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.
-
jv-vogler Bundle ArchitectureThe four-layer frontend architecture — infrastructure → domain → view → routes — with its dependency rules, file layout, naming conventions, and the recurring patterns that hold it together (serialization boundary, initial-data hook ladder, flow state machines, typed domain errors). Use whenever adding or changing a feature, page, API call, hook, form, or component in a React app laid out as src/infrastructure + src/domain + src/view + src/pages; whenever deciding which layer a piece of code belongs in; whenever reviewing a diff for layering violations; and whenever structuring a greenfield React frontend that wants a proven shape. Reach for it even when a request sounds purely local — "add a field to this form", "call this new endpoint", "show a spinner here" — because those are precisely the changes that quietly leak business rules into components.
-
kcsujeet Skill Verify UIVerify a UI change visually before calling it done. Trigger on "check the UI", "does this look right", "verify my UI change", "screenshot this page", "check dark mode", "check mobile", or before reporting a frontend change complete. Drives the actual screen with realistic data across states, viewports, themes and font scales, and reports what was checked and what was seen. Use when a change touches anything a person looks at.
-
kcsujeet Bundle Review CodeGate-based code review for a PR, branch, or set of changes in any repo. Trigger on "review this PR", "review my code", "review my changes", "review my branch", "is this clean", "is this good to merge", "code review please", a bare PR URL, or a branch name. Fans out one subagent per rule file (naming, clarity, structure, simplicity, datetime, react, i18n, project conventions, verification), aggregates per-box PASS/FAIL verdicts into a single PASSED/FAILED result. Reads the target repo's own .claude/review-conventions.md as an extra gate when present. Output stays in chat only - never posts comments to the PR without explicit approval.
-
kevin-liu-01 Bundle Local SearchUse the local-search (`lsearch`) Rust CLI for browser-backed web search, readable page extraction, site mapping, structured DOM extraction, browser interaction, authenticated in-browser requests, tab and cookie control, and PNG/PDF/MHTML/HTML/HAR artifacts. Use when an agent needs current web results through a local Chrome or Chromium profile without a hosted search API key or metered search bill, especially from Claude Code, Codex, Cursor, OpenClaw, or another shell-capable agent.
-
kzahel Skill BrowserControl a headless Chromium browser — navigate pages, read content via accessibility snapshots, interact with elements, fill forms, take screenshots
-
lackeyjb Skill Code StyleguidesLanguage-specific code style guidelines. Use when writing TypeScript, Python, Go, JavaScript, or HTML/CSS code to ensure consistent, idiomatic, and maintainable code following best practices.
-
lambdatest Skill Scan And Fix AccessibilityScan webpages for accessibility issues using getAccessibilityReport, analyzeAppViaTunnel, and buildLocalAppForAnalysis MCP tools. Use for WCAG compliance testing, identifying violations, and fixing accessibility bugs.
-
showlotus Bundle Frontend Project Interview互联网大厂前端面试官,根据简历中的项目经历或工作经历进行由浅入深的阶梯式技术提问,并提供实时反馈和改进建议。Use when: (1) 用户要求模拟前端面试,(2) 需要对简历中的前端项目/工作经历进行技术深挖,(3) 用户提供了简历内容并希望进行面试练习,(4) 需要评估前端技术深度和理解能力,(5) 希望获得面试表达技巧和改进建议。
-
showlotus Bundle Frontend Scenario Interview前端场景题面试技能
-
showlotus Bundle Frontend Knowledge Interview互联网大厂前端面试官,提供阶梯式技术提问、实时反馈和改进建议。支持 HTML/CSS/JavaScript/TypeScript、浏览器与网络、Vue/React/SSR、工程化、性能优化、安全、移动端、架构与设计、算法、Node.js 等 11 个技术分组、40+ 具体方向、三级难度。支持两种模式:(1)系统出题模式:根据选择的技术方向和难度进行面试;(2)自定义问题模式:用户输入任意前端技术问题,系统给出标准答案解析。当用户要求模拟前端面试、想要检验某个前端技术的掌握程度、希望获得面试反馈和改进建议、或想要进行针对性技术面试练习时,请务必使用此技能。
-
shyuan Bundle Complete Test CodeUse this skill whenever the user wants test code written, added, audited, or judged "good enough" — not merely run. Trigger when they: ask you to write or improve tests for a module (parser, retry/network logic, migration, auth/token, billing, state machine, library/SDK); worry that edge cases or "garbage input" keep slipping through release after release; ask what testing a component needs before shipping, open-sourcing, or tagging a version; want code made robust, reliable, or production-ready; report flaky, missing, or weak tests; or raise data corruption, crash/rollback/atomicity, concurrency, or fault-handling concerns. Also apply proactively right after non-trivial logic is implemented, to cover failure paths and boundaries even if "test" was never said. Brings SQLite-grade methods (fuzzing, property/differential/metamorphic testing, fault injection, mutation testing, coverage) but right-sizes rigor to the component's blast radius. Not for just running an existing suite or general debugging.
