设计与三维建模

使用 Transformers.js 直接在 JavaScript/TypeScript 中运行前沿机器学习模型。支持 NLP（文本分类、翻译、摘要）、计算机视觉（图像分类、目标检测）、音频（语音识别、音频分类）和多模态任务。使用 Hugging Face Hub 的预训练模型，通过 WebGPU/WASM 在浏览器及 Node.js、Bun、Deno 等服务端运行时工作。

Use when building Apple TV apps — focus-based navigation, Siri Remote interactions, or media/video streaming UI.

Implement and test advanced TypeScript types and inference; not diff review or runtime validation.

Implement and test advanced TypeScript types and inference; not diff review or runtime validation.

Implement and test advanced TypeScript types and inference; not diff review or runtime validation.

Craft depth for interface type inside an established visual direction: the evidence-backed type assessment, role scale, measure and leading, font loading and fallback metrics, script coverage, and verifying text under stress. Pull when a specific type defect needs fixing, such as a heading that wraps badly in one language or text that reflows as fonts load.

使用 Playwright 录制精美的 UI 演示视频。当用户要求为 Web 应用创建演示、操作演示、屏幕录制或教程视频时使用。生成带有可见光标、自然节奏和专业质感的 WebM 视频。

面向高级 UI 设计师的设计系统工具包，包括设计变量生成、组件文档、响应式设计计算和开发交接工具。适用于创建设计系统、保持视觉一致性，以及促进设计与开发协作。

在构建设计系统时使用：设计令牌、组件文档、响应式尺度或开发者交接。使用 design_token_generator.py 生成令牌。

Audits and refines existing UI layouts for optical alignment, baseline consistency, visual hierarchy, tabular numbers, and micro-interaction polish. Use when upgrading rough prototypes into production-grade interfaces.

Interaction judgment for interfaces: start from the decisions, reduce effort, act next to the object, one gesture per decision, only valid choices, truthful async state, local waits, preserved user edits, undo and drafts, one vocabulary, stable layout and complete states, host conventions and focus, and long labels. Pull when designing or reviewing how a screen or a control behaves, or when choosing between two UI options.

UI/UX 设计智能。50 种风格、21 套配色、50 组字体搭配、20 种图表、9 个技术栈（React、Next.js、Vue、Svelte、SwiftUI、React Native、Flutter、Tailwind、shadcn/ui）。操作：规划、构建、创建、设计、实现、评审、修复、改进、优化、增强、重构、检查 UI/UX 代码。项目：网站、落地页、仪表盘、管理面板、电子商务、SaaS、作品集、博客、移动应用、.html、.tsx、.vue、.svelte。元素：按钮、模态框、导航栏、侧边栏、卡片、表格、表单、图表。风格：玻璃拟态、黏土拟态、极简主义、粗野主义、新拟态、便当网格、深色模式、响应式、拟物化、扁平设计。主题：配色、无障碍、动画、布局、排版、字体搭配、间距、悬停、阴影、渐变。集成：用于组件搜索和示例的 shadcn/ui MCP。

Designs token-driven UI/UX systems with fluid typographic scales, 8px spatial grids, WCAG AA/AAA perceptual contrast, and complete interactive component states. Use for building cohesive design systems, dashboards, and web applications.

Cheap small business web design: the site's own MCP server — enquiry (enquiry = a human handoff,...

Web design Guildford: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

Web design Woking: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

Web design Basingstoke: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

Web design Cheltenham: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

Web design Poole: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

Web design Suffolk: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

Web design Sussex: the site's own MCP server — enquiry (enquiry = a human handoff, not a...

Inspect and remove C2PA content credentials from AI-generated images, video and audio. Free, no key.

可选的音乐启发式构思增强器。将 Michael Luchtan（Music For Robots）的一首未量化声学作品导入安全的私有目录，使多模态智能体能够分析微时序漂移与和声转折，从而为发散式头脑风暴和创造性问题解决提供参考。

Audit UI design, extract Design DNA, generate tokens, and create transformation blueprints.

AI visual generation agent: multi-pipeline rendering, prompt crafting, and image composition.

useVyre component context for AI agents — valid props, variants, anti-patterns, and design tokens.

按照 3C 原则（卡片、对话、确认）和 INVEST 标准创建用户故事，包含描述、设计链接和验收标准。适用于编写用户故事、将功能拆分为待办事项或定义验收标准。

How a project's Confluence is read and written: the project's spaces and pages from its standard's wiki.md, what the tools cannot read, how a page carries Jira macros, mentions and diagrams, and how the skills that write a page write and revise it. Applies whenever Confluence, a wiki page, a space or a design doc page, is searched, read or written.

Use when writing or reviewing any visible copy — headlines, buttons, body, errors, empty states — inside a design-method move or standalone.

面向高级 UX 设计师和研究员的研究与设计工具包，包括数据驱动的用户画像生成、旅程映射、可用性测试框架和研究综合。适用于用户研究、画像创建、旅程映射和设计验证。

Audit a site's UX the way a design-literate reviewer would, with a concrete fix for every finding.

