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.
-
sheshiyer Bundle Vercel React View TransitionsAnimate React/Next.js UI state with native view transitions — shared elements, route transitions, transition types, and reduced-motion-safe patterns. USE WHEN adding view transitions or shared-element route animations in React.
-
sheshiyer Skill Configuring Tauri CapabilitiesConfigure Tauri v2 capabilities to bind permissions to specific windows and webviews for access control. USE WHEN writing capability files, scoping permissions per window label, setting desktop/mobile targets, or tightening frontend security boundaries.
-
sheshiyer Skill Creative Frontend OrchestratorRoute a creative-frontend task to the correct spoke — in-browser animation (GSAP ScrollTrigger, Anime.js, web-motion-library) over an Astro substrate, or render-time programmatic video (Remotion). USE WHEN a user wants motion, animation, scroll effects, or video on the web but hasn't named the specific tool, or needs to decide between a live interactive effect and a rendered video file.
-
sheshiyer Skill Integrating Tauri JS FrontendsConfiguring JavaScript frontend frameworks for Tauri v2 desktop apps (Next.js, Nuxt, Qwik, SvelteKit, Vite) with SSG setup and tauri.conf.json settings. USE WHEN integrating a JS framework into a Tauri v2 app or fixing static-output and dev-server config for it.
-
sheshiyer Skill Calling Frontend From Tauri RustCall the Tauri v2 frontend from Rust via the event system, channels, and JavaScript evaluation. USE WHEN emitting events from Rust to the webview, streaming data over IPC channels, or pushing state changes from backend to frontend.
-
sheshiyer Skill Calling Rust From Tauri FrontendCall Rust backend functions from the Tauri v2 frontend with invoke and #[tauri::command]. USE WHEN defining commands, passing arguments or return values across IPC, handling command errors, or wiring async frontend-to-Rust calls.
-
sheshiyer Skill Integrating Tauri Rust FrontendsIntegrating Rust/WASM frontend frameworks (Leptos, Yew, Dioxus, Sycamore) with Tauri v2 via Trunk, covering WASM compilation, Cargo.toml and Trunk.toml config, and withGlobalTauri API access. USE WHEN building a Tauri v2 app with a Rust/WASM frontend or wiring up Trunk.
-
sheshiyer Skill Understanding Tauri ArchitectureExplains Tauri's core architecture: the Rust backend, native webview integration, Core-Shell design, IPC mechanisms, and security model fundamentals. USE WHEN orienting to how a Tauri app is structured, deciding what belongs in Rust vs the frontend, or reasoning about the Core-Shell split.
-
ashfordeou Bundle Beta Factor AnalysisUse when you must quantify the common-cause contribution to redundant-channel failure: split a component failure rate into the independent rate (1 - beta) * lambda and the shared common-cause rate beta * lambda, compute the common-cause shock probability Q_cc = 1 - exp(-beta * lambda * t), compute the dual-channel failure probability that combines the independent double failure with the common-cause shock by inclusion-exclusion, and compute the CCF enhancement ratio over the independence-only assumption. Produces the rate split, Q_cc, the dual-channel CCF-inclusive probability and the enhancement ratio that gate redundancy credit decisions. Trigger: beta-factor-analysis, beta-factor, common-cause-fraction, ccf-probability, common-cause-model, redundant-channel failure, common-cause shock.
-
ashfordeou Bundle Brayton Optimum Pressure RatioUse when you must select the pressure ratio of a simple gas-turbine-cycle that maximizes the net specific work at the cycle temperature limits: compute the max-work pressure ratio from x_opt = sqrt(tau) for the ideal cycle and x_opt = sqrt(tau*eta_c*eta_t) with component efficiencies; check the zero-work limiting ratio, exactly the max-work ratio squared; and judge the verdict that the max-efficiency ratio diverges from the max-work ratio. Produces the ideal and lossy max-work pressure ratios, the zero-work limit with the r_zero = r_opt**2 cross-check, the specific work at the optimum, and the efficiency-versus-work verdict in SI units. Trigger: maximum specific work, max-work pressure ratio, gas turbine cycle pressure ratio selection.
