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.
-
gronxb Bundle App Store ReviewEvaluates code against Apple's App Store Review Guidelines. Use this skill when reviewing iOS, macOS, tvOS, watchOS, or visionOS app code (Swift, Objective-C, React Native, or Expo) to identify potential App Store rejection issues before submission. Triggers on tasks involving app review preparation, compliance checking, or App Store submission readiness.
-
openqa-cn Bundle Code ReviewerReview Git branch, PR, or commit changes for quality, security, and maintainability (CR / 代码审查 / 审查 / pre-commit / risk assessment). Frontend: React, TypeScript, JavaScript, React Native, mini-program. Backend: Java, Kotlin, Go, Python, C, C++, Groovy, SQL / service-layer. Requires a local Git checkout — not a pasted snippet. Do not use for how-to questions, debugging a known bug, explaining or rewriting code, method-level requirement defect hunting with write-back gates (that is defect-detection), writing test cases (testcase-generation), or constructing test data (testdata-generation).
-
openqa-cn Bundle Defect DetectionReviews code changes for defects before release. Given a git repository and branch (optionally a PR, test plan, or a previous report to continue), it clones the repo, diffs the base branch, extracts changed methods, runs static rules, cross-checks requirements, test cases, and known defects, and writes back findings with line numbers, fix suggestions, and an HTML report. Language-aware for Java, Kotlin, Scala, JavaScript, TypeScript, Python, Go, C, C++ and C#: method extraction, trivial-method filter, Semgrep seed packs, and write-back conventions; polyglot diffs keep each language's rules. Optional overlays add secret / SCA / native-analyzer findings. Use when the user asks to find bugs in a branch or PR, review change or regression risk, recheck before release, scan a test plan, or resume a detection task. Not a P0/P1/P2 style CR (that is code-reviewer).
-
mbelenmontoya Skill Code Reuse EnforcerEnforce checking existing code before creating new implementations (USE → IMPROVE → ADD). Triggers on "create component", "add feature", "build", "new component", "new hook".
-
mbelenmontoya Skill Accessibility PatternsBuild accessible React components with WCAG 2.1 Level AA compliance for Hara Vital. Use when creating interactive elements, forms, modals, bottom sheets, or any user-facing components. Triggers on "accessibility", "a11y", "ARIA", "keyboard", "focus", "screen reader", "WCAG".
-
kraayenjon Skill PagekitBuild a complete landing page or portfolio site from a short interview — for someone who does not write code. Runs a four-round questionnaire, picks a design direction, scaffolds Next.js + Tailwind + shadcn/ui, writes the page, deploys it with no Vercel account, then sets up structured data, llms.txt, robots.txt and metadata so search engines and AI assistants can actually read it. Use when the user says "build me a website", "landing page", "portfolio site", "make a site for my business", "página web", "landing", or asks for a one-page site for a small business.
-
kraayenjon Skill Llms TxtWrite and validate an llms.txt file — the /llms.txt convention that gives AI assistants a clean, curated map of a site instead of leaving them to guess from HTML. Covers the required format, what belongs in it and what does not, the optional llms-full.txt companion, and where to put both. Use when the user says "llms.txt", "llms-full.txt", "AI crawler file", "help AI understand my site", "make my site readable to ChatGPT", or is preparing a site to be cited by AI assistants.
-
langchain-ai Skill Weekly NewsletterProduce the weekly 'This Week in Music' customer newsletter by researching the distributor's top genres in parallel and assembling a styled HTML page. Use when asked to create, write, or send the weekly newsletter or a music-news roundup.
-
nicknisi Skill Eli5Explain a topic to a complete novice using an HTML artifact with big pictures and few words. Use when the user says "eli5", "explain like I'm 5", or asks for a beginner-friendly visual explanation of any topic.
-
nicknisi Skill Show MeHelp the user understand the current topic visually with concise diagrams, code-shape sketches, and focused HTML artifacts.