-
solvapay Bundle Sdk IntegrationIntegrate the SolvaPay TypeScript SDK into an existing app -- Next.js, React, Express, Supabase Edge Functions, Deno, or an MCP server that already exists. Use when the user says "integrate sdk", "protect api", "paywall my api", "usage events", "webhooks", "add solvapay to existing mcp", "supabase edge functions", "npx solvapay init", or wants account-management UI (CurrentPlanCard, LaunchCustomerPortalButton, usePaymentMethod). Covers paywall enforcement, usage tracking, hosted checkout, customer portal, plan activation / cancellation / reactivation, and webhook signature verification. Use the `create-mcp-app` skill instead when scaffolding a brand-new paid MCP server.
-
solvapay Bundle Lovable CheckoutPaste-in SolvaPay hosted checkout for Lovable-generated apps (Vite + React + TypeScript + shadcn/ui + Supabase). Backend is Supabase Edge Functions — no Node server to add. Use when the user says "lovable", "vite checkout", "shadcn checkout", "supabase edge checkout", "solvapay in lovable", "paste this into lovable", or "@preview". Pinned to the floating `@preview` tag and the SolvaPay dev backend (`https://api-dev.solvapay.com`). Not for production. Use `website-checkout` for Next.js / production web apps, or `sdk-integration` for general SDK wiring.
-
solvapay Bundle Website CheckoutAdd SolvaPay hosted checkout and customer portal to a web app with minimal PCI surface. Use when the user says "add checkout to website", "hosted checkout", "customer portal", "nextjs checkout", "checkout session", or wants a server-side checkout-session route plus a return-URL handler. Next.js is fully supported; React (no Next.js) gets partial guidance. Use the `sdk-integration` skill instead for usage metering, Express, MCP server wiring, or webhook-heavy flows; use `lovable-checkout` for Lovable / Vite / Supabase Edge apps.
-
spatie Bundle Swiftui ProWrite and review Bloom macOS SwiftUI views for data flow, accessibility, API correctness and measured performance.
-
story-has-you Skill Vue DevMUST BE USED PROACTIVELY whenever writing Vue 3 or TypeScript code. This agent provides authoritative guidance on Vue architecture, component design, state management, and performance optimization, ensuring production-level scalability and maintainability. [Vue 3 stack specific]
-
story-has-you Skill React DevMUST BE USED PROACTIVELY whenever writing React or TypeScript code. This agent provides authoritative guidance on architecture, component design, state management, and performance optimization, ensuring production-level scalability and maintainability. [Next.js stack specific]
-
superlinked Bundle Superlinked DocsOffload document, image, and structured-output work to the Superlinked inference cluster: convert PDF/DOCX/PPTX/XLSX/HTML/scans to clean markdown, describe an image (caption + tags), or produce schema/grammar-constrained JSON off the cluster — instead of ingesting the file directly, which can reduce the tokens billed in many cases for document- and image-heavy work. Use whenever the user drops or references a document or image file to read, summarize, extract from, describe, or answer questions over, or when they need reliable structured (schema-valid) output.
-
swathidbhat Bundle Book ReviewDocument a reader's experience with a non-fiction book through active recall and guided reflection. Triggers when user wants a book review/summary/notes AND provides their highlights, annotations, or reading data (JSON, HTML, CSV, export, copy-paste). Interviews the user with four reflection questions before evaluating their recall against their own highlights, checking factual accuracy, and flagging missed themes. Produces a one-page summary in the user's voice. Do not trigger for fiction, or requests without the user's own reading data.
