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.
-
deepnoodle-ai Skill Social Network DesignDesign and build social networking sites and community platforms. Use this skill when the user asks to create a social network, community platform, forum, feed-based app, or any site centered on user profiles, social interactions, content sharing, or community engagement. Covers UX architecture, visual design, engagement systems, moderation, and frontend implementation. Applies to full platforms, individual features (feeds, profiles, chat), or redesigns of existing social products.
-
jayteealao Bundle UiprotoPrototype a UI component/screen from a prompt. Fans out to Stitch + an LLM by default (side-by-side); a provider keyword yields one. Writes a self-contained, sandboxed HTML fragment. Internal to `/wf design`; invoke it through that key.
-
ssojet Bundle Oidc Hosted Page ReactImplement "Sign in with SSO" in React SPA applications using SSOJet OIDC with PKCE.
-
ssojet Bundle Oidc Hosted Page NextjsImplement "Sign in with SSO" in Next.js applications using SSOJet OIDC Authorization Code flow with the App Router.
-
cgbarlow Bundle IrisDrive the iris-cli command-line tool to search, browse, ask AI questions about, and export content from an Iris architecture-knowledge repository (https://github.com/cgbarlow/iris). Use whenever the user mentions iris in an architecture/systems context, references an iris diagram/element/package/set/collection, asks iris's AI a question about systems, or wants to export an iris artefact as JSON or Markdown — even when the user doesn't say "iris-cli" by name. The skill ensures iris-cli is installed (uv tool), guides login (SQLite mode is interactive; Supabase deployments require --token with an externally-minted PAT because /api/auth/login is disabled), prefers --json for machine-parsable output when chaining results, and routes the user to the correct iris-api backend host (not the SvelteKit frontend, not the iris-mcp service).
-
jack-taylor-gorman Skill Remotion VideoBest practices for Remotion - Video creation in React. Use when working with programmatic video generation, animations, compositions, and motion graphics.
-
jack-taylor-gorman 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.
-
sreenivasanac Bundle React UseeffectReact useEffect best practices from official docs. Use when writing/reviewing useEffect, useState for derived values, data fetching, or state synchronization. Teaches when NOT to use Effect and better alternatives.
-
shawn-sandy Bundle Wcag Compliance ReviewerReviews HTML/CSS and React code for WCAG 2.2 Level AA violations. Provides targeted fixes for each accessibility issue found. Use when the user asks to check WCAG compliance or audit accessibility.
-
jmmarotta Bundle Frontend DesignCreate distinctive, production-grade web UI. Use for web components, pages, apps, posters, landing pages, dashboards, React components, HTML/CSS layouts, or styling and beautifying existing web interfaces.
-
microsoft Bundle Maf Prs JobConvert an existing Prompt Flow Parallel Run Step (PRS) pipeline submission into an Azure ML PRS pipeline that runs a Microsoft Agent Framework (MAF) workflow. Wraps the MAF workflow into a PRS init()/run() entry script, generates the parallel component YAML and conda environment, and rewrites the pipeline submission script. Replaces what `load_component(flow.dag.yaml)` did automatically for Prompt Flow — produces the hand-built equivalent so that downstream pipeline code (`flow_node = flow_component(...)`, `flow_node.outputs.flow_outputs`, `flow_node.outputs.debug_info`, `flow_node.mini_batch_size`, scheduler, batch endpoint) stays unchanged. WHEN: convert promptflow PRS to MAF PRS, migrate PRS pipeline to agent framework, wrap MAF workflow as parallel component, bulk run MAF workflow, run agent framework as parallel run step, batch run MAF workflow on AML, submit MAF workflow as pipeline component, replace flow.dag.yaml with MAF workflow in pipeline, load_component equivalent for MAF workflow, MAF version o
2.7k -
dair-ai Skill X Agent IntelligenceBuild or refresh a readable local AI and agent intelligence feed from the official X MCP server. Use when the user asks for an X-based digest, monitoring dashboard, daily AI feed, source-account timeline, or a self-contained HTML artifact backed by X posts.
-
modelscope Bundle X MarkdownUse when building or reviewing Markdown rendering with @ant-design/x-markdown, including streaming Markdown, custom component mapping, plugins, themes, and chat-oriented rich content.
-
way-platform Bundle Way Typescript React StyleGuide for writing idiomatic, high-quality TypeScript and React code, and for writing or reviewing vitest tests. Use this skill when writing, refactoring, or reviewing TypeScript/React code or test files to ensure adherence to established conventions, React rules, performance best practices, and vitest testing patterns. Trigger proactively when writing React components, TypeScript types, Next.js pages, or vitest tests, or when auditing existing tests.
