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.
-
prof-ramos Bundle Edital VerticalizadoTransforma editais de concurso público em edital verticalizado estruturado (tabela por tópico estudável). Aceita PDF, HTML, Markdown, DOCX, TXT ou texto colado. Entrega Markdown, CSV, XLSX ou JSON.
-
prof-ramos Bundle Resend APIAlways use when the user asks to send transactional or batch emails, configure custom email domains, manage API keys, verify Svix webhooks, handle email templates (HTML/React Email), or manage audiences and contacts using Resend API or SDKs (Node.js, Python). Trigger phrases include: 'resend', 'send email resend', 'enviar email resend', 'resend api key', 'resend domain', 'resend webhook', 'resend email template', 'resend audiences', 'resend contacts', 'gerenciar dominio resend', 'verificar webhook resend'.
Audited -
rynhardt-potgieter Skill Event MqttEvent-driven architecture standards — MQTT patterns (MQTTnet), Server-Sent Events (SSE), pub/sub design, topic hierarchies, QoS levels, message schemas, event sourcing, outbox pattern, and idempotency. Use this skill when implementing MQTT messaging, SSE streams, event handlers, pub/sub systems, or any asynchronous communication between services or between backend and frontend.
-
rynhardt-potgieter Skill Zod Rjsf FormsSchema-driven questionnaire engine — Zod as the single source of truth, converted to JSON Schema and rendered with react-jsonschema-form (RJSF). Use this skill when building multi-section data-capture forms (onboarding, tax/compliance questionnaires, declarations), a Zod→JSON-Schema conversion utility, tabbed section layouts, or any form where a schema drives rendering and validation. Covers the cross-tab validation-error-summary rule and the 'A-or-B' schema representability rule.
-
rynhardt-potgieter Skill React TypescriptReact 19 + TypeScript 5.9 + Vite 7 + Tailwind 4 + Zustand + React Query frontend standards. Use this skill when writing or reviewing any frontend code — components, hooks, stores, API clients, routing, styling, or state management. Also use when debugging React rendering issues, TypeScript errors, or state management problems.
-
rynhardt-potgieter Skill Nextjs App RouterNext.js App Router + React 19 + Tailwind v4 + shadcn-on-Base-UI + TanStack Table/Query frontend standards. Use this skill when writing or reviewing any App Router web code — pages, layouts, server/client components, server-side auth guards, data tables, forms, styling, or data fetching. Covers the server-side auth-boundary pattern, shadcn-first component selection, design-token alignment, and the persistent-surface rule for compliance/assurance messages.
-
jordanchoo Bundle DirectusDiscipline for self-hosted Directus headless CMS projects with row-level multitenancy, custom extensions, and Directus-backed frontend builds. Use when the repo has docker-compose with `directus/directus`, an `extensions/` folder, `@directus/sdk` or `@directus/extensions-sdk` in deps, a `snapshot.yaml` / schema migration file, or the user mentions Directus, collections, flows, hooks/endpoints/operations, filter rules, permissions, policies, schema snapshots, `PUBLIC_URL`, or `CORS_ORIGIN`. Encodes the row-level tenant pattern, frontend offline/cache fallback, self-hosted env triage, extension discipline, schema-promotion workflow, and recurring traps seen in real sessions.
Audited -
jordanchoo Skill Astro SiteDiscipline for Astro v5 static-site projects (Tailwind v4, MDX, content collections, sitemap, RSS). Use when the repo has astro.config.{mjs,ts}, src/content.config.ts, or `astro` in deps; when adding content collections, pages, redirects, or sitemap entries; when migrating a site from WordPress or another platform; when debugging Astro build/check failures. Encodes the canonical layout, content schema patterns, sitemap filter, redirect handling, and Tailwind v4 conventions used across this user's Astro template lineage.
-
saturate Skill Performance ProfilingGuides active performance investigation with measure-identify-fix-measure cycle for both frontend and backend. Triggers chrome-devtools for frontend profiling. Use when profiling performance, investigating slow code, optimizing speed, performance issues, slow page, slow API, latency problems, or when something feels sluggish.
-
saturate Skill Frontend UI EngineeringGuides frontend UI development with component hierarchy, separation of concerns, accessibility as requirement, and performance awareness. Framework-agnostic, detects stack from project. Triggers chrome-devtools for verification. Use when building UI, frontend development, creating components, UI engineering, component architecture, building pages, or when working on frontend code.
