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.
-
ndhananj Skill Backend Patterns 3后端架构模式、API设计、数据库优化以及针对Node.js、Express和Next.js API路由的服务器端最佳实践。
-
jaykim88 Skill Cicd Pipeline 2Set up GitHub Actions for Next.js with parallel type-check / lint / test / build, dependency + Next.js caching, concurrency cancellation, Vercel Preview, branch protection, and least-privilege CI security. Use at project start, when manual deploys cause errors, or when the team grows. Coordinates with test-strategy for what gets gated and developer-experience for local pre-commit gating.
-
jaykim88 Skill Test Strategy 2Apply the Testing Trophy (mostly integration tests with RTL + MSW, sparing E2E with Playwright) and set coverage thresholds. Use before new feature work, after bug fixes, when CI coverage falls below target, or when tests are flaky or break on every refactor. Not for wiring coverage gates + Playwright into the GitHub Actions matrix (use cicd-pipeline) or auditing WCAG a11y compliance (use accessibility-audit).
-
jaykim88 Skill Observability Setup 2Set up Sentry for Next.js (error.tsx integration, Server Action capture), source-map upload for readable traces, PII scrubbing, release tagging, sampling/quota control, useReportWebVitals for CWV, structured logging, console.log replacement. Use before production deploy or when unexplained errors recur. Not for building error fallback UI (use async-ux-states) or optimizing CWV (use rendering-performance) — this only captures and reports them.
-
jaykim88 Skill Architecture Improvement 2Reorganize a project into a feature-based folder structure with unidirectional imports. Use when adding a new feature conflicts with existing structure, when teammates can't find files, when circular dependencies appear in build logs, or at the start of a new quarter. Not for changes within a single file (use code-refactoring) or component extraction (use component-quality).
-
treasure-data Skill React Dashboard 2Build interactive React dashboards in Treasure Work using render_react. Use when the user explicitly asks for an interactive dashboard or custom React component beyond what render_chart supports.
-
kortix-ai Bundle Presentations 2Create, manage, validate, preview, and export slide decks and presentations. Build 1920x1080 HTML slide decks (the default, higher-quality path) and export to PDF or PPTX — or produce/edit a fully native, editable PowerPoint (.pptx) file directly when the user needs a plain PowerPoint deliverable. Load this skill when you need to build a slide deck, presentation, or PowerPoint file, or export/edit/validate one.
-
amhuppert Bundle Knip 2Detect and remove dead code with knip. Use when the user asks to "run knip", "find unused files", "find unused exports", "find unused dependencies", "clean up dead code", "remove dead code", "set up knip", "configure knip", "knip.json", "knip false positive", "knip CI", or mentions a `knip` config, dependency bloat, bundle bloat from unused imports, or tree-shaking unused exports. Covers the configuration-first workflow, confidence-gated deletion, framework-specific gotchas (Next.js 15+, Tailwind, Storybook, Jest, Bun's test runner and `bun build --compile`), monorepos, CI integration, and performance tuning.
-
avav25 Bundle AI Skills 2Create, modify, validate, and analyze Windsurf AI assets such as AGENTS.md files, Windsurf skills, templates, and supporting scripts. Use when building or maintaining the repository's Windsurf-specific AI component package.
-
amhuppert Bundle React Scan 2Install and use react-scan tooling for component-level React render attribution: "set up react-scan", "diagnose React re-renders", "find unnecessary renders", "find unstable props", "measure component renders programmatically", or automated render checks with Playwright (react-scan + playwright, lite headless API for CI). Covers install across Next.js/Vite/Remix/script-tag/browser-extension and the render-attribution → fix → validate loop. For trace-based triage of LCP/INP regressions, ForcedReflow, bundle bloat, or memory leaks, use investigate-web-perf instead.
-
amhuppert Skill Web Debugger 2Debug a running web app via the web-debugger SDK: app logs, application state, runtime snapshots, React state, query cache.
-
amhuppert Bundle Compare Reports 2Compare two reports written by different AI agents from the same prompt — score both across accuracy, prompt adherence, organization, readability, and usefulness, then produce a polished self-contained HTML comparison report that declares a winner. Use whenever the user wants to compare, judge, grade, rank, or pick between two AI-generated reports, answers, research outputs, or documents ("which of these is better?", "evaluate these two responses", "A/B test these reports", "grade these two drafts"), even if they don't mention HTML, scoring, or the word "report".
-
avav25 Bundle Asset Validation 2Validate Windsurf AI assets such as AGENTS.md files, Windsurf skills, templates, checklists, and support scripts. Use after creating or modifying the repository's Windsurf component package.
-
madappgang Skill Shadcn UI 2shadcn/ui component library patterns. Covers CLI usage, installation, component categories, theming with CSS variables, dark mode setup, and integration with React Hook Form + Zod. Use when adding UI components, setting up design systems, or implementing forms with shadcn/ui.
-
madappgang Skill Tanstack Router 2Use when setting up routes, implementing navigation, or configuring route loaders. TanStack Router patterns for type-safe, file-based routing. Covers installation, route configuration, typed params/search, layouts, and navigation.
-
amhuppert Bundle Review Guide HTML 2Render a change-review-guide as an interactive, self-contained HTML page (and optionally regenerated markdown) from a YAML content file, with the file index and stats pulled from git.
