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.
-
insightfulanalytics Bundle Pbi Report DesignThe Power BI report design canon covering design identity, visual hierarchy and the 3-30-300 rule, layout/spacing/alignment, color discipline, chart selection, KPI and card design, tables and matrices, accessibility, and the closing design gate. The shared reference home for report design judgment, routed to by the create-pbi-report, pbir-cli, review-report, modifying-theme-json, and custom-visual skills. Load when committing a design identity or making a design, layout, color, chart-selection, or accessibility decision for a report.
-
letsloose501 Skill Claude ReservedConverts a <table> element into a markdown table. Use when HTML is pasted in, or when the user asks for a markdown version of a table.
-
insightfulanalytics Bundle Pbi PlanPlan a multi-session Power BI report or model build as a numbered ticket map with an HTML plan board. Use when the user asks to plan a build, map out a report, or resume a build that spans more than one session. User-invoked only, via /pbi-plan.
-
lmaick Skill Nextjs App RouterEspecialista em arquitetura Next.js App Router (Next 15/16) e React 19. Aplica padrões estritos de Data Access Layer (DAL), Server Components por padrão, Server Actions validadas com Zod, streaming de UI com Suspense e prevenção de vazamento de estado.
-
yogiraja Bundle Conference Talk DeckUse when the user wants to create a new conference talk / presentation deck (a slide deck), or asks to "make a deck", "start a talk deck", "scaffold slides", or mentions building a PlumDeck-style presentation. Interviews the user, then generates a self-contained, offline HTML slide deck with built-in author mode.
-
yogiraja Bundle Primitive ClassifierAudit a folder for Claude Code primitives (skills, MCP servers, subagents, hooks, settings.json, CLAUDE.md) and classify each item into the primitive that actually fits, cross-checked against Anthropic docs. Produces a self-contained interactive HTML report with KPI hero, today vs target layout tabs, an explicit migration list, the 7-question decision framework, and provenance badges flagging documented vs inferred vs org-specific claims. Use when the user says "audit primitives", "classify skills and MCP", "primitive audit", "where does this content belong", "is this stuff in the right place", "review my Claude setup", or after generating any deck or doc that asserts which primitive a piece of context belongs in.
-
yogiraja Bundle Sdd Workshop WalkthroughGenerate a self-contained, animated, single-file HTML workshop walkthrough in the Athena SDD house style (the specworkshop.html / repo.html players): a step-by-step player with a workflow diagram, progress meter, narrated action band, expected-outcome boxes, a terminal/file/tree/scene artifact panel, toggleable trainer notes, autoplay, and keyboard nav. Use this WHENEVER the user wants an animated or interactive HTML walkthrough, workshop page, hands-on lab page, guided demo, or "click-through" explainer for a tool, script, repo, or CLI workflow, and ESPECIALLY when they reference an existing page like specworkshop.html or repo.html, say "like that other workshop", "same style", "animated HTML for this workshop", "make a repo.html / foo.html for X", or ask to turn a set of workshop steps into a playable page. Trigger even if they do not say the word "skill". Do NOT use for PowerPoint/Google Slides decks (use a pptx skill), for general web apps or dashboards, or for static prose docs.
-
tommyducx Bundle Tri Frontend Design前端设计技能——为构建或重塑前端提供"风格锚点"驱动的可视化方向(静态视觉层),并补齐"时间维度 + 交互物理层":动效引擎(频率闸门/缓动/弹簧/可中断性/GPU 属性/性能/a11y)、动效评审与全库审计、多变体探索。通过配色/字体/结构/质感锁定具体 CSS 令牌,并要求屏幕内容命名真实信息而非编造。支持独立安装,含上游依赖检测三态逻辑(快照/引导/降级)。当用户要"做/改一个前端界面""设计一套有风格的 UI""给界面加动效/评审动效""想看几个方向再选"时激活。
-
arozumenko Bundle Accessibility AuditAccessibility and WCAG compliance analysis, from the accessibility snapshot and visual review — flags issues automated axe-style scans miss.
-
arozumenko Bundle Screen SpecsUse when screens need designing or documenting as reference a developer or agent can build from — "design the screens", "screen specs", "what should this screen look like", "turn the flows into designs", "document the UI", or when a flow map's nodes need to become actual screens. Produces standalone HTML pages showing each screen as a device-framed mock beside its spec — regions with Material component and token names, every state the criteria demand, the MD3-vs-platform calls, accessibility notes, and traceability back to a flow node and acceptance criterion. Mock and spec are generated from one source so they cannot drift. NOT for flow/journey diagrams (use user-flow-maps), NOT a design tool replacement, and NOT for writing the screens' production code.
