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.
-
kbarbel640-del Bundle Zoho Email 2Complete Zoho Mail integration with OAuth2, REST API (5-10x faster), Clawdbot /email commands, HTML emails, attachments, and batch operations. Perfect for email automation and workflows.
1 -
eryajf Skill Pinecone RAG 2Build production RAG pipelines and persistent agent memory using Pinecone as the vector database backend. ALWAYS USE THIS SKILL when the user mentions Pinecone, wants to index documents for semantic search, build a retrieval-augmented generation system, store agent memory across sessions, implement hybrid search, or connect an LLM to a searchable knowledge base — even if they don't say "Pinecone" explicitly. Also use when the user asks about vector databases for RAG, namespace isolation for multi-tenant agents, embedding pipelines, or scaling a knowledge base beyond what local storage can handle. DO NOT use for local-only vector stores (Chroma, FAISS, pgvector) or pure keyword search with no semantic component.
0 -
helderberto Bundle E2e 2Write end-to-end tests for user flows using Cypress. Use when user asks to "write e2e tests", "/e2e", "add Cypress tests", or wants to test a user flow end-to-end. Don't use for unit tests, component tests, or projects using Playwright, Puppeteer, or other non-Cypress frameworks.
-
helderberto Bundle I18N 2Audit internationalization coverage and find hardcoded strings. Use when user asks to "check i18n", "/i18n", "find hardcoded strings", "check translations", or wants to verify translation coverage. Don't use for backend string extraction, non-frontend code, projects without an i18n library, accessibility (use /a11y-audit), or bundle size (use /perf-audit).
-
helderberto Skill Review 2Orchestrated REVIEW phase — fan out parallel, read-only reviewers over a diff (scope-detected audit skills AND independent agent lenses), then consolidate into one severity-ranked verdict. Use for a full pre-ship review, "review/validate this PR", or "spawn agents to review". Don't use to implement fixes (use /build or /tdd), for a single focused audit or one-lens pass (call it directly, e.g. /a11y-audit, /code-review), or to triage existing reviewer comments (use /triage-review).
-
helderberto Skill A11Y Audit 2Audit accessibility compliance in frontend code. Use when user asks to "check accessibility", "/a11y-audit", "audit a11y", "check WCAG", or wants to find accessibility issues. Don't use for backend code, non-UI files, projects without HTML/JSX output, bundle size (use /perf-audit), or translation coverage (use /i18n).
-
helderberto Skill Perf Audit 2Audit frontend bundle size and performance. Use when user asks to "audit performance", "/perf-audit", "analyze bundle", "check bundle size", or wants to find performance bottlenecks. Don't use for backend performance, database query optimization, projects without a frontend build step, accessibility (use /a11y-audit), or translation coverage (use /i18n).
-
helderberto Bundle Visual Review 2Render a GitHub Pull Request diff as a self-contained HTML page where each changed hunk is annotated with a software-principle explanation and a suggested simplification. Use when the user wants to review a PR visually, generate an HTML/visual diff report, or see PR feedback linked to principles (e.g. an unnecessary useMemo/useCallback) before commenting. Don't use for text-only PR feedback (use code-review), browser UI screenshots (use visual-validate), or orchestrating multiple reviewers (use review).
-
helderberto Bundle Codebase Design 2Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary. Don't use for codebase-wide structural audits (use /architecture-audit) or UI component design (use /frontend-ui-engineering).
-
helderberto Skill Frontend UI Engineering 2Front-load UI construction decisions — component boundary and prop API, where state lives, data/async, the required UI states (loading/empty/error), responsive behavior, and accessibility by construction. Use when creating or refactoring a component, page, or design-system primitive. Don't use for pure logic (tdd), throwaway direction exploration (prototype), generic module design (codebase-design), or auditing finished UI (a11y-audit/perf-audit/visual-validate).
-
darthlinuxer Bundle UI Styling 2Create 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.