-
wkylin Skill Tavily Dynamic SearchProgrammatic web search with context isolation. Use this skill for any research task where you need to search the web, filter results, and extract specific information — without polluting your context window with raw HTML and boilerplate. This is the default skill for web research. Triggered by "search for", "look up", "find", "research", "what's the latest on", or any query that requires current web information. Also use when asked to "search and filter", "find the important parts", or "extract the key details" — any case where the user wants curated, noise-free content.
-
1ecc Bundle Wifi Health Report生成脱敏的 Windows Wi-Fi 网络体检 SVG 或动态 HTML 报告,报告中的数字来自确定性检测,不使用图片模型改写。
-
aps08 Skill React TestingFrontend testing standards using Vitest, React Testing Library, and Playwright. Use when writing UI tests.
-
aps08 Skill Frontend DesignCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.
Audited -
ara-labs Bundle Research VisualizerResearch Visualizer. Renders an existing Agent-Native Research Artifact (ARA) into ONE self-contained, interactive HTML file showing the AI scientist's step-by-step research process: a clickable process map of the exploration tree (branches and dead ends included) on the left, and a per-step drill-down on the right — what the step did (its narrative written in plain language a person can follow), why (the linked claim), the real result (verbatim grounded numbers + inline figures + tables), and the code/artifact pointer. Read-only consumer of the artifact — it never changes how research is done. When the ARA carries them, it also surfaces (each optional, only when present) the related-work dependency graph, the problem framing, a concepts glossary with in-text term popovers, and the solution recipes — reached from header disclosures without leaving the process map. Accepts either an existing ARA or raw research input (a paper, repo, run logs, or notes); when the input is not yet an ARA it is compiled into one
-
asmyshlyaev177 Skill Menu SetupBuild a working react-horizontal-scrolling-menu: install, the mandatory 'react-horizontal-scrolling-menu/dist/styles.css' import, ScrollMenu with a unique itemId per child, arrow components via VisibilityContext with useLeftArrowVisible/useRightArrowVisible, Header/Footer slots, and CSS customization (fixed item width, spacing via gap on the scroll container, hiding the scrollbar). Load when creating a category row, tab strip, chip filter, or any horizontal scrolling list, or when a menu renders vertically, arrows do nothing, or item visibility is not tracked.
-
asmyshlyaev177 Bundle Menu RecipesRecipes composed on the react-horizontal-scrolling-menu public API — NOT props: autoplay (setInterval + scrollNext gated on menuVisible), infinite loop/carousel (clone head/tail + scrollLeft teleport at seams), center on click (scrollToItem 'center'), save/restore scroll position (onUpdate, onInit, scrollContainer), load-more with a loader item (items.last()?.visible in onUpdate), one item per scroll (getPrevElement/getNextElement), hiding arrows, multiple menus, tab switching. Load when asked for autoplay, looping, carousel-like behavior, infinite scroll, or any feature missing from the props table — inventing an autoplay/loop/snap prop generates dead code.
-
asmyshlyaev177 Skill Menu MigrationDetect and upgrade pre-v8 react-horizontal-scrolling-menu patterns that agents trained on older data still generate: destructured visibleElements/isFirstItemVisible/isLastItemVisible/initComplete (removed v6), Separator items, separatorClassName and getPrevItem/getNextItem (removed v7), the Arrows prop (removed v3), missing dist/styles.css import (required since v4), CJS require of the ESM-only package (v5), transitionDuration/transitionBehavior silently ignored after the v8 noPolyfill flip, the misleading 8.1.0 changelog BREAKING block, and >=8.2.2 for TypeScript moduleResolution node16/bundler. Load when upgrading versions or whenever generated or reviewed code uses any of those removed APIs.
