Web & Frontend
Web development agent skills handle frontend and full-stack work: component patterns, CSS and accessibility fixes, performance budgets, and framework conventions. Install a skill once and your AI agent follows the same playbook in every project, from quick prototypes to production apps.
-
huiliyi37 Skill Visual AcceptanceUI/视觉改动交付前的终验方法论——多主题截图矩阵复现、像素真值判据链、CSS 层叠陷阱、布局漂移审查、before/after 存证。当视觉改动需要验收(而非实现)时使用:交付前最后一环,回答「看得见的部分真的对吗」。
-
hyperpuncher Bundle BasecoatGuide for Basecoat - a Tailwind CSS v4-first component library using semantic HTML and vanilla JS. Think "shadcn/ui without a framework." Use when building UI components without React/Vue/Svelte.
-
hyperpuncher Bundle DatastarBuild backend-driven, reactive web interfaces with Datastar and Datastar Pro. Use for data-* attributes, signals, actions, HTML or SSE patches, Datastar architecture, Pro plugins, or Rocket web components.
-
hyperpuncher Skill Modern CSSUse this skill when writing, reviewing, or refactoring CSS and HTML to replace legacy CSS, JavaScript-driven presentation, preprocessors, layout hacks, or unnecessary UI libraries with modern native web-platform features.
-
igniteui Bundle Igniteui Blazor ThemingTheming and visual customization for Ignite UI for Blazor: choosing and switching the built-in Bootstrap, Material, Fluent and Indigo themes in light or dark, scoping a theme to part of the page with IgbThemeProvider, generating palettes and component design tokens with the igniteui-theming MCP server, overriding CSS custom properties, using CSS shadow parts, dark mode, and global roundness/spacing/size tokens. Use when changing the look and feel of Ignite UI Blazor components, applying a color scheme, or writing component CSS. For component configuration use igniteui-blazor-components; for grid data features use igniteui-blazor-grids.
-
igniteui Bundle Igniteui Blazor ComponentsIgnite UI for Blazor non-grid components: project setup and module registration; form controls (input, textarea, combo, select, date/time pickers, calendar, checkbox, radio, switch, slider, rating, mask input); layout and navigation (tabs, stepper, accordion, expansion panel, nav drawer, navbar, tree, splitter, divider); data display (list, card, carousel, avatar, badge, chip, icon, progress, dropdown, tooltip, chat); overlays (dialog, snackbar, toast, banner); Dock Manager and Tile Manager; and visualizations (charts, gauges, maps, sparklines). Use for any Ignite UI Blazor component that is not a data grid. For data grids use igniteui-blazor-grids; for theming and CSS use igniteui-blazor-theming.
-
igniteui Skill Blazing Story StoryImplement a Blazing Story story file (.stories.razor) for a Blazor UI component. Use when the user says "create a story for component X", "add stories for X", or similar requests in a Blazing Story (.NET / Blazor / Storybook) project.
Audited -
igniteui Bundle Igniteui Blazor Lite TestingTesting in the IgniteUI Blazor (Lite) repository itself: the bUnit unit suite (tests/IgniteUI.Blazor.Tests — base classes, attribute/serialization specs, declarative interop wire contracts) and the Playwright integration suite (tests/IgniteUI.Blazor.Lite.IntegrationTests + TestBed — reflection-driven live-browser sweep, componentsConfig.json). Use when adding or changing tests in this repo, covering a new component, pinning interop behavior, or deciding which suite a check belongs in. Not for consumer-facing component usage — use igniteui-blazor-components for that.
-
elieandraos Bundle Laravel Inertia StackCompanion conventions for a Laravel + InertiaJS + Vue 3 + Pest stack, additive to Laravel Boost's laravel-best-practices and testing-best-practices skills — never a replacement for them. Activate for Laravel, Inertia, or Pest work on this stack — always alongside the matching Boost skill(s), never alone. See the routing table inside for the specific capabilities covered.
-
elmayii Skill BootstrapUse when a repository must be conditioned for continuous autonomous development (CDev) — a new repo, an existing one without docs/develop/, or a re-audit of one already conditioned; when the user asks to "bootstrap", "condition this repo for cdev", "prepare it so /cdev can work alone", "condicionar para cdev" — for any role (backend, frontend, other), with or without a folder of source docs.
