Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Design & UI
Build interface motion that would pass a strict review. Decides whether something should animate at all, names its purpose, picks the cheapest tool, the right properties, the curve, the duration or spring, the origin, how it interrupts and how it exits, then writes the implementation with reduced-motion built in. Use when asked to animate, add motion, add a transition, make something feel alive, or when building any component that enters, exits, moves or changes state. For scroll-driven and WebGL work use scroll-and-webgl.
Create, revise, audit or polish submission-grade manuscript figures for Nature-family and other high-impact journals using Python or R. Covers multi-panel scientific plots, matplotlib/seaborn, ggplot2/patchwork/ComplexHeatmap and journal-ready SVG/PDF/TIFF exports. Also use for OpenRouter GPT Image 2 graphical abstracts, concept or mechanism schematics when the user explicitly requests AI generation. Establish the figure conclusion, evidence logic and exports before execution; honor the chosen or saved plotting backend. Trigger on paper figures, scientific/academic plotting, manuscript data visualization, 论文配图、学术写作配图、科研绘图、科研作图、画图、作图、出图、论文图表、可视化、论文示意图、机制示意图、图形摘要. Not for dashboards or Illustrator/Figma-first infographics.
Move design work through Bitwarden's Product and Design Jira workflow — final designs attached to tickets, the 30/60/90 critique cadence tracked in Figma, status transitions on engineering epics and stories, and the one-off engineering story flow.
Elite Website Reviewer Agent for AEO, GEO, SEO, UI/UX Psychology, and Copywriting. Use this skill when asked to review or evaluate a website's positioning. It conducts an EXHAUSTIVE, multi-page, psychologically-driven, and ruthless analysis of the entire website. Produces a massive, comprehensive, scored report with charts and actionable fixes. NO EMOJIS allowed.
Use when implementing animations, transitions, or motion effects in React apps. Invoke this skill whenever someone asks about animation, transition, motion, framer motion, react spring, GSAP, entrance/exit effects, scroll animation, parallax, gesture, drag, card flip, screen shake, health bar, damage numbers, loading states, page transitions, hover effects, or any element that should move, fade, scale, or respond to interaction — even if they don't use the word "animation".
Write, rewrite, edit, review, or localize Russian text for interfaces, marketing materials, and documentation, or generate an interface component that contains Russian text. Use only for UI copy; marketing copy such as landing pages, product pages, ads, promotional emails, campaign messages, and promotional social posts; and documentation such as user guides, technical documentation, instructions, README files, help content, and API references. Do not use for ordinary answers, explanations, discussions, correspondence, meeting notes, support replies, editorial articles, or other Russian text outside interface, marketing, and documentation work.
Spectacle, budgeted. Scroll-driven animation with native CSS first and GSAP ScrollTrigger when needed, smooth scrolling with Lenis and when to turn it off, split-text reveals, pinned scenes, canvas and WebGL on a performance budget, shaders as material, pausing off-screen, loading strategy, and the reduced-motion and no-JS fallbacks that keep the page readable. Use for marketing pages, portfolios, launches and hero sections. Never for product UI.
Make impressive, on-brand presentation slides and decks end-to-end, for ANY design system. Use this skill whenever the user wants to brainstorm, build, design, generate, review, or export a slide, deck, presentation, pitch, or company/product/sales deck. It runs as job-specific WORKFLOWS: brainstorm a deck's structure, generate the HTML deck with a review loop, and export to editable PPTX, image PPTX, standalone HTML, or PDF. It is design-system-agnostic — it uses the user's own design system if they have one, a `nextlevelbuilder/ui-ux-pro-max-skill` suggestion if that's installed, or a bundled neutral default theme — and drives everything from design tokens (never hardcoded colors or fonts). It ships a token-driven brand kit (tokens, fonts, logos, 34 premade layouts), a "wow" craft guide, an anti-slop validator, a ready-made React deck template, point-and-comment edit mode, and a validated editable-PPTX pipeline. It can also supply just the design layer (tokens, components, patterns) to another slide generator so its output uses a real design system instead of a generic theme.
Query and apply The Website Specification — a platform-agnostic specification of what a good website does, with each item tagged required, recommended, optional, or avoid. Use when the user asks what their site should have, whether something is required, how to audit a URL, what's missing for agent readiness, or anything else where you'd otherwise be guessing at web best practice. Backs answers with primary sources (WHATWG, W3C, IETF RFCs, IANA, WCAG). Available as Markdown over HTTP and as an MCP server with search, list, fetch, checklist, and audit tools.
Design and build UIs with Google Stitch using @_davideast/stitch-mcp as the proxy and CLI. Covers screen generation, editing, variants, design systems, site building, prompt engineering, and the DESIGN.md spec. Updated for Stitch's March 2026 infinite canvas, 4-mode AI, and first-class design systems.