-
tommyducx Bundle Frontend DesignCreate distinctive, production-grade frontend interfaces with high design quality. Use this skill when building web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.
-
yogiraja Bundle ArchifyCreate polished, validated architecture, workflow, sequence, data-flow, and lifecycle/state diagrams as explorable standalone HTML with inline SVG, dark/light themes, optional trace motion, and PNG/JPEG/WebP/SVG/WebM export. Accept plain-language requirements or pasted Mermaid flowchart, sequenceDiagram, and stateDiagram input; inspect repository evidence when the diagram must reflect real code. Use when the user asks to visualize system architecture, infrastructure, cloud/security/network topology, technical workflows, API call sequences, request lifecycles, data pipelines, ETL/ELT, data lineage, state machines, or to convert/beautify Mermaid.
-
arozumenko Bundle User Flow MapsUse when a user flow, journey, or screen-to-screen behaviour needs to become a visual flow map — "draw the flow", "make a flow map", "user flow diagram", "map the screens", "turn these journeys into diagrams", or when acceptance criteria need a picture reviewers can sign off on. Renders a spec of screens, decisions and transitions into standalone HTML posters — numbered screen wireframes, decision diamonds, Start/End markers naming where a flow hands off, orthogonal connectors routed from the data, and an authoritative edge table. Layout, routing and label collision are handled by the bundled flowmap.js; you supply data, never coordinates. NOT for architecture or sequence diagrams, NOT for visual/UI design of the screens themselves (that is a design role's job), and NOT a mermaid replacement — the source diagram stays canonical.
-
arozumenko Bundle User Flow Maps 2Use when a user flow, journey, or screen-to-screen behaviour needs to become a visual flow map — "draw the flow", "make a flow map", "user flow diagram", "map the screens", "turn these journeys into diagrams", or when acceptance criteria need a picture reviewers can sign off on. Renders a spec of screens, decisions and transitions into standalone HTML posters — numbered screen wireframes, decision diamonds, Start/End markers naming where a flow hands off, orthogonal connectors routed from the data, and an authoritative edge table. Layout, routing and label collision are handled by the bundled flowmap.js; you supply data, never coordinates. NOT for architecture or sequence diagrams, NOT for visual/UI design of the screens themselves (that is a design role's job), and NOT a mermaid replacement — the source diagram stays canonical.
-
swyxio Skill Web PerfMeasure, diagnose, or review web page performance when page speed, Core Web Vitals, Lighthouse performance, loading behavior, or a named performance regression is the primary task. Use current browser evidence and first-party documentation. Do not turn a focused metric investigation into a full performance, accessibility, bundler, and codebase audit.
-
swyxio Skill Schedule DesignDesign patterns and lessons for building conference schedule pages with React. Covers theme systems, 2D grid overviews, filter UX, sticky layouts, modals, favorites, and data normalization. Use when building or modifying schedule views, grid tables, filter panels, or conference UI components.
-
swyxio Skill Web Animation PerfPrevent layout/transition/reflow thrash in JS-driven CSS animations. Use when building or debugging continuous motion (rotation, orbit, parallax, scroll-linked effects, marquee, carousels) and when symptoms appear like jank, stutter, lag, animation drift, ghosting, "elements collapsing toward center", "going slow", "should we use canvas?", or when mixing `setInterval`/React state with CSS `transition`.
-
swyxio Skill Sync Url NavigationSyncs URL query parameters with app navigation, tabs, and filter state so views are bookmarkable and shareable. Use when building or changing frontend routing, filters, tabs, modals, deep links, browser back/forward, or when the user asks to remember navigation in the URL, sync state to query params, or make screens linkable.
-
ivy00johns Bundle Render SanityLightweight visual sanity check that catches failure modes passing "tests green + dev server boots + 0 console errors" but visibly breaking the app when a human clicks — stale mock IDs on "live" pages, lone `?` / `—` / `undefined` / `Loading…` where data should be, dead links from list pages, and "Couldn't load X / Unauthorized" dead-end shells. Runs four objective checks BEFORE the build is declared done: smell scan, click-through every list, signed-out matrix, signed-in matrix. Use when a build is wrapping up, after ux-review or qe-agent finishes, when the user says "is it actually working", "broken pages", "dead links", or pastes a screenshot showing `?`, `undefined`, or a "Not found" page. Also invoke proactively when a frontend agent rewires mocks → real backend, when auth was added, or when seed data is regenerated.