-
madappgang Skill Tanstack Query 2Comprehensive TanStack Query v5 patterns for async state management. Covers breaking changes, query key factories, data transformation, mutations, optimistic updates, authentication, testing with MSW, and anti-patterns. Use for all server state management, data fetching, and cache invalidation tasks.
-
chatandbuild Bundle Webapp TestingToolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
-
agentient Skill Tailwind Utility Styling 2Tailwind CSS utility-first styling, mobile-first responsive design, dark mode, CSS variables, and cva variants. Keywords: "style", "tailwind", "responsive", "dark mode", "mobile-first", "css variables"
-
agentient Skill Shadcn Component Scaffolding 2shadcn/ui CLI usage, component installation, composition patterns, and file ownership philosophy. Keywords: "add component", "install shadcn", "scaffold", "cli", "components.json"
-
agentient Skill Rsc Composition Patterns 2React Server Components (RSC) architecture patterns for Next.js 14+. Server-first development, client component boundaries, composition patterns. Use when deciding "Server or Client Component?", composing components, managing interactivity. Keywords: "server component", "client component", "'use client'", "state", "interactivity", "composition".
-
agentient Skill Architectural Decision Records 2Architecture Decision Records (ADRs) format, templates, and best practices. Use when documenting technical decisions, design choices, trade-offs. Keywords: "ADR", "decision record", "architecture", "trade-offs", "document decision".
-
agentient Skill Firebase Admin Sdk Server Integration 2Server-side Firebase Admin SDK patterns for Next.js 14+, including secure initialization, custom claims, server-only protection, token verification, privileged operations, and environment separation. Keywords: "admin sdk", "server-only", "custom claims", "verify token", "server", "privileged"
-
agentient Skill Nextjs App Router Data Fetching 2Data fetching patterns for Next.js 14+ App Router. Async Server Components, Server Actions, caching, revalidation. Use when fetching data, calling APIs, using Server Actions. Keywords: "fetch data", "api call", "database", "server action", "revalidate", "cache".
-
agentient Skill Zod Schema Type Inference Chain 2Zod Schema Type Inference Chain
-
agentient Skill Zustand V5 Typed Store Creation 2Zustand v5 Typed Store Creation
-
hainamchung Bundle Agent Assistant Design Fast⚡ Quick Design — Rapid component/UI design. Use when user types /design:fast.
-
hainamchung Bundle Agent Assistant Design Fast 2⚡ Quick Design — Rapid component/UI design. Use when user types /design:fast.
-
alexandrbasis Skill Dev Server 4Start any project's dev server and monitor it for errors in real-time. Universal — works with Node.js (Next.js, Vite, Remix, Astro, SvelteKit, Nuxt, Angular, Gatsby, Expo), Python (Django, Flask, FastAPI, Uvicorn), Ruby (Rails, Sinatra), Go, Rust (Cargo), Java (Spring Boot, Gradle, Maven), PHP (Laravel, Symfony), Elixir (Phoenix), and Docker Compose. Auto-detects the stack and package manager from project files. Uses the Monitor tool to stream only errors, warnings, and crashes — not routine request logs. Use this skill whenever the user says "start dev server", "run dev", "start the app", "launch the server", "npm run dev", "cargo run", "python manage.py runserver", "rails server", "go run", or anything that implies starting a local development server. Also trigger when the user asks to "monitor the server", "watch the build", "check for errors while I work", or simply "dev".
-
netdata Skill Collectors Snmp Profiles 2Author or review Netdata SNMP polling profiles, ddsnmp parsing, topology/licensing/BGP rows and profile-format documentation. Check source MIB accessibility and row-index extraction for affected symbols. Trap profiles and topology payload design use their separate skills.
-
irahardianto Skill Accessibility Principles 3Apply WCAG accessibility standards when building UI components, forms, interactive elements, or any user-facing interface. Covers semantic HTML, ARIA attributes, keyboard navigation, color contrast, and screen reader support.
-
bobmatnyc Bundle Env Manager 4Environment variable validation, security scanning, and management for Next.js, Vite, React, and Node.js applications
71 -
bobmatnyc Skill Artifacts Builder 3Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui)
71 -
bobmatnyc Bundle Systematic Debugging 4Step-by-step debugging workflow: reproduce the bug, isolate the failing component, trace to root cause, apply a targeted fix, and verify the fix resolves the issue without regressions. Use when you encounter a bug, error, exception, crash, or unexpected behavior that needs troubleshooting.
71 -
archibate Bundle Read Url 3Extract clean, complete markdown from any web page — articles, docs, READMEs, blog/social posts, academic papers. Also use as a fallback when curl returns noisy HTML or WebFetch returns truncated, summarized, or refused results.
-
alexanderop Bundle Walkthrough 3Generate interactive HTML walkthroughs with clickable Mermaid diagrams (flowcharts and ER diagrams) that explain codebase features, flows, architecture, and database schemas. Use when asked to "walkthrough", "explain this flow", "how does X work", "trace the code path", "annotated diagram", "code walkthrough", "explain the architecture of", "walk me through", "database schema", "explain the tables", "data model".
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 backend-patterns, cicd-pipeline, test-strategy. 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.