-
ashfordeou Bundle Reliability Block DiagramUse when you must analyze aircraft system reliability with a reliability block diagram (RBD) per ARP4761A: evaluate a structure of blocks in series from constant failure-rate components, compute component and system mission reliability R(t) = exp(-lambda t), combine series, active parallel, k-out-of-n voting and cold standby redundancy blocks, derive exact block and system MTBF, convert a non-exponential block to an equivalent failure rate -ln(R)/t, and identify the dominant component whose failure rate drives system reliability by one-at-a-time sensitivity analysis. Parses a block structure of rates and returns system reliability, MTBF, per-block reliabilities and the dominant component. Produces the quantitative series-parallel reliability view that complements the fault tree logic view. Trigger: reliability block diagram, RBD, series parallel reliability, redundancy, k-out-of-n, standby, MTBF, mission reliability, failure rate.
-
ashfordeou Bundle Msg3 Maintenance AnalysisUse when you must run the MSG-3 maintenance steering group decision logic to develop a scheduled maintenance program for an aircraft system or component: categorize each failure mode by effect visibility (evident to the flight crew or hidden) and consequence (safety-significant or economic-only), select the applicable scheduled maintenance task categories (lubrication, servicing, operational check, visual check, inspection, functional check, restoration, discard), and assign the interval verdict including the hidden failure exposure rule at half the single-failure interval. Produces the failure category, the recommended task set with rationale, and the interval verdict that gate the maintenance program development handoff. Trigger: MSG-3, maintenance steering group, scheduled maintenance, hidden failure, evident failure, task category selection, exposure rule, interval determination, maintenance program development.
-
mturac Skill Repo ScanCross-stack source code asset audit — classifies every file, detects embedded third-party libraries, and delivers actionable four-level verdicts per module with interactive HTML reports.
-
tuyv Bundle Resend CLIOperate the Resend platform from the terminal — send emails (including React Email .tsx templates via --react-email), manage domains, contacts, broadcasts, templates, webhooks, API keys, logs, automations, and events via the `resend` CLI. Use when the user wants to run Resend commands in the shell, scripts, or CI/CD pipelines, or send/preview React Email templates. Always load this skill before running `resend` commands — it contains the non-interactive flag contract and gotchas that prevent silent failures.
-
tuyv Bundle Native Data FetchingUse when implementing or debugging ANY network request, API call, or data fetching. Covers fetch API, React Query, SWR, error handling, caching, offline support, and Expo Router data loaders (`useLoaderData`).
-
tuyv Bundle Swiftui ReviewReviews SwiftUI code for best practices on modern APIs, maintainability, and performance. This skill should be used when the user asks to review SwiftUI code, check for deprecated iOS/macOS APIs, validate data flow patterns, or audit accessibility compliance in Swift projects.
-
tuyv Bundle CritiqueEvaluate design from a UX perspective, assessing visual hierarchy, information architecture, emotional resonance, cognitive load, and overall quality with quantitative scoring, persona-based testing, automated anti-pattern detection, and actionable feedback. Use when the user asks to review, critique, evaluate, or give feedback on a design or component.
-
tuyv Bundle Next Devtools GuideProvides guidance on using the next-devtools MCP server. Use when working with Next.js projects that have the MCP server configured, when the user encounters connection issues, or when needing help with error detection, route inspection, Server Action tracing, or Cache Components migration.