-
dotnet Bundle Aspireify**WORKFLOW SKILL** - Wire an Aspire AppHost after `aspire init` drops a skeleton. Scans the repo, proposes a resource graph, edits the AppHost (C#, file-based C#, or TypeScript), wires `Aspire.ServiceDefaults` + OTel, validates with `aspire start`, then self-deactivates. USE FOR: wire AppHost, scaffold resource graph, add Postgres/Redis/Rabbit/Mongo to Aspire, connect frontend to API, after `aspire init` what next, AddNextJsApp, AddViteApp, WithBrowserLogs, file-based apphost.cs, apphost.ts, unified withEnvironment, refuse .aspire/modules edit, migrate .env files, migrate user secrets. DO NOT USE FOR: skeleton drop (use aspire-init), start/stop/wait/restart (use aspire-orchestration), publish/deploy/destroy (use aspire-deployment), logs/traces (use aspire-monitoring). INVOKES: aspire CLI (add, start, wait, describe, docs api search, stop), AppHost source edits, ServiceDefaults wiring. FOR SINGLE OPERATIONS: Run `aspire add PACKAGE` directly for a one-off integration.
4k -
alexander-danilenko Skill ReactApply these opinionated React conventions when writing React 18+ or 19 components: hooks patterns, Server Components, Suspense boundaries, state management, performance memoization, React 19 features (use, form actions).
-
alexander-danilenko Bundle NestjsOpinionated house conventions for NestJS backends — module boundaries and layering, provider wiring and injection scopes, guards/interceptors/pipes/filters, DTOs and validation, domain exceptions, config, and the Nest 11 / Express 5 behaviour that compiles cleanly and fails at runtime. Use whenever the code is NestJS (`@nestjs/*` in package.json, or `@Module`/`@Injectable`/`@Controller`/`@Cron` in the file), including when the question sounds like plain TypeScript, an OOP refactor, a code review, or an ops problem — the Nest-specific answer differs from the generic one. Typical asks: scaffolding a module, adding a controller, provider, or endpoint, wiring an enhancer, a boot-time DI or circular-import failure, a response leaking entity fields despite `@Exclude()`, a cron job firing on every replica, upgrading NestJS, or reviewing a Nest diff. Not for plain Express or Fastify, Angular, frontend, SQL, or CI.
-
alexander-danilenko Skill NextjsApply these opinionated Next.js conventions whenever writing or reviewing App Router code (14+): Server Components by default, where the 'use client' boundary belongs, the caching defaults that changed in Next 15, tag-based revalidation, treating Server Actions as public endpoints, the Metadata API, and next/image and next/font.
-
seeed-studio Bundle Ee Datasheet MasterUse when user has/is reading a component datasheet or spec sheet to find chip parameters: pinout, voltage, I2C address, timing, register map, electrical characteristics. Trigger on PDF+chip questions. Also: 规格书, 数据手册, 芯片参数. All IC types.
-
wordpress Skill Emotion To Scss ModulesUse when planning or implementing an Emotion-to-SCSS-Modules migration in @wordpress/components, including styled wrappers, css/useCx composition, and migration-related cascade fixes.
-
eous Skill Typescript Best PracticesTypeScript development best practices, patterns, and conventions. Use when writing TypeScript code, reviewing .ts/.tsx files, discussing type safety, generics, utility types, or TypeScript project configuration. Triggers on mentions of TypeScript, tsconfig, type inference, generics, discriminated unions, React TypeScript.
-
benjaminhaeberli Bundle Gdpr AuditAnalyze a web application or codebase for GDPR/RGPD and nLPD (Swiss) compliance. Use when the user asks to audit, check, review, or analyze privacy compliance, data protection, GDPR, RGPD, nLPD, cookie consent, personal data handling, or user rights implementation. Also use when the user mentions "privacy by design", "données personnelles", "CNIL", "protection des données", "consentement", or "droit à l'effacement". Works with HTML, CSS, JavaScript, TypeScript, PHP, and common web frameworks.
-
benjaminhaeberli Bundle Ecodesign AuditAnalyze a web application or codebase for eco-design and digital sobriety. Use when the user asks to audit, check, review, or analyze the ecological impact, green IT compliance, eco-design, energy efficiency, or digital sobriety of a website, web app, or codebase. Also use when the user mentions "ecodesign", "green IT", "sobriete numerique", "eco-conception", "RGESN", or "115 pratiques". Works with HTML, CSS, JavaScript, TypeScript, PHP, and common web frameworks.
-
benjaminhaeberli Bundle Accessibility AuditAnalyze a web application or codebase for accessibility and WCAG compliance. Use when the user asks to audit, check, review, or analyze accessibility, a11y, WCAG, RGAA, inclusive design, or eCH-0059 compliance of a website, web app, or codebase. Also use when the user mentions "accessibilite", "handicap", "lecteur d'ecran", "screen reader", "ARIA", "contraste", "navigation clavier", "keyboard navigation", "focus", or "WAI". Works with HTML, CSS, JavaScript, TypeScript, PHP, Blade, Kirby, and common web frameworks.