-
ivy00johns Bundle Wiki ResearchRead the project's Obsidian-style wiki (index.md + wiki/) BEFORE any codebase exploration, repo-deep-dive, or raw source reading. Reading 3-4 wiki pages (~2,000 tokens) typically replaces crawling raw source directories (~100,000-500,000 tokens). Always invoke when orchestrator, a role agent, or code-review needs project context, architecture, component knowledge, or design decisions before touching files. Trigger on "how does X work", "understand the architecture", "review this code", or "build X" when project context matters. Skip only for purely mechanical tasks (rename a variable, fix a typo) where zero project understanding is needed.
-
ivy00johns Bundle Interactive DocProduce rich documentation as a paired Obsidian-friendly markdown source plus a self-contained HTML companion built from it — the .md is canonical, the HTML is the experience. Two workflows: (A) render an existing research markdown file into an HTML companion (the .md stays read-only by default), or (B) write both for a new doc, .md first as the substantive source and the HTML derived from it. Trigger for architecture deep-dives, module maps, concept explainers with interactive demos, side-by-side repo/approach comparisons, feature walkthroughs, or whenever the user says "interactive doc", "wiki page", "Obsidian doc", "explainer", "render this research", "architecture diagram", or "compare these repos". Output is always a pair: an Obsidian-native `.md` plus a self-contained `.html`.
-
ivy00johns Bundle Artifact PublishPublish a visual or interactive deliverable as a Claude Code Artifact — a self-contained HTML/Markdown file rendered to a hosted, default-private claude.ai web page the user can share with a link — instead of leaving it as a local file. Use whenever a result reads better as a page than as text: a dashboard, rendered report, chart or diagram, comparison, prototype, walkthrough, or mockup you built in code. Trigger on "publish this as an artifact", "make a shareable link", "host this page", "turn this into a web page", "claude artifact", "publish the dashboard", "share this report as a page", "give me a link to this", "put this on claude.ai". This is the Claude Code Artifact feature (code.claude.com), NOT the claude.ai design canvas (that is claude-design-brief). It is the publish step for the visual-output skills — interactive-doc, mermaid-charts, dataviz, nano-banana — and defers all look-and-feel to the artifact-design skill.
-
ivy00johns Bundle Design Token GuardSource-level gate that prevents inline styles and hardcoded CSS from bypassing a project's design-token system. Use whenever frontend work touches colors, styling, or themes — before committing or declaring a UI task done, when auditing for hardcoded hex/rgb/inline styles, when setting up enforcement so inline CSS can't slip in again, or as an orchestrator/agent wave-gate. Trigger on: "inline CSS", "inline styles", "hardcoded colors", "hardcoded hex", "style={{}}", "theme/token drift", "design tokens", "we keep shipping inline styles", "lint for tokens", "why did this get through review". Framework- and stack-agnostic (React/JSX, Vue, Svelte, Angular, Astro, HTML; CSS variables, SCSS/Less, JS theme objects, design-token JSON) — auto-discovers the project's tokens; NOT specific to any one repo or to Tailwind. Don't skip it because a render review passed: render gates can't see a hardcoded color — it renders identically to the token.
-
ivy00johns Bundle Frontend AgentOrchestrator-dispatched only. Builds user interfaces, client-side state, and presentation layers for multi-agent builds. Composes with frontend-design and ui-ux-pro-max for visual quality. Not user-invocable.
-
ivy00johns Bundle PlaywrightRun browser-based E2E tests, capture screenshots, and validate user flows using Playwright with visible Chrome. Use this skill when testing a web UI end-to-end, capturing screenshots for visual review, checking responsive layouts, or auditing accessibility in a real browser. Trigger on: "e2e test", "screenshot the UI", "click through the app", "responsive layout check", "accessibility audit". Also invoke when qe-agent needs browser-level integration testing.
-
ivy00johns Skill Yagni GateGate every build behind a persistent YAGNI ladder — the laziest senior dev in the room, adapted from DietrichGebert/ponytail (MIT). Before any code: does this need to exist, can something already present do it, can it be one line — only then the minimum that works. Never lazy about trust-boundary validation, data-loss error handling, security, accessibility, or understanding the problem first; every non-trivial change leaves one runnable check. Persists until 'stop yagni-gate' or 'normal mode'. Use when code keeps getting over-built, a tiny ask balloons into scaffolding, or you want a standing minimal-code gate on a session. Trigger on: 'yagni-gate', '/yagni-gate', 'yagni mode', 'YAGNI', 'stop over-building', 'over-engineered', 'keep it minimal', 'minimum code', 'lazy mode', 'don't gold-plate', 'ponytail', 'less code'.