Integrates shadcn/ui into React apps generated from Stitch designs. Component discovery and installation, token alignment with Stitch design system, customization patterns, and blocks (auth, dashboard, sidebar). Use with stitch-react-components or stitch-nextjs-components.
Converts a Stitch mobile screen, a local HTML file, or a URL into SwiftUI views for native iOS apps — VStack/HStack/ZStack layout mapping, Color asset tokens with dark mode, NavigationStack/TabView routing, and Xcode project structure. Only the Stitch route needs an API key.
Invoke FIRST, before creating, editing, or deleting components, stories, styles, CSS, themes, colors, or design tokens — anything that changes how the UI looks, no exceptions. Also for starting or previewing Storybook to verify UI, requests to show, browse, or list components, stories, or UI states, and docs, props, or usage lookups.
Colour, elevation and material for interfaces. Neutral palettes that survive dark and light mode, semantic tokens, borders versus shadows by theme, alpha overlays, contrast that passes, a single accent used sparingly, glass and blur budgets, theme switching without a flash. Use when building a palette, adding dark mode, fixing colours that look "muddy", "cheap", "flat" or "washed out", or when shadows and borders look wrong in one theme.
Implements the Syncfusion ASP.NET Core TimePicker component (EJ2). Use this skill when the user needs to add a time picker, time selection input, time field, or clock picker in an ASP.NET Core application. Trigger this skill for: TimePicker setup, time range configuration, strict mode, time masking, masked time input, globalization, RTL support, localization, accessibility, keyboard navigation, CSS customization, custom styling, form validation with TimePicker, TimePickerFor model binding, time format configuration, time step interval, floating label, clear button, full screen popup, popup behavior, scroll position, server timezone, and any scenario involving ejs-timepicker tag helper or Syncfusion EJ2 TimePicker.
Implements the Syncfusion .NET MAUI DatePicker (SfDatePicker) control for date selection. Use when implementing date pickers, adding date selection UI, or working with the SfDatePicker control. Covers date picker appearance customization (headers, footers, columns), date formatting (20+ predefined formats), date restrictions (min/max dates, blackout dates), and picker modes (Dialog, RelativeDialog).
Implements Syncfusion .NET MAUI DateTimePicker (SfDateTimePicker) control. Use when implementing date and time selection, datetime pickers, or date-time input interfaces in .NET MAUI applications. Covers DateTimePicker setup, formatting dates/times, picker modes (dialog/relative), customization, date restrictions, intervals, events, localization, and accessibility.
Write Tailwind CSS following practices that keep a fast-to-write codebase maintainable — use design tokens instead of magic values, keep class lists short, group tokens semantically, generate classes in consistent order, avoid @apply for extracting repeated styles, and use fixed variants instead of arbitrary className props. Use this whenever writing or editing Tailwind classes, components, or config, and also when reviewing, cleaning up, refactoring, or auditing an existing Tailwind project. Do NOT use for general CSS architecture unrelated to Tailwind, or for build tooling unrelated to CSS output (bundlers, JS minification, etc.).
Build, review, debug, migrate, or plan TanStack Charts Alpha (0.18.x) charting with current docs. Use for @tanstack/charts, @tanstack/charts/react, @tanstack/charts/react-native, @tanstack/charts/scales/*, defineChart, scales registry (scales.x/scales.y, named scales, multiple axes), svgAnimation, motion(), tooltip/portal, layout stack/group, groupBy/binX/rollingWindow/rank/normalize/fold/waterfall/mosaic, lineY, areaY, barY (corner radius), boxY, violinY, waffleY, ridgelineY, differenceY, linearRegressionY, rect, cell, dot, hexagon, crosshair, whenFocused, decorative, facet, polar, geoShape, treemap, sunburst, sankeyDiagram, hexbin, contour, brushX, zoomX, keyedSelection, colorLegendItems, gradients, focusRing, Chart, Canvas, canvasChartRenderer, grammar-of-graphics marks/channels/scales, and migrations from Recharts, Chart.js, ECharts, Observable Plot, archived react-charts, @tanstack/react-charts, @tanstack/charts-scales, or pre-Alpha TanStack Charts 0.0.x–0.15.x (root x/y scales).
Senior WebGPU & 3D Graphics Architect for 2026. Specialized in Three.js v172+, WebGPU-first rendering, TSL (Three Shader Language), and high-performance React 19 integration via `@react-three/fiber` and `@react-three/drei`. Expert in building immersive, low-latency, and accessible 3D experiences for the modern web.