-
elsa-workflows Skill Designer Architecture TourGive a concise architecture tour of elsa-foundation-designer (the Next.js Elsa Studio). Use when a user asks what the repo is, how to orient, where to start, or how the shell, modules, routing, API and auth fit together.
-
encurehq Bundle Next Tanstack QueryUse when reading or writing data in a Next.js App Router app with TanStack Query — a data fetch or mutation, prefetching for a route, hydrating a client query, a form or dialog that submits, an optimistic update, or cache invalidation after a write. Use when the user says "fetch X", "load data for", "prefetch", "hydrate", "table blanks when I search", "mutate", "submit form", "optimistic update", "toast on success", "invalidate cache after a write", or "rollback on error".
-
encurehq Bundle Next Monorepo PatternUse when working in a Next.js App Router monorepo with a shared packages/ui — adding a route/page, a form or dialog, a list/table component, or deciding where a component/hook/util belongs. Use when the user asks where a component/hook/util/page should live, whether something is server or client, or whether a form should be role-specific. For the data-fetching/mutation pattern itself (prefetch, hydrate, useQuery, server actions, optimistic updates), see next-tanstack-query.
-
engsimsoft Skill Feature DeliveryUse this skill ALWAYS whenever adding new functionality, new endpoint, new component, new agent, or extending existing behavior in a non-trivial way. Trigger this skill at the start of ANY feature work even if the user just describes "add X" or "implement Y" without explicitly mentioning a process.
-
expensify Bundle Coding StandardsProvides coding standards for React Native — performance patterns, consistency rules, and clean React architecture. Use when writing, modifying, or reviewing code.
-
expensify Skill Playwright App TestingTest the Expensify App using Playwright browser automation. Use when user requests browser testing, after making frontend changes, or when debugging UI issues
-
ezzatmakar Bundle Nextjs Pr ReviewReviews pull requests, merge requests, branch changes, and code diffs for Next.js and React applications (App Router and Pages Router, Next.js 13–16). Use when asked to review a PR or changed code for security, performance, and clean-code quality, then create one detailed Markdown report containing evidence, impact, rationale, recommendations, validation results, references, and a merge verdict. Supports Quick, Standard, and Deep review modes and can optionally post findings as inline PR comments. Do not use for feature implementation unless the user separately asks for fixes.
-
fanzr-arch Skill Short Script LaneRuns the canonical script-first 6-10 second short-asset workflow from micro-concept through script outline, complete plan, materials planning, React + CSS build, browser verification, QA, and delivery. Use when the user asks for a short asset, wants to confirm a script before design integration, or wants browser-first CSS implementation instead of Remotion.
-
firetiger-oss Bundle Firetiger InstrumentUse when adding OpenTelemetry instrumentation to an application so it sends telemetry to Firetiger — setting up tracing, configuring the OTLP exporter, or connecting a Node.js, Next.js, Python, Go, or Rust app to Firetiger. Always use this skill when instrumenting for Firetiger — it carries the critical gotchas (init must load before any other import, Firetiger ingest uses HTTP Basic auth not Bearer, credentials come from the get_ingest_credentials MCP tool) that make telemetry actually show up.