-
epam Skill Fe API HandoffUse when the user wants to hand off the current branch's changes to a frontend developer/agent — "summarize changes for the FE", "write FE handoff", "what API changes does the frontend need". Works for a raw POC branch or one or more implemented opsx changes. Diffs the current branch against `development`, and writes a single raw-HTML instruction file (wrapped in one `<important>` block, no styling) to `/tmp/fe-api-handoff/` containing the overall context plus every API contract change (endpoints, request/response DTOs, status codes & errors, enums/constants) the frontend must support. Never makes UI/UX judgments. Chat gets brief highlights + the file path only.
-
gsd-build Skill Dependency UpgradePlan, batch, and verify dependency upgrades safely. Triages outdated packages into risk tiers, upgrades in order (dev/minor/patch first, runtime majors last), verifies each batch before moving on, and produces an auditable commit sequence. Use when asked to "upgrade deps", "bump packages", "update node_modules", "fix vulnerabilities", "upgrade React/Node/TypeScript", or after `/gsd start dep-upgrade`. Complements the dep-upgrade workflow template with execution-level rigor.
256 -
databricks Bundle Databricks Apps PythonBuilds Databricks applications. Prefers AppKit (TypeScript + React SDK) for new apps; falls back to Python frameworks (Dash, Streamlit, Gradio, Flask, FastAPI, Reflex) when Python is required. Handles OAuth authorization, app resources, SQL warehouse and Lakebase connectivity, model serving, foundation model APIs, and deployment. Use when building web apps, dashboards, ML demos, or REST APIs for Databricks, or when the user mentions AppKit, Streamlit, Dash, Gradio, Flask, FastAPI, Reflex, or Databricks app.
Audited -
gustavo-meilus Bundle More With LessApply minimum-sufficient engineering to project development, design, debugging, refactoring, specification, architecture, dependencies, tooling, agents, hooks, MCP, automation, and verification. Use for non-trivial project work where unnecessary complexity should be minimized without weakening correctness, security, data integrity, accessibility, operability, observability, or acceptance criteria. Do not use for pure prose or unrelated non-project tasks.
-
larsboes Bundle UnslopStrips the tells that make source code and web UI read as AI-generated and forces a deliberate, project-specific choice instead of the model's default average. It writes neither the code nor the design, and has no house style. Code: chat artifacts, placeholder comments, emoji, swallowed errors, generic names like process_data, plus the structural tells a linter passes (tutorial boilerplate, hallucinated APIs, over-engineering, ignoring the surrounding repo). UI: default shadcn/Tailwind, AI-purple gradients, emoji-as-icons, the hero-plus-three-cards skeleton, and the newer cream-serif-sage 'tasteful default'. Use whenever writing, generating, reviewing, refactoring, or auditing code or a web interface, especially when it 'looks AI-generated', 'reads like a tutorial', is 'too generic' or 'vibe-coded'. Trigger even if the request never says AI tell. Do not use for prose a human reads (use human-writing), thesis text (use academic-writing), or agent skills (use writing-skills).
Audited -
larsboes Bundle HomectlMaterializes overlay-owned Home Assistant templates and vendors overlay-owned pinned components through a public, host-neutral CLI. Use for template coverage, materialization, or reviewed component vendoring. Real devices, automations, entity IDs, component selections, and output stay in the active private overlay.
-
michelve Bundle ReactCore React 19 patterns for DSAI projects including hooks, Suspense, lazy loading, component structure with forwardRef, TypeScript best practices, and performance optimization. Use when working with React components, hooks, lazy loading, Suspense boundaries, or React-specific TypeScript patterns.
-
michelve Skill Dsai ToolsCLI reference and build system documentation for the @dsai-io/tools package. Covers the `dsai` command, component/hook/util installation from registry, design-token pipeline, icon generation, configuration schema, and framework mappers.
-
michelve Skill Dsai StylingDSAI styling system reference, Bootstrap 5 utilities, CSS custom properties (design tokens), cn() utility, dark mode, and token pipeline. Replaces the old tailwindcss skill. Use this skill when generating or modifying styles, classNames, or theme configuration in DSAI consumer applications.