Design token audit and enforcement skill. Finds every hardcoded color, spacing value, shadow, border radius, font size, and z-index in the codebase, maps them to an existing or proposed token system, then replaces hardcoded values with tokens — making the design system maintainable, themeable, and dark-mode-ready. Use when user wants to set up a token system, enforce design consistency, prepare for dark mode, or invokes /tokens.
Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns, forms, tables), customizing themes and colors, implementing dark mode, generating visual designs and posters, or establishing consistent styling patterns across applications.
Use when working with Vunor, the Vue 3 + UnoCSS design system and component library. Covers presetVunor, vunorShortcuts/defineShortcuts/mergeVunorShortcuts, VunorVueResolver, Nuxt module, Vu-prefixed components, semantic UnoCSS classes (scope-*, layer-*, surface-*, current-*, c8-*, i8-*, card, fingertip, spacing, typography), public composition primitives (btn, menu-item, popup-card, i8-bare, disabled-soft), palette/theme tuning, and shortcut override patterns. Imports: vunor, vunor/theme, vunor/utils, vunor/vite, vunor/nuxt.
Best practices for designing UI widgets in xmcp. Use when creating interactive widgets for GPT Apps or MCP Apps, choosing between React components and template literals, designing widget layouts, handling state and data fetching, or troubleshooting widget rendering issues.
Generate an interactive HTML diagram of the user's business systems, workflows, or tooling — showing how everything connects, where data flows, which AI agents / scheduled tasks run when, and how processes hang together. Use this whenever the user says 'visualize my workflow,' 'map my systems,' 'show me how this all connects,' 'business OS,' 'system diagram,' 'workflow map,' or wants to see the architecture of their work as a picture rather than a list. Output is a single self-contained HTML file with clickable nodes and progressive disclosure of detail.
Use when writing, reviewing, or rewriting user-facing error messages, validation messages, form errors, empty/error states, auth errors, failure notifications, retry/support copy, CLI errors, or API errors humans will read. Helps make errors specific, actionable, non-blaming, accessible, and safe without leaking sensitive details.
Interfaces with a model in the loop. Streaming text without layout thrash, thinking and reasoning states, tool calls and their status, approvals, citations, the composer, stop and regenerate, scroll pinning, markdown rendering, latency masking, and honesty about what the system is doing. Use when building chat, copilots, agent dashboards, AI features inside a product, or anything that shows model output as it is produced.
Build React frontends for LiveKit voice AI agents. Use this skill when creating web interfaces for voice assistants using LiveKit's shadcn-based Agents UI components. Covers AgentSessionProvider, audio visualizers, media controls, chat transcripts, and customization with Tailwind CSS.
This skill should be used when the user asks about "data journalism", "data visualization", "data storytelling", "FOIA request", "RTI request", "spreadsheet analysis", "chart design", "act as a data journalist", "data journalist mode", "infographic", "open data", "statistical analysis for journalism", "investigative data", "public records", "Datawrapper", "Flourish", "Tableau Public", "D3.js", "chart type selection", or needs expertise in finding, analyzing, and visualizing data for journalistic storytelling. Part of the AlterLab FC Skills collection (New Media & Communication department).
Provides Apple's Human Interface Guidelines (HIG) for designing, building, and reviewing native UI/UX on iOS, iPadOS, macOS, watchOS, tvOS, and visionOS. Covers system components (buttons, sheets, menus, lists, pickers, navigation), input methods (gestures, Apple Pencil, Digital Crown, Camera Control, keyboards), foundational design elements (color, typography, materials, motion, SF Symbols, accessibility, dark mode, app icons), interaction patterns (onboarding, search, drag and drop, notifications, undo/redo), platform-specific considerations, and technologies (Siri, Apple Pay, HealthKit, SharePlay). Use whenever the user is designing, building, or reviewing UI for an Apple platform, choosing between system components, asking what Apple recommends for an interaction or visual element, checking HIG compliance, or asking about Apple design terminology — even without saying "HIG" explicitly.
Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components—not for simple single-file HTML/JSX artifacts.
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing. Triggers: remove background, background removal, remove bg, transparent background, cut out image, background remover, rembg, product photo editing, cutout, transparent png, bg removal, photo cutout
Use when the user needs to turn content (articles, notes, screenshots, data, product descriptions) into Chinese image-and-text card sets — Xiaohongshu / Rednote 3:4 vertical images, WeChat official account covers, social cards. Provides three exclusive visual languages (Still Paper 本手记 / Signal Proof 证据层 / Bridge Canvas 跨平台桥): Claude reads the content and writes brief.json itself, then hands it to a deterministic engine that renders a card set that is striking at first glance, instantly recognisable, and ready to use out of the box in China.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.