 / 数据卡, 适合配推文
小红书风格知识卡片, 多张联排可滑动浏览
固定侧栏 + 顶栏 + KPI 网格 + 1-2 张图
把 CSV/Excel/JSON 数据转成漂亮的可视化报告页
消费感配对仪表板: 信号 ticker + KPI + 30 天柱状 + 趋势
奶油纸 + 锈红 + 蓝图网格 mask + 黑边硬卡片 + pipeline 盒
暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页
8 页单色背景, 160px display + 4px accent + Mono 箭头列表
深夜渐变 + 漂浮 orbs + SVG 力导向图谱 + JetBrains Mono
电子杂志 × 电子墨水; 10 个版面 + 5 套调色板 (墨水/靛蓝瓷/森林墨/牛皮纸/沙丘)
黑底 + CRT 网格扫描线 + $ 命令行标题 + 薄荷绿大字 + 三档 tag
电子杂志 × 电子墨水风, WebGL 流体背景 + 衬线 display
GitHub-dark + 紫蓝环境光 + 三色渐变标题 + GitHub 风代码
锁死 1920×1080 画布, React 组件级自由组合, 不绑模板
10 页融资 deck, 白底 + 蓝紫渐变 hero, traction 柱状, $X.XM ask
tokyo-night 默认主题, T 切换 5 主题, S 打开提词器 popup
暗 hero + 亮内容, 橙→桃 accent, 特性卡 + 定价 + CTA
Replit Slides 八套主题 (helix/holm/vance/bevel/world/atlas/bluehouse)