-
tuyv Bundle React Best PracticesReact and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
-
tuyv Bundle Graphic OverlaysPackage an existing talking-head / interview / podcast video by layering timed, designed GRAPHIC OVERLAY cards onto the playing video — titles, lower-thirds, data callouts, quotes, side panels, picture-in-picture — synced to the transcript. The source video plays in full; the agent designs and writes each card's HTML in conversation, then renders to MP4 via hyperframes. Use when the user asks for graphic overlays, on-screen graphics / lower-thirds / data callouts / kinetic titles on a video, "package / dress up my video", "add overlay cards / graphic cards", or AI-composed graphic packaging of an existing video. NOT for plain subtitles (→ embedded-captions) or building a video from scratch (→ the creation workflows); when unsure overlays-vs-captions, see /hyperframes.
-
tuyv Bundle ExpoExpert on Expo and React Native — EAS Build (cloud iOS/Android builds + credentials), EAS Update (OTA updates, channels, runtime versions, staged rollouts), EAS Submit, Expo Router (file-based routing, dynamic routes, layout groups), Expo Modules API, managed vs bare workflow, and deployment. Invoke when user mentions Expo, React Native, EAS Build, EAS Update, OTA updates, Expo Router, file-based routing, or expo-* packages. Example queries — "configure eas.json for production builds", "publish an OTA update to the staging channel", "set up dynamic routes in Expo Router", "handle push notifications in a managed app".
-
javimosch Skill UI DesignerDesign beautiful interfaces using 16+ design systems including Material You, Fluent Design, Apple HIG, Ant Design, Carbon Design, Shopify Polaris, Minimalism, Glassmorphism, Neo-Brutalism, Neumorphism, Skeuomorphism, Claymorphism, Swiss Design, and Atlassian Design. Expert in Tailwind CSS, color harmonics, component theming, and accessibility (WCAG).
-
javimosch Skill Jina ReaderExtract clean, readable markdown content from any URL using Jina Reader API. Use when you need to fetch and parse web pages without dealing with HTML, JavaScript rendering, or paywalls. Ideal for research, article summarization, content analysis, and working with search results from tavily-search, web_search, or searxng skills.
-
javimosch Skill Sparkle VpnControl Sparkle VPN - start, stop, manage system proxy, query status and switch nodes using Mihomo core directly.
-
javimosch Skill Copilotkit React PatternsCopilotKit React best practices for agentic applications. Use when writing, reviewing, or refactoring React code that uses CopilotKit hooks (useAgent, useFrontendTool, useRenderTool, useCopilotAction, useCopilotReadable), providers (CopilotKit), or chat UI components (CopilotChat, CopilotSidebar, CopilotPopup). Triggers on tasks involving agent integration, tool rendering, shared state, or generative UI in React.
Audited -
caishengold Bundle Developer当需要执行编程类任务时使用。触发场景:网站开发、React/Vue组件开发、Python/Node.js脚本编写、API开发集成、代码修复调试、README编写。当用户提到"写代码"、"开发"、"React"、"API"、"bug修复"、"网站"、"脚本"、"组件"时应触发此技能。
-
tuyv Bundle SupabaseSupabase integration expert — Postgres schema design with RLS policies, Auth (email/OAuth/magic link, JWT claims), Realtime (Postgres changes, Broadcast, Presence), Storage (buckets + RLS), Edge Functions (Deno runtime, secrets, scheduled jobs), pgvector for embeddings, and client libraries (`@supabase/supabase-js`, `@supabase/ssr` for Next.js SSR). Invoke when user mentions Supabase, PostgreSQL + RLS, Supabase Auth, realtime subscriptions, Edge Functions, or pgvector. Example queries — "write an RLS policy so users only see their own rows", "set up Google OAuth with Supabase Auth and SSR cookies", "subscribe to INSERTs on a table from a React component", "store embeddings in pgvector and do similarity search".