-
swig Skill Swig DocAuthor and edit chapters of the SWIG Users Manual under Doc/Manual: chapter conventions, manual heading anchors, the four content `<div>` styles (code / targetlang / shell / diagram), the auto generated section TOC, the `make` targets that renumber headings and validate HTML, and the rules for cross document anchored links.
-
makeplane Skill React DoctorUse when finishing a feature, fixing a bug, before committing React code, or when the user types `/doctor`, asks to scan, triage, or clean up React diagnostics. Covers lint, accessibility, bundle size, architecture. Includes a regression check and a full local-triage workflow that fetches the canonical playbook.
-
marsidev Skill Nextjs SsrIntegrate Turnstile with Next.js, handle SSR, hydration, and App Router. Activate when building Next.js applications with App Router or Pages Router, or when encountering SSR-related errors.
-
marsidev Skill Basic SetupInstall and render your first Turnstile widget with required configuration. Activate this skill when starting a new project with react-turnstile or when implementing basic CAPTCHA protection for the first time.
-
maskshell Bundle Parallel DevelopmentParallel-development orchestrator: runs multiple AI agents in parallel on independent dev tasks. Use it whenever the user wants to implement several features or components at once, work in parallel, do TDD (red-green-refactor, tests first), safely refactor code modules, coordinate backend and frontend simultaneously, or manage multi-agent tasks. Also trigger on "同时做", "并行实现", "test first", "red green refactor", or whenever multiple independent subtasks are identified. Platforms: iOS/Apple (Xcode, Swift, SwiftUI, XCTest, XCUITest, SPM, Simulator); Python (FastAPI, Django, Flask, SQLAlchemy, Pydantic, pytest, poetry, uv, pyproject.toml); Rust (Rust, cargo, Cargo.toml, clippy, rustfmt); Web/frontend (React, Vue, Svelte, TypeScript, JavaScript, Node.js, Express, Next.js, Playwright, ESLint, dependency-cruiser); Java (JDK 17+, Maven, Gradle, JUnit, Checkstyle, google-java-format); Go (Go, golang, go.mod, go vet, golangci-lint, go test). Trigger readily, even without an explicit "parallel" or "TDD" keyword.
-
microsoft Skill Theme AuthoringAdd a new color theme to the Ontology Playground. Use when someone wants to create, author, or plug in a theme, palette, color scheme, dark mode, or light mode, or add an entry to the theme picker. Covers the appStore registration plus the CSS token block.
2.7k -
microsoft Bundle Msresearch PromptionsPromptions — Microsoft Research's dynamic prompt middleware that turns a user's prompt into ephemeral UI controls (sliders, toggles, selects) they can adjust and replay to steer model output without rewriting instructions. Use for integrating Promptions, designing control schemas, rendering controls in React/Fluent UI, or showcasing the hosted ImageGen Workbench demo (the recommended first-look) or the self-hosted `promptions-chat` reference app.
2.7k -
nvidia Skill Trt Onnx QuickstartBuild and verify a TensorRT engine from a Hugging Face model ID or ONNX file, with numerical parity checked against ONNX Runtime. Use when the user imports a non-LLM model to TensorRT, needs a verified engine from ONNX, hits trtexec "unsupported operator", must verify the engine matches ONNX numerically, debugs a polygraphy parity failure (large max abs diff at FP16), or configures multi-input dynamic shapes. Triggers: convert ONNX to TensorRT, Hugging Face to TensorRT, trtexec onnx, trtexec unsupported operator, optimum-cli export, polygraphy parity check, polygraphy run --trt --onnxrt, parity check failed, max abs diff, verify engine matches ONNX, --minShapes, dynamic shapes trtexec, multi-input shape profile, FP16 engine, INT64 warning. Adjacent skills: `trt-torch-quickstart` (PyTorch frontend), `trt-cpp-runtime-quickstart` (C++ engine load). LLM token generation belongs in TensorRT-LLM, not here.
2.2k -
oh-summy Bundle Prompt ComponentsPrompt assembly engine for AI image generation and video generation. Provides a structured component library (style selection, quality boosters, lighting, composition, color mood, texture, camera movement, pacing) and categorized negative prompts, with three interaction modes for vague or specific requests. Use when composing, improving, or translating a prompt for image or video models, when selecting a visual style, when appending negative prompts, or when a user's visual request needs clarification.