-
benjaminhaeberli Bundle PHP Performance AuditAnalyze a PHP web application or codebase for performance issues and optimization opportunities. Use when the user asks to audit, check, review, or analyze the performance, speed, optimization, slow queries, caching, or scalability of a PHP, Laravel, Kirby, Livewire, or Blade application. Also use when the user mentions "performance", "lenteur", "slow", "N+1", "query optimization", "cache", "OPcache", "eager loading", "lazy loading queries", "index SQL", "optimisation", or "benchmark". Specialized for PHP, Laravel, Kirby CMS, Livewire, Blade, Vite, Tailwind CSS, and SQL databases.
-
redpanda-data Skill ReviewCode review a pull request for Redpanda Connect, checking Go patterns, tests, component architecture, and commit policy
6 -
redpanda-data Skill Common Schema AuditAudit every consumer of the schema.Common metadata format (the format produced by schema_registry_decode's store_schema_metadata, the parquet_decode processor, and CDC sources) for type-coverage drift and value-coercion gaps. Run this whenever a new component starts consuming schema.Common, when a new schema.CommonType variant is added upstream in benthos, or as a periodic maintenance check.
6 -
noklip-io Bundle NuqsUse when implementing URL query state in React, managing search params, syncing state with URL, building filterable/sortable lists, pagination with URL state, or using nuqs/useQueryState/useQueryStates hooks in Next.js, Remix, React Router, or plain React.
-
noklip-io Bundle React 19React 19 patterns and breaking changes vs React 18. Trigger: When writing React 19 components/hooks in .tsx (ref as prop, new hooks, Actions, deprecations). If using Next.js App Router/Server Actions, also use nextjs-15.
-
effect-ts-effect Bundle Vendored AssetsVendored assets. Use when importing or updating checked-in third-party or externally generated JavaScript, CSS, registries, schemas, snapshots, or Scalar, Swagger, and MIME artifacts.
-
thewaywithin Skill Saas EmailImplement transactional email for SaaS applications using Resend or Postmark — welcome emails, password resets, email verification, notifications, and plain-text/HTML templates. Use when building email, transactional email, email-sending, notification, or messaging features.
-
hive-intel Skill Hive BuildUse this skill when the user is integrating Hive into application code, backend services, agents, cron jobs, source-controlled adapters, or production systems — wiring Hive into a Next.js API route, a Python or Go cron job, a Rust or Java service, or a LangChain/CrewAI agent — rather than asking a one-off chat query.
-
ntaksh42 Bundle HTML Reportコードレビュー・調査・バグ解析・リサーチ・セキュリティ監査・改善提案の結果を、見やすいHTMLレポートとして保存・表示するスキル。「レポートを保存して」「結果をまとめて」「HTMLに出力して」「ドキュメントに残して」「レポートにして」などと言われたときに必ず使用する。また、明示的に依頼されていなくても、調査・レビュー・比較検討・改善提案の結果が長く構造を持つ(複数の指摘、比較表、複数観点の調査結果、「改善アイデア」「ブラッシュアップ案」「〜の仕様書」など)場合は、このスキルの使用をユーザーに提案する。種別を自動判定し、設定された保存先へ番号付きHTMLを生成してブラウザで表示する。Mermaid図・SVG図・進捗バー・重要度バッジ・目次・ダークモードに対応。
-
ntaksh42 Bundle Save Reportコードレビュー・調査・バグ解析などの結果をHTMLドキュメントとして保存するスキル。「レポートを保存して」「結果をまとめて」「HTMLに出力して」「ドキュメントに残して」「保存しておいて」「調査結果をファイルにして」などと言われたときに必ず使用する。会話の内容から種別を自動判定し、output-config.toml に設定された保存先へ番号付きHTMLファイルを生成する。コードレビュー、バグ調査、コード調査、リサーチ結果のどれにでも対応。
-
ebal5 Skill Show MeHelp the user understand the current topic visually. Pick the smallest view that makes the key point clear: pseudocode, call tree, component tree, file tree, Mermaid, diff, or one focused HTML artifact. 以下の依頼時に使用: - 「show me」「図で」「図解して」「可視化して」「絵にして」 - 「構造を見せて」「フローを描いて」「どう変わるか見せて」 - 今の議論の選択肢・構造・差分を図で示したいとき 以下では使用しない: - このセッションの実装内容を段階的に理解したい場合(→ teach-me を使う) - 自分の計画を批判的に詰めてほしい場合(→ grilling を使う)
-
devcsde Skill Oatda Generate SpeechUse when the user wants to generate speech/audio from text using OATDA's unified audio API. MCP generate_speech returns a short-lived signed AUDIO_URL (download with curl, no login). HTTP /api/v1/llm/speech returns a file via curl --output. Supports OpenAI TTS, xAI grok-tts, voiceovers, and accessibility audio.
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 nestjs, social-network-design, uiproto. 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.