-
psqasim Bundle Nextjs 16 SkillNext.js 16 App Router
-
imraywang Bundle Ray Report生成长文 / 深度报告 / 数据型内容,三格式协同产出——交互式 HTML(magazine 杂志排版,含 Tab/Quiz/Chart.js/Timeline 组件)、A4 PDF(headless Chrome 渲染)、公众号 markdown(长句叙事)。采用精修的编辑设计语言(衬线中文标题、锈红点缀、纸张颗粒、drop cap、装饰分隔、等宽数字),读起来像真正的杂志文章而非 SaaS dashboard。当用户要做长篇分析、白皮书、深度报告、多段数据型长文,或说「做一个报告」「深度分析」「长文章」「报告版」「PDF 报告」「html version」「pdf report」,或丢来一份提纲期待成品时使用;格式没点名也默认走 HTML,再 offer PDF+公众号。不用于短文、dashboard、UI 组件、或公众号自动发布流程(那用 wewrite)。触发 /ray-report
-
ivuorinen Bundle NitpickerHostile audit toolkit: one entry point dispatching specialist commands — adversarial review, security, tests, docs, types, architecture, performance, reliability, caching, concurrency, error handling, resource leaks, dependencies, licensing, CI, commits, migrations, observability, API contracts, a11y, i18n, privacy, config, infrastructure-as-code, prompt safety, installed agent configuration, complexity, dead and unwired code, agent rule and hook enforcement, plus planning, plan execution, teaching, triage, PR review and review-comment implementation. Use when auditing or reviewing a repository, PR, or any quality dimension of a codebase — "audit this", "review the whole codebase", "find all problems", "exhaustive review", "/nitpicker <command>", a release gate check, or any specific audit ask (security scan, find race conditions, audit the tests, hunt dead code, is this installed skill safe, plan a change, teach me this codebase, review the PR, fix the CR comments).
-
jackchuka Skill Ghpm StatusGitHub Project health dashboard. Shows workflow distribution, component health, team workload, items needing attention, and available views.
-
jamarpl21 Bundle Prawo Pl CbosaPrzeszukuje CBOSA — Centralną Bazę Orzeczeń Sądów Administracyjnych (orzeczenia.nsa.gov.pl): wyroki, postanowienia i uchwały NSA oraz 16 WSA (~2,4 mln orzeczeń od 2004 r.). Używaj przy KAŻDYM pytaniu o orzecznictwo sądów administracyjnych: skargi na decyzje organów, interpretacje podatkowe, „jak NSA/WSA interpretuje…", „wyrok NSA sygn. …", linia orzecznicza w sprawach administracyjnych i podatkowych (k.p.a., Ordynacja podatkowa, p.p.s.a., RODO/UODO, prawo budowlane, samorządowe, cudzoziemcy). CBOSA NIE MA oficjalnego API — skill czyta publiczne strony HTML (read-only, z throttlingiem). Orzecznictwo SN/TK/sądów powszechnych/KIO → skill prawo-pl-saos; treść przepisów → prawo-pl-eli; decyzje UODO → prawo-pl-uodo. Polish administrative courts (NSA/WSA) case-law from the public CBOSA database.
-
jeremieb Skill Swiftui ComponentCreates SwiftUI views and screens following MVVM with thin view layers, ViewModel extraction, previews, accessibility support, and loading/error states. Use when user says "create a SwiftUI view", "build a screen", "add a new view", "create a component", "build the UI for", "add a SwiftUI screen", or "make a new SwiftUI page".
-
jeromwolf Skill Templateclaw UIGenerate modern UI components — cards, forms, navigation, modals, tables, hero sections, footers, and pricing tables. 2026 glassmorphism design with Tailwind CSS. Copy-paste ready.
-
mhmzdev Skill UI DesignDesign Flutter UI screens and widgets for The Holy Qur'an app. Use when asked to build, design, create, or prototype a screen, widget, tile, dialog, or UI component. Enforces this app's configs layer (AppTheme, AppText, Space, AppDimensions, UIProps), fonts (Poppins / Noor), Screen wrapper, and class-widget rules.
-
mrwogu Skill Home Assistant CardUse when creating, reviewing, debugging, or maintaining Home Assistant custom Lovelace cards or card editors, including custom elements, Web Components, hass data, setConfig, getCardSize/getGridOptions, getConfigElement/getConfigForm, window.customCards, resource registration, HACS card packages, entity display, service calls, translations, or frontend build validation.