-
michelve Bundle AccessibilityUse this skill for any accessibility concern: WCAG compliance (any success criterion including SC 1.3.5 autocomplete, SC 2.4.11 focus obscured), ARIA roles/attributes, screen reader behavior, axe-core or WAVE audit failures, color/non-text contrast, keyboard navigation, focus trapping/management, skip links, touch targets, VPAT reports, or accessible form patterns. Also trigger when a user asks whether a UI library (DSAI) handles keyboard interactions — but only if the question is specifically about accessibility behavior, not general usage. Do NOT trigger for general component usage questions where keyboard behavior is incidental (e.g., "does DSAI Tooltip show on hover and focus?" without an accessibility problem to solve).
-
michelve Bundle Dsai ComponentsComprehensive reference for the DSAI component library. Guides AI agents on installing, importing, composing, and extending DSAI components in consumer projects. Covers the full component catalog (38+), type system, FSM patterns, compound components, hooks, utilities, and critical conventions.
-
michelve Bundle Component VisualizerGenerate interactive HTML dependency graphs for React components. Use when asked to "visualize components", "show component dependencies", "dependency graph", "component map", or "what depends on what".
Audited -
michelve Bundle React Best PracticesReact performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React code to ensure optimal performance patterns. Triggers on tasks involving React components, data fetching, bundle optimization, or performance improvements.
-
michelve Bundle Web Design GuidelinesReview 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".
-
gkwa Bundle TsconfigAdd a tsconfig.json for TypeScript projects using Vite and/or Chrome extensions. Use when setting up TypeScript in a frontend or Chrome extension project.
-
gkwa Bundle Use ViteSet up Vite and Vitest as the build and test tools, with vite-plugin-checker for TypeScript checking and ESM configuration. Use when starting or configuring a frontend project.
-
grahamcrackers Skill ViteVite configuration patterns for React and TypeScript projects including plugins, environment variables, proxy setup, build optimization, library mode, and SSR. Use when configuring Vite, setting up dev servers, optimizing builds, creating Vite plugins, or when the user asks about Vite configuration, HMR, or build tooling.
-
grahamcrackers Skill ZustandZustand state management patterns for React including store design, selectors, slices, middleware (immer, persist, devtools), and async actions. Use when managing client-side state, creating stores, working with Zustand, or when the user asks about global state management, store patterns, or state persistence.
-
grahamcrackers Skill StorybookStorybook 8 patterns for component-driven development including writing stories, args and controls, interaction testing, documentation, and addon configuration. Use when building component libraries, writing stories, testing interactions, documenting components, or when the user asks about Storybook, component isolation, or visual testing.
-
grahamcrackers Skill TailwindcssTailwind CSS v4 best practices including CSS-native configuration, theme variables, modern utilities, and migration patterns. Use when writing Tailwind CSS, styling components, configuring Tailwind, working with the v4 theme system, or when the user asks about Tailwind conventions or migration.
-
grahamcrackers Skill React RouterReact Router v7 patterns for client-side routing including nested routes, loaders, actions, route params, search params, navigation guards, and code splitting. Use when setting up React Router, creating routes, handling navigation, loading route data, or when the user asks about React Router, SPA routing, or route configuration.
-
grahamcrackers Skill Framer MotionFramer Motion animation patterns for React including transitions, variants, layout animations, AnimatePresence, gestures, scroll animations, and performance optimization. Use when animating React components, building transitions, adding micro-interactions, or when the user asks about Framer Motion, React animation, or motion design.
-
grahamcrackers Skill State MachinesXState v5 patterns for state machines and statecharts in React including machine design, actors, guards, actions, services, parallel states, and React integration. Use when modeling complex UI state, building multi-step flows, managing async processes, or when the user asks about state machines, XState, statecharts, or finite state automata.
-
grahamcrackers Skill Tanstack QueryTanStack Query v5 patterns for server state management, caching, mutations, optimistic updates, and query organization. Use when working with TanStack Query, React Query, server state, data fetching hooks, or when the user asks about caching strategies, query invalidation, or mutation patterns.
-
grahamcrackers Skill Tanstack TableTanStack Table v8 patterns for building headless, type-safe tables in React with sorting, filtering, pagination, and virtualization. Use when building data tables, grids, or list views, or when the user asks about TanStack Table, React Table, column definitions, or table state management.
-
grahamcrackers Skill Vitest TestingVitest and Testing Library patterns for unit, component, and integration tests in TypeScript and React projects. Covers test organization, mocking, assertions, component testing, and MSW integration. Use when writing tests, setting up Vitest, mocking dependencies, testing React components, or when the user asks about testing patterns or test configuration.
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 dependency-upgrade, performance-profiling, zod-rjsf-forms. 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.