-
tuyv Bundle Mkfast Deploy把 mkfast-template / TanStarter 系项目部署到 Cloudflare Workers —— 自动检测实际启用的组件(D1 / R2 / Email / Better Auth / Stripe / Creem / Beehiiv / 通知 / 分析),动态裁剪部署步骤。Use PROACTIVELY whenever 用户提到部署、上线、deploy 到 Cloudflare、wrangler、pnpm deploy、推到生产、发布站点、CF Workers 上线 —— 即使用户没明确说 "mkfast",只要项目含 `wrangler.jsonc` + `@tanstack/react-start` 或 `drizzle-orm` / `better-auth` 任一,就**优先使用此 skill 而非通用 wrangler / cloudflare skill**(本 skill 更懂 mkfast 的占位符、logpush 默认值陷阱、enable=false 陷阱、tailoring 策略)。SKIP when 项目明显不是 mkfast-template 派生(无 wrangler.jsonc + 无 @tanstack/react-start)→ 改用通用 wrangler skill。触发词:「部署到 Cloudflare」「deploy to Cloudflare」「mkfast 部署」「TanStarter 上线」「wrangler deploy」「准备部署」「上线前要做什么」「deploy 流程」「pnpm deploy」「推到 Cloudflare 生产」「ship to CF」「go live」「发布 CF Workers」「production deploy」「把网站上线」「上线我的 SaaS」。
-
tuyv Bundle Linkedin HumanizerRemove the AI tells human readers and LinkedIn's AI-slop filter react to in a post or comment: 2026 vocabulary by paragraph density, reveal bridges, staccato fragments, stacked triads, performed sincerity. Tiered rewriter (forensic / strict / aesthetic / all) plus `--mode audit` pass-fail review and `--mode profile` voice profile builder. Not for beating AI detectors (no edit reliably does). Keywords: humanize, de-AI, reads like ChatGPT, AI slop, scrub AI tells, review this draft, audit before posting.
-
tuyv Bundle IOS Simulator Skill29 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized for AI agents with minimal token output.
-
tuyv Bundle Hig Doctor AuditHIG Doctor audit workflow for scanning app projects against Apple Human Interface Guidelines. Use when the user asks for a HIG audit, Apple UI compliance scan, accessibility/design lint, HIG Doctor, severity report, CI gate, or wants to verify SwiftUI, UIKit, React, Next.js, Vue, Svelte, Angular, React Native, Flutter, Compose, Android XML, CSS, or HTML against Apple HIG rules.
-
tuyv Bundle Tw BlazorRazor file authoring — one @code at the top, markup, optional <style> last. Use when creating or editing .razor files, @code blocks, or in-file <style> tags. CSS placement: tw-blazor-css-strategy. App shell: tw-blazor-layout.
-
tuyv Bundle Blazor LayoutHow to structure Blazor app chrome with the "empty layout + cascaded page-component shell" pattern — keep LayoutComponentBase empty and put header/nav/content/aside/footer in ONE shell component that pages wrap their content in and that cascades itself. Use when designing a Blazor app's layout/navigation, deciding where chrome belongs, building a layout shell, or when chrome must react to a state store or per-navigation lifecycle that a layout can't provide.
-
tuyv Bundle Tw Blazor LayoutHow to structure Blazor app chrome with the "empty layout + cascaded page-component shell" pattern — keep LayoutComponentBase empty and put header/nav/content/aside/footer in ONE shell component that pages wrap their content in and that cascades itself. Use when designing a Blazor app's layout/navigation, deciding where chrome belongs, building a layout shell, or when chrome must react to a state store or per-navigation lifecycle that a layout can't provide.
-
tuyv Bundle Atlas ReportRender agent findings as a styled HTML report in the browser. Use when asked for "full report", "detailed report", "show in browser", or when CLI output exceeds the 40-line budget.
-
tuyv Bundle Blazor CSS StrategyHow to style Blazor + FluentUI components in this repo without Tailwind. The "isolation-first hybrid" convention — CSS isolation by default, global design tokens, and two documented exceptions for FluentUI shadow-DOM and light-DOM children. Use when authoring or restyling any .razor component, choosing where CSS lives, or styling a FluentUI component.
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 vercel-react-view-transitions, configuring-tauri-capabilities, creative-frontend-orchestrator. 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.