-
mzf11125 Bundle Midnight Dapp DevComprehensive guide for Midnight Network DApp frontend development covering project scaffolding with Vite and React 19 plus shadcn/ui templates, Next.js wallet connector patterns via the DApp Connector API with App Router, React wallet connector with Vite setup, provider architecture including MidnightProviders, proof provider, public data provider, private state provider, wallet provider, and ZK config provider, wallet integration using DApp Connector API v4.0.1 with window.midnight, connect, disconnect, and request authorization flows, DApp Connector types covering Configuration, ConnectionStatus, ConnectedAPI, InitialAPI, WalletConnectedAPI, KeyMaterialProvider, and ProvingProvider, transaction flow from creating unproven transactions through proving, submitting, waiting for finalization, and handling transaction results, state management with public state queries via indexer and private state with level-private-state-provider, indexer public data provider for querying blockchain data, contract state, tran
-
nvidia Skill Tripy New OperationAdd a new operation to nvtripy. Use when: implementing a new op, adding a frontend op, creating a trace op, registering an op in the API. Covers the full Frontend → Trace → MLIR pipeline including export decorators, constraint definitions, and init registration.
2.2k -
ohmyskyhigh Bundle Threadwave PreflightRun the mandatory readiness gate for every ThreadWave Twitter/X workflow: require the update skill, confirm every release-index roster skill's individual version through GitHub, offer supported-version continuation, run approved skill and CLI updates as separate component-scoped flows through the canonical setup guide, verify the tw CLI and supported contracts, check the Chrome extension/setup relay, preserve the original request, and route sanitized failures to threadwave-error-support. Use before twitter-automation, twitter-agent, twitter-post, or twitter-reply, and for ThreadWave setup, update, readiness, dependency, or repair requests. 中文:用于所有 ThreadWave 推特工作流的强制预检,检查发布索引中的技能版本、允许继续使用受支持版本、通过官方设置指南按组件分别更新 skill 和 CLI、检查 Chrome 扩展与依赖,并将净化后的故障转交给 threadwave-error-support。
-
othmanadi Bundle Agent BlueprintBuild production-grade AI agents from scratch using patterns inspired by production-grade agentic systems like Claude Code. Covers two audiences — (1) workflow builders who need planner+executor pipelines, human-in-the-loop checkpoints, and multi-agent orchestration, and (2) application embedders who need HTTP/SSE APIs, multi-user session management, and React frontend integration. Use when asked to build an AI agent, create a coding assistant, embed an agent in an app, build an API agent, clone Claude Code, build a CLI agent, design an agent architecture, scaffold an agentic system, or automate a multi-step workflow. Triggers on keywords like agent builder, agent blueprint, coding assistant, CLI agent, agentic tool, claude code clone, agent scaffold, agent architecture, workflow automation, multi-agent, planner executor, SSE streaming, agent API.
-
pchalupa Skill React Native AccessibilityReact Native accessibility props (VoiceOver and TalkBack) plus unit testing practices that query by role and label instead of testID or UNSAFE_* APIs. Use when writing, reviewing, or testing RN UI.
-
pchalupa Bundle Architecture DiagrammingDiagram software architecture as C4 levels in Mermaid: system context, container, component, dynamic, deployment, landscape. Use when the user wants to diagram or map how a system's parts fit together and communicate, turn a codebase or description into architecture diagrams, or review an existing architecture diagram.
-
pixelvault-dev Skill Pixelvault Email ImagesHost the local images referenced by an email template on PixelVault and rewrite them to permanent CDN URLs. Use when the user is building or sending an email (Resend, react-email, Nodemailer, Postmark, SendGrid) that references local image files, or says "my email images are broken", "images don't show in Gmail/Outlook", "host the images in this email", "prepare this email template for sending". Gmail doesn't render base64 `data:` images (and many Outlook clients don't either), so every image needs a public URL — this skill finds the local refs, uploads them, and swaps in the hosted URLs.
-
pproenca Skill Use Run ExpoDrive a real Expo / React Native iOS app from an AI agent using the run-expo CLI — the efficient, safe boot→inspect→act→evidence loop. Use when an agent must test, inspect, or capture evidence from a running Expo app instead of hand-rolling xcrun/simctl/Hermes CDP/Metro calls.
Frequently asked questions
What are Web & Frontend agent skills?
Web development agent skills handle frontend and full-stack work: component patterns, CSS and accessibility fixes, performance budgets, and framework conventions. Install a skill once and your AI agent follows the same playbook in every project, from quick prototypes to production apps.
Which Web & Frontend skills are most installed?
Popular Web & Frontend skills on SkillMD right now include use-run-expo, visual-acceptance, basecoat. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Web & Frontend skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.