-
darthlinuxer Skill Writing Plans 2Create comprehensive implementation plans for complex, multi-component tasks (>30 min, multiple files/modules, or >5 distinct steps). Breaks work into bite-sized tasks following TDD, DRY, YAGNI principles. After plan creation, execute using subagent-driven-development. For simple single-feature implementations, skip planning and use test-driven-development directly.
-
darthlinuxer Skill Tailwind Patterns 2Tailwind CSS v4 principles. CSS-first configuration, container queries, modern patterns, design token architecture.
-
darthlinuxer Bundle Nextjs React Expert 2React and Next.js performance optimization from Vercel Engineering. Use when building React components, optimizing performance, eliminating waterfalls, reducing bundle size, reviewing code for performance issues, or implementing server/client-side optimizations.
-
darthlinuxer Bundle Frontend Development 2Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, useSuspenseQuery, file organization with features directory, MUI v7 styling, TanStack Router, performance optimization, and TypeScript best practices. Use when creating components, pages, features, fetching data, styling, routing, or working with frontend code.
-
darthlinuxer Skill Web Design Guidelines 2Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".
-
acaprino Skill Xtermjs Skill 2Build, configure, debug, and extend in-page console UIs. TRIGGER WHEN: the user mentions xterm, xterm.js, @xterm/xterm, terminal emulator in the browser, web terminal, WebSSH, in-browser shell, addons like FitAddon, WebglAddon, SearchAddon, AttachAddon, integration with node-pty, ANSI/VT sequences, terminal theming, PTY over WebSocket, custom key handlers, parser hooks, or embedding a terminal in React/Vue/Angular/Electron apps.
-
acaprino Bundle Markmind Exporter 2Render a JSON outline into a drop-in vault file for the Obsidian plugin. TRIGGER WHEN: the user says 'markmind' or needs MarkMind Rich output from a mindmap structure, typically one produced by generate-mindmap. DO NOT TRIGGER WHEN: the user wants an interactive HTML mindmap (use forcegraph-exporter).
-
acaprino Bundle Pwa Development 2Knowledge base for the app layer of the web platform, and the gaps between engines. TRIGGER WHEN: building or auditing a PWA: Web App Manifest, service workers, Workbox, Serwist, vite-plugin-pwa, @angular/pwa, @vite-pwa/nuxt, Web Push, VAPID, Declarative Push, beforeinstallprompt, Window Controls Overlay, OPFS, Background Sync, Wake Lock, Project Fugu, Bubblewrap, TWA, PWA Builder, Capacitor. DO NOT TRIGGER WHEN: React performance (use react-development:review-react), non-PWA platform security (use platform-engineering), or Tauri and Electron shells (use tauri-development).
-
acaprino Bundle Forcegraph Exporter 2Render a JSON outline into a standalone browser page; needs internet for the CDN. TRIGGER WHEN: the user says 'interactive map', 'force graph', 'web mindmap', or 'HTML mindmap', or asks for a zoomable, draggable visual export. DO NOT TRIGGER WHEN: the user wants Obsidian MarkMind format (use markmind-exporter).
-
hack23 Skill C4 Architecture Documentation 2Document system architecture using C4 model with context, container, component views and Mermaid diagrams
-
rwilson504 Skill Cad Render Images 2Generate publication-quality PNG/GIF/MP4 renders from build123d models for documentation sites, README hero shots, and embedded HTML images. USE FOR: hero/isometric renders, web-optimized PNGs, exploded views, cross-section/cutaway renders, animated turntables, color preservation from build123d Color() tags, transparent or dark-theme backgrounds, HTML <img>/<picture> embedding patterns, documentation render pipeline, headless render with trimesh + pyvista, render PCB assembly, render enclosure with components.