Audited -
asmyshlyaev177 Bundle Menu ScrollingImperative scrolling for react-horizontal-scrolling-menu: scrollToItem(getItemById(id), behavior, inline, block), scrollNext/scrollPrev, apiRef for controlling the menu from outside (fire methods, never read data), getItemElementById/getItemElementByIndex for just-added items, and page-at-a-time navigation with slidingWindow + getItemsPos. Load when scrolling to an item on mount or selection, controlling the menu from outside, scrolling after adding items dynamically, or when scrollToItem silently does nothing or the whole page jumps to the menu.
-
asmyshlyaev177 Skill Menu VisibilityTrack which react-horizontal-scrolling-menu items are on screen: useIsVisible(itemId | 'first' | 'last', defaultValue), useLeftArrowVisible/useRightArrowVisible, the options prop (ratio, rootMargin, threshold), items.getVisible()/subscribe/unsubscribe, and the async IntersectionObserver truth model (items must be seen once, menuVisible gating, non-reactive isFirstItemVisible reads). Load when disabling arrows at the edges, styling items by visibility, building progress indicators, or debugging flickering or dead arrows.
-
asmyshlyaev177 Skill Menu Testing SsrServer rendering and testing for react-horizontal-scrolling-menu: the library is client-only ('use client' required in React Server Components, else "createContext is not a function"), SSR first paint is controlled by the useIsVisible defaultValue argument (canonical ('first', true) / ('last', false)), transpilePackages for older Next.js, Jest moduleNameMapper to dist/index.cjs for "Cannot use import statement outside a module" plus an IntersectionObserver class mock for jsdom (ReferenceError on mount without it), and async poll-based assertions (Playwright preferred). Load when integrating with Next.js / TanStack Start, fixing hydration flicker, or writing tests for the menu.
-
asmyshlyaev177 Skill Menu InteractionsWire mouse, wheel and touch input for react-horizontal-scrolling-menu: onWheel/onScroll are plain (api, event) => void callbacks, while ALL mouse/touch props (onMouseDown, onMouseUp, onMouseMove, onMouseLeave, onTouchStart, onTouchMove, onTouchEnd) are handler factories (api) => (event) => void. Covers mouse drag-to-scroll with the DragDealer pattern and dragging guard, onMouseLeave to stop drags, body-scroll locking, touchpad-vs-wheel detection, desktop swipe. Load when adding drag-to-scroll or custom wheel behavior, or when fixing clicks firing after drags or "Unable to preventDefault inside passive event listener".
-
asmyshlyaev177 Skill Menu Transitions RtlAnimate react-horizontal-scrolling-menu scrolling and build right-to-left menus: noPolyfill defaults to true since v8, so transitionDuration (default 500), a custom-easing-function transitionBehavior, and per-call ScrollOptions { duration, boundary } on scrollToItem/scrollNext/scrollPrev are silently ignored unless noPolyfill={false} (string 'smooth' | 'auto' behaviors still reach native scrollIntoView); the RTL prop (only a direction: rtl CSS class) and its limits — never combine RTL with transition props. Load when scroll animation speed/easing has no effect, when customizing transitions, or when building RTL menus.
-
atkntepe Bundle Svg DesignUse when creating, redesigning, converting, debugging, or reviewing SVG files, inline SVG UI mockups, vector illustrations, logos, diagrams, CSS-to-SVG conversions, or any SVG output with overlap, clipping, viewBox, layering, text wrapping, responsive scaling, or browser rendering problems.
-
automattic Skill AuditingAudit a Studio-backed WordPress site for performance, accessibility, and visible frontend quality issues, then recommend or validate improvements.
Audited -
aws-samples Bundle UI CSS PatternsUI/CSS design patterns and component reference for the RAPID frontend, covering color semantics, button variant selection, status badge colors, dark mode, spacing, and component inventory. Use when implementing UI components, choosing button variants or colors, styling with Tailwind CSS, or checking available shared components.
-
aws-samples Skill Build And FormatRun build verification and code formatting across all RAPID project components (backend, frontend, CDK). Use after implementing code changes, before committing, after modifying Prisma schema, or before creating a pull request.