-
ivy00johns Bundle Class Extraction GuardSource-level gate that catches utility-class soup — the same long run of utility classes (e.g. `flex items-center gap-1.5 text-fg-muted hover:text-accent`) copy-pasted inline across many files instead of extracted into a named class or component. Use whenever frontend work touches className/class markup: before committing or declaring a UI task done, when auditing for utility soup, when a Tailwind combo is repeated everywhere, or as an orchestrator/agent wave-gate. Trigger on: "utility soup", "repeated tailwind classes", "extract into named classes", "className duplication", "class string copy-pasted", "DRY up the styles", "class-extraction". Framework-agnostic (React/JSX, Vue, Svelte, Astro, HTML; clsx/cn/cva). Sibling to design-token-guard: it checks WHICH values styling uses (tokens vs hex), this checks HOW it's organized (extracted vs repeated) — invisible to render review since repeated utilities render identically.
-
optimuslabs-io Skill Changelog WriterMaintains CHANGELOG.md from commit history.
-
ekinoxis-evm Skill Ekx PrivyWallet and auth layer for Ekinoxis dApps using Privy — embedded wallets, email/social/wallet login, server-side token verification, and wagmi integration. Use when adding login to a dApp, creating embedded wallets for users, verifying a Privy access token in an API route or server action, gating a page or contract call behind authentication, or debugging "user is not authenticated"/wallet-not-found issues. Covers @privy-io/react-auth, @privy-io/server-auth and @privy-io/wagmi.
-
ekinoxis-evm Skill Ekx ResendTransactional email with Resend — sending from a route handler or cron, React Email templates, domain verification and DNS, dry-run mode for local development, and delivery webhooks. Use when sending an alert, receipt, magic link or digest email, when email is not arriving, or when setting up a new sending domain.
-
ekinoxis-evm Skill Ekx SupabaseThe default Ekinoxis database — Postgres, auth, storage and realtime via Supabase. Use when creating or changing tables, writing RLS policies, wiring the browser/server client pair with @supabase/ssr in Next.js App Router, running migrations, debugging "permission denied"/empty-result/RLS surprises, generating TypeScript types, or choosing between anon and service-role keys. Covers @supabase/supabase-js, @supabase/ssr and the Supabase MCP server.
-
ekinoxis-evm Skill Ekx ThegraphIndexing and querying onchain data with The Graph — subgraph development and deployment, GraphQL queries from a frontend, the Token API, and when a subgraph beats direct RPC log queries. Use when you need historical onchain data, an event feed, aggregations across many blocks, or when eth_getLogs is hitting range limits.
-
ekinoxis-evm Skill Ekx Nextjs AppThe Ekinoxis Next.js App Router conventions used across 18 projects — folder layout, server vs client components, server actions, route handlers, data fetching and caching, Tailwind v4 setup, and the version differences between Next 14, 15 and 16 in our portfolio. Use when starting a new app, adding a route or API endpoint, deciding where code should run, or debugging hydration, caching or "use client" boundary errors.
-
ekinoxis-evm Skill Ekx Coinbase CdpCoinbase Developer Platform and OnchainKit — CDP server wallets for agent-controlled keys, AgentKit with LangChain for onchain AI agents, OnchainKit React components (Wallet, Swap, Checkout, Identity), and Base App / Farcaster miniapp integration. Use when an agent rather than a person must hold a key, or when building with OnchainKit components.
-
agentik-os Bundle UI UX Pro Max 2UI/UX design intelligence for web and mobile — produces design-system decisions and production UI code in ONE coherent designer voice. Use when the task changes how a feature looks, feels, moves, or is interacted with. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart types across 10 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind, shadcn/ui, and HTML/CSS). Actions (EN): plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX. Actions (FR): conçois, construis l'UI, crée une interface, design, refonte composant, améliore l'UX, corrige le design, palette de couleurs, choix de police, accessibilité, mode sombre, design système. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid
-
agentik-os Skill Redesign Existing ProjectsUpgrades an existing website or app to premium quality — audits the current design, finds generic "AI-looking" patterns, and applies high-end standards without breaking functionality. Works with any CSS framework or vanilla CSS. Use when the user says "redesign this", "refonte", "améliore le design", "make this look premium / less generic / less AI", "upgrade the UI of my existing project", "de-AI-ify the design", "polish the design", "rends ça moins générique". Not for net-new design from scratch (use a fresh design skill) and not a pure forensic UI score (use /uiuxaudit).
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 pbi-report-design, claude-reserved, pbi-plan. 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.