-
ohzw Bundle Roblox UI MasteryAdvanced Roblox UI engineering with React-Lua. Use when creating, modifying, or debugging any React-Lua UI component for Roblox games. Triggers: React-Lua, Roact, UI component, createElement, useState, useEffect, useSpring, Binding, animation, tween, spring, modal, panel, selector, tooltip, dropdown, tab, toast, notification, cooldown display, health bar, leaderboard, inventory UI, shop UI, HUD, overlay, popup, fade, slide, bounce, glow effect, shadow effect, gradient, responsive layout, mobile UI, gamepad UI, DesignSystem, tokens, theme, UI performance, memo, virtual scroll, Context API, useReducer, custom hook, BillboardGui, SurfaceGui, ViewportFrame, EditableImage, UIListLayout, UIGridLayout, UIFlexItem, UIDragDetector, Path2D, RichText, ScreenGui, CanvasGroup, UIStroke, UIGradient, UICorner. Tech stack: jsdotlua/react, ReactRoblox, react-spring (chriscerie/react-spring), Luau --!strict, Rojo, Wally.
-
okturan Bundle Generate File MapCreate or update a self-contained HTML report of file structure, storage use, and suggested actions. Use when the user asks for a file map, storage dashboard, folder map, or file-structure report.
-
opentiny Bundle Genui Integrationgenui-sdk 全方位指南:安装、配置、集成、示例。用户提到 genui-sdk、genui-sdk-server,或想构建 AI 聊天界面、动态 UI 组件、Node.js 后端 LLM 代理(OpenAI 兼容 chat/completions API)时使用。涵盖 Vue/Angular 前端(主题、物料、GenuiChat/GenuiRenderer)与 Server 后端(CLI、Express 集成、流式代理)。即使用户只描述需求(如"搭建 LLM 代理服务"、"AI 聊天+动态组件")而未提及 SDK 名称也应触发。
-
ownerng Bundle Frontend DesignCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
-
pacho-h Bundle Improving Feature CompletenessAudits a working feature for the gap between "happy path passes" and "production-ready" — edge cases, error handling, loading/empty/error states, a11y, responsive, i18n, observability, ops hooks. Use when a feature works but needs polish, for "완성도 높여줘", "production ready로", "edge case 검토", "polish this feature", "is this ready to ship?", "엣지 케이스 다 챙겼나", "PR 전 점검", "빠진 상태 없나", or before shipping any non-trivial feature. Also triggers proactively right before PR creation on a non-trivial branch. Triggers even when the diff is small or the happy path was verified manually; gaps emerge from state interactions (empty/loading/error/disabled, role and locale variants), not line count, and "I already clicked through it in Playwright" does not substitute for the audit. Distinct from brainstorming (designs), test-driven-development (implements), and requesting-code-review (evaluates structure); raises the bar of a working impl via production-readiness audit.
-
paleo Skill Pleasant Bem CSSApply the Pleasant BEM syntax and methodology to CSS class names.
-
llnl Skill Sundials New ModuleAdd a new SUNDIALS module (e.g., NVECTOR_*, SUNMATRIX_*, SUNLINSOL_*, SUNNONLINSOL_*, SUNMEMORY_*, or a new shared component) including source/header layout, CMake wiring, enable/disable options, exported CMake targets, installed component registration, and developer tests/examples/docs updates.
-
lncitador Bundle EdgeUse this skill alongside the adonisjs skill when the project uses the AdonisJS Hypermedia starter kit or Edge.js server-side templates. Trigger for .edge files, view.render(), router.on().render(), resources/views, Edge syntax, AdonisJS Edge helpers, request/auth/session/flashMessages/old/route/signedRoute/config/app/asset/i18n, @vite/@viteReactRefresh/@can/@cannot/@flashMessage/@error/@inputError, template state, interpolation, conditionals, @if/@elseif/@else/@unless, loops, @each, layouts, Edge components, component props, $props, slots, provide/inject, $context, partials, @include/@includeIf, stacks, @stack/@pushTo, form components, CSRF form helpers, field/input/select/textarea components, alert/button/link/avatar components, or debugging templates with @dump.
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 architecture, verify-ui, review-code. 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.