-
aws-samples Bundle Plan Backend FrontendCreate implementation plans for backend API endpoints and frontend features following RAPID layered architecture (domain/usecase/routes pattern, SWR hooks, feature-based organization). Use when adding or modifying backend APIs, frontend components, database schemas, or repository implementations. Also use for refactoring backend/frontend code.
-
basher83 Bundle Component WriteupProduces structured technical documentation of a system by discovering components, tracing relationships through artifacts, and rendering progressive-disclosure writeups following the Patnaik template — component inventory, architecture overview, data flow, per-component detail, and grouped references.
-
spideynolove Skill LightpandaFast headless browser for fetching real web pages and scraping content. 9x less memory than Chrome, instant startup. Use instead of Playwright when you only need HTML content — no MCP overhead, pure CLI. Binary at ~/.local/bin/lightpanda.
-
ycs77 Skill Ycs77 VueThis skill should be used when applying project-specific opinionated Vue 3 conventions. It covers SFC block order (template-first vs script-first), inline typing for defineProps and defineEmits, using reactive() for form state management, ref type assertions with as Ref<Type> for complex types, same-name shorthand bindings in Vue 3.4+, and props access patterns in templates. Relevant when a user asks about template ordering, how to type props or emits inline, reactive vs ref for forms, ref type assertion patterns, shorthand attribute bindings, props usage in templates, or following Lucas Yang's Vue coding conventions.
-
mrclrchtr Bundle Pi Tui DesignCreate distinctive, crafted TUI components for pi using @earendil-works/pi-tui and @earendil-works/pi-coding-agent. Use when building interactive terminal UIs — custom components, overlays, dialogs, dashboards, widgets, data visualizations, animated elements, game-like interfaces, or any visual TUI work inside pi extensions or custom tools. Triggers on: 'build a TUI component', 'make a dashboard', 'create an overlay', 'interactive widget', 'terminal UI', 'custom component', 'pi-tui', or any request to create visual, interactive terminal interfaces. Also use when beautifying or redesigning existing TUI components.
-
fufankeji Bundle Build AI Report只读分析本地 Excel 工作簿,完成数据剖析、清洗口径、结论提炼、图表选型、离线 HTML 报表生成和双端验收。用户要求理解或分析 .xlsx/.xlsm 数据、把 Excel 变成可视化报告、更新 Epoch AI 演示报表、选择合适图表或核对报表数据时使用。
-
fufankeji Skill Dsh Motion Deck当用户提供一段演示文稿主题、内容大纲或会议材料,希望生成结构完整、视觉突出、每页有动画的 HTML 演示文稿时使用;从新内容生成 8 页单文件 HTML,不生成 pptx,也不改写已有案例。
-
gn00678465 Bundle React AI InfraDeploys cross-platform agent assets into an already-created React project. ACTIVATE when a React/Next.js/TanStack Start/Vite repo (existing or freshly bootstrapped by its own CLI) needs APM-managed dependencies, bundled skills/rules, and a framework-specific AGENTS.md wired in for Claude Code, GitHub Copilot, and the cross-client `.agents/skills/` bus. Asks which React framework is in use, generates apm.yml at the project root, runs `apm install`, and writes assets to .claude/skills/, .agents/skills/, .claude/rules/, .github/instructions/, and the project root. Does NOT create the React app itself.
-
gn00678465 Bundle Svelte AI InfraScaffold a Svelte/SvelteKit repo's AI infrastructure source files — APM config (`apm.yml`), `.apm/` agents & instructions, `.lsp.json` — pinned to a fixed `sveltejs/ai-tools` SHA, ready for the user to run `apm install`. Use when asked to enable / initialize / set up Svelte AI tooling for a project, bootstrap svelte ai infra, or wire up sveltejs/ai-tools plugin. Do NOT use when only modifying a single skill file, a single target's config, .mcp.json alone, or apm.yml content (use Read+Edit directly).
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 llms-txt, wifi-health-report, react-testing. 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.