-
rwilson504 Skill Cad Glb Component Map 2Export named, colour-tagged GLB component maps from build123d so a human and an AI can name parts of a model out loud ("make the blue plates thicker") and inspect them in a glTF viewer. USE FOR: colour in STL, does STL support colour, name parts in a viewer, GLB hierarchy, glTF node names, component map, assembly view, interference check, view model in VS Code, shared vocabulary for design review.
-
rwilson504 Skill Streamdeck Property Inspector 2Stream Deck property inspector (PI) UI: HTML in *.sdPlugin/ui/, sdpi-components web components (sdpi-item / textfield / select / checkbox / range / file / password / color / button etc.), streamDeckClient (setSettings, getSettings, send, onDidReceiveSettings, onSendToPlugin), action vs global settings, sending sendToPropertyInspector from plugin, debugging at localhost:23654, security (never store secrets in action settings — use global). USE FOR: building an action configuration UI, sdpi-components, web components for PI, settings persistence patterns, plugin↔PI messaging, secure token storage, PI ↔ plugin handshake on open, dropdowns populated from plugin (e.g. fetched device list), zod validation of settings.
-
zephyrwang6 Skill Remotion Video 2使用 Remotion 框架以编程方式创建视频。Remotion 让你用 React 组件定义视频内容,支持动画、字幕、音乐可视化、3D 视频、教程讲解视频等。适用于程序化视频、批量生成、数据驱动视频、音乐可视化、自动字幕等场景。
-
matevip Skill Sketch 2Throwaway HTML mockups: 2-3 design variants to compare.
-
matevip Skill Claude Design 2Design one-off HTML artifacts (landing, deck, prototype).
-
matevip Bundle Popular Web Designs 254 real design systems (Stripe, Linear, Vercel) as HTML/CSS.
-
matevip Bundle Architecture Diagram 2Dark-themed SVG architecture/cloud/infra diagrams as HTML.
-
acaprino Bundle Skills Creator 2Creates new Claude Code plugin components: skills, agents, commands, full plugins. Also decides skill vs agent architecture. TRIGGER WHEN: the user asks to create, add, scaffold or build a new skill, agent, command or plugin, or says "new skill", "new agent", "new plugin", "skills-creator", "skills-hammer". DO NOT TRIGGER WHEN: editing or updating an existing component, or auditing marketplace integrity (use marketplace-audit instead).
-
acaprino Bundle React Best Practices 2Vercel Engineering's 70 rules, ordered by impact across 8 categories. TRIGGER WHEN: writing, reviewing, or refactoring React or Next.js code: components, pages, data fetching, bundle size, or render performance.
-
acaprino Skill Typescript Write 2Apply house coding standards to everyday application work. TRIGGER WHEN: writing or reviewing TypeScript/JavaScript code, including types, generics, async patterns, module boundaries, and style conventions. DO NOT TRIGGER WHEN: React performance (use react-development), or advanced type-system depth (use mastering-typescript).
-
acaprino Bundle Mastering Typescript 2Deep reference for advanced TypeScript. TRIGGER WHEN: migrating JavaScript to TypeScript, bootstrapping a TS project (strict tsconfig, ESLint, Vite/Vitest, pnpm), writing generics, mapped or conditional types, `satisfies`, branded types, discriminated unions or template literal types, designing Zod schemas for runtime validation, building type-safe NestJS APIs, deep React and TypeScript typing, typing LangChain.js, or comparing TS with Java/Python enterprise approaches. DO NOT TRIGGER WHEN: routine TS/JS (use typescript-development:typescript-write), React performance (use react-development:review-react), or dead-code detection (use typescript-development:knip).
-
dokhacgiakhoa Bundle Frontend Design 2Design thinking and decision-making for web UI.
505 -
dokhacgiakhoa Bundle Nextjs React Expert 2React and Next.js performance optimization from Vercel Engineering.
505 -
dokhacgiakhoa Bundle Modern Web Architect 2Master Frontend & Web Architecture.
505
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 zoho-email, pinecone-rag, e2e. 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.