Separate the hard constraints that decide whether an option is admissible at all from the soft criteria that rank the admissible ones — then gate before you rank, so a beautiful invalid choice cannot outscore a plain valid one. Use this whenever you are about to pick, shortlist, or recommend from a set: choosing a library or vendor, triaging bugs to fix, screening candidates, selecting a design, or scoring alternatives against a rubric. Also use it when a scoring scheme deducts points for a violation that should have been disqualifying, when someone asks for N options and only two clear the bar, or when you notice a favourite you are about to justify. Not for running the head-to-head comparison once the admissible set exists (that is blind-evaluation), not for wording the final claim (falsifiable-claims), and not for checking your own work is finished (superpowers:verification-before-completion).

Design a detailed value proposition using a 6-part JTBD template — Who, Why, What before, How, What after, Alternatives. Use when creating a value proposition, analyzing customer value delivery, or articulating why customers should choose your product.

Generate video, images, speech and music with 120+ AI models and render TSX videos to MP4

Optional: run a design-system consistency and AI-taste review with gstack /design-review when the change touches the design.

Trace authoritative spec requirements to existing code evidence; not general diff or design review.

Trace authoritative spec requirements to existing code evidence; not general diff or design review.

Trace authoritative spec requirements to existing code evidence; not general diff or design review.

Read public videos (TikTok, YouTube, Instagram, X) as text. Pay per video with x402.

Make, edit, or render videos with HyperFrames (HTML to deterministic MP4), tuned to this toolchain: PR and release videos after ship, product promos from a URL or show-off page, concept explainers, and short motion graphics for X devlog posts. Front door for HyperFrames - read this before the hyperframes skill: it bootstraps the upstream skills, pre-selects the workflow, sets media and output defaults without a HeyGen account, and hands the MP4 to devlog/twitter. Use when the user asks to make, create, or render a video, PR or changelog video, release reel, launch promo, demo clip, motion graphic, or explainer, or mentions hyperframes. Not for AI-generated footage or text-to-video clips (vd:omnimedia), slide decks (vd:opendesign), recording a browser session (vd:agent-browser), still images (vd:marketing-design), or a video the user wants built in Remotion (porting Remotion source to HyperFrames is in scope).

Create on-screen text hooks and captions for short-form video clips. Built around the Complementarity Principle - on-screen text should ADD to what the viewer hears, not repeat it. Includes podcast clip workflow, hook categories, and Triple Word Score optimization.

适用于视频策略、脚本、YouTube SEO、短视频流水线（Reels、TikTok、Shorts），或在编写脚本前将长内容转化为视频。按平台设定钩子、结构和内容再利用方式。

从YouTube及其他平台下载视频，用于离线观看、编辑或归档。支持多种格式和质量选项。

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

実写素材のカット、構築、強化のためのAI支援ビデオ編集ワークフロー。生の撮影素材からFFmpeg、Remotion、ElevenLabs、fal.aiを経て、DescriptまたはCapCutで最終仕上げを行う完全なパイプラインをカバーする。ユーザーがビデオの編集、素材のカット、vlogの作成、またはビデオコンテンツの構築を望む場合に使用する。

AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pipeline from raw capture through FFmpeg, Remotion, ElevenLabs, fal.ai, and final polish in Descript or CapCut. Use when the user wants to edit video, cut footage, create vlogs, or build video content.

AI辅助的视频编辑工作流程，用于剪辑、构建和增强实拍素材。涵盖从原始拍摄到FFmpeg、Remotion、ElevenLabs、fal.ai，再到Descript或CapCut最终润色的完整流程。适用于用户想要编辑视频、剪辑素材、制作vlog或构建视频内容的情况。

Composite a graphic onto video — text, a logo/image, a static transparent PNG, or an animated effect — and place it accurately, including locking it to a moving subject (a face, eye, hand, object). Use whenever the user wants to add/overlay/burn-in/stick something onto footage, place a watermark or label, or position a graphic precisely. Covers transparency (RGBA), animated overlays, timed windows, and coordinate-finding.

Create cinematic product videos from frontend projects or webpages with Remotion, real page captures, shot cards, the Ink Press template, beat sync and sound design. Use for full product promos, reproducing Ink Press, single shot-card effects, or finding, adding, replacing and aligning sound effects in an existing product video or shot, including candidate-only SFX searches. 用真实页面、镜头卡与 Ink Press 模板制作产品宣传片；用户要求用 video-shotcraft 做视频、复刻模板、制作单镜头，或给已完成的产品片/镜头找音效候选、加音效、换音效、对齐声音时使用。

Join two clips with a visible transition effect (wipe, slide, dissolve, pixelize, circle open/close, fade-to-black, etc.) using ffmpeg xfade. Use whenever the user wants a transition between shots/scenes, a scene change with an effect, or anything beyond a hard cut. For a barely-visible seam between adjacent cuts use the splice command instead; for generative effects on the footage itself use grok-video-edit.