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.
-
velt-js Bundle Velt View Analytics Best PracticesBest practices for Velt View Analytics — the 'who viewed this document today' indicator with a count badge, recent-viewers dialog, and date- or user-aggregated subscriptions. Use whenever the user is adding the VeltViewAnalytics component, scoping it to a sub-document via type='location' + location-id, reading unique-view counts via the React hooks (useUniqueViewsByUser / useUniqueViewsByDate) or the non-React observable form (client.getViewsElement().getUniqueViewsByUser/ByDate().subscribe), building a custom trigger or viewer-list overlay via the velt-view-analytics-wireframe / velt-view-analytics-dialog-wireframe / velt-view-analytics-bottom-sheet-wireframe tags, or binding componentConfig.* template variables (todayViewsCount, totalUniqueViewsCount, treadsVisible, userViews, bottomSheetMode). Trigger on any task involving Velt View Analytics, document view counts, recent-viewers lists, viewers-by-date trends, view aggregation, or VeltViewAnalytics customization — even when the user does not explicitly say
-
velt-js Bundle Velt Live State Sync Best PracticesVelt Live State Sync implementation patterns and best practices for React, Next.js, and web applications. Use when adding real-time shared state, syncing data across clients, Redux store synchronization, or live variables. Triggers on any task involving Velt live state, useLiveState, useSetLiveStateData, useLiveStateData, useLiveStateSyncUtils, createLiveStateMiddleware, getLiveStateSyncElement, live state broadcast API, real-time collaborative state, or building shared-state features — even if the user doesn't explicitly say 'live state sync'.
-
velt-js Bundle Velt Chat Sdk Adapter Best PracticesVelt Chat SDK Adapter implementation patterns and best practices for building bots that integrate with Velt comment threads. Use when building a bot (greeting bot, AI bot, support bot) that responds to @-mentions in Velt comments, handling webhook events from Velt (comment.add, comment.reaction_add), configuring the Chat SDK with createVeltAdapter, setting up webhook routes in Next.js or other Node.js frameworks, handling reactions on Velt comments, resolving user identities for bot responses, or deploying a Velt-connected bot to Vercel or other platforms. Triggers on any task involving @veltdev/chat-sdk-adapter, Chat SDK adapters for Velt, Velt bot integration, Velt webhook handling for comments, onNewMention, onReaction, thread.post(), or building an automated responder for Velt comment threads — even if the user doesn't explicitly say 'chat SDK adapter'.
-
velt-js Bundle Velt Self Hosting Data Best PracticesVelt self-hosting data implementation patterns and best practices for React, Next.js, and web applications. Use when storing sensitive user-generated content (comments, attachments, reactions, recordings, user PII) on your own infrastructure instead of Velt servers, implementing data providers (endpoint-based or function-based), building backend API routes, or debugging data provider events.
-
velt-js Bundle Velt Single Editor Mode Best PracticesVelt Single Editor Mode implementation patterns and best practices for React, Next.js, and web applications. Use when implementing exclusive editing access, editor/viewer role management, access request handoff flows, element-level sync control, timeout-based editor transfer, or multi-tab editing restrictions.
-
vesely Bundle Ssh GuiDrive the graphical desktop of a remote macOS machine over plain ssh, with no VNC, no screen sharing and no agent installed on the far side. Gives you clicks, drags, keystrokes, text entry, menu navigation, window geometry and screenshots through cliclick, screencapture and the accessibility API, with a coordinate model that actually lines up on Retina displays and a preflight that tells you which of the three macOS permissions is missing before you waste a click. Use this whenever the task is to operate the GUI of a Mac you reach by ssh: a headless Mac mini or Mac Studio, a build or CI Mac, a second machine on the desk, a Mac in a rack or a colo. Trigger on "control the GUI over ssh", "click something on my mini", "automate the remote Mac desktop", "screenshot the other Mac", "drive an app on the headless Mac", "cliclick over ssh", "no VNC available". Not for controlling a virtual machine's guest OS (drive the guest from inside instead) and not for web pages (use a browser automation tool).
-
qualcomm Bundle App BuilderApp Builder — generate complete, runnable fullstack WebUI applications (FastAPI backend + pure HTML/CSS/JS frontend) around on-device AI Model Packs (OCR, TTS, ASR, Super-Resolution, etc.). Use this skill when the user wants to build, generate, modify, or debug a standalone WebUI app around any installed Model Pack.
Audited -
radustefandumitru Bundle Fluid AnimationsImplement natural, Apple-quality fluid UI animation and gesture behavior. Use when coding or reviewing spring motion, Framer Motion/React animations, SwiftUI/UIKit animation, CSS transitions, drag/swipe/scroll interactions, rubberbanding, snap points, momentum projection, interruptible animations, press feedback, spatially consistent enter/exit transitions, or any interface motion that should feel tactile, responsive, and physically believable.
-
radustefandumitru Bundle Convert To MarkdownUse when the user references a local PDF, Office document, spreadsheet, presentation, HTML file, CSV/data file, or ovd-workflow knowledge-vault document and the agent should convert it to clean Markdown before reading to reduce tokens and preserve structure. Uses Microsoft's MarkItDown when available; falls back gracefully when Python/MarkItDown is unavailable.
-
rexedge Skill Paystack Payment PagesPaystack Payment Pages API — create and manage hosted payment pages for collecting payments without writing frontend code. Supports fixed/flexible amounts, custom slugs, subscription pages, product pages, split payments, redirects, custom fields, and phone collection. Use this skill whenever building checkout pages, donation pages, event ticket sales, product catalogs with payments, or any hosted payment link. Also use when you see references to page slug, /page endpoint, paystack.com/pay/ URLs, or need to add products to a payment page.
-
saschb2b Bundle Ask UXForce UX questioning before any UI work, refactor, or redesign. Use when the user asks to design, redesign, restyle, polish, "fix", or "make nicer" a screen, component, page, or flow. Also use when the user describes a problem in UI terms ("the button is hard to find", "this form is confusing", "this page is ugly") and is about to reach for a visual fix, since most UI-shaped complaints have UX-shaped causes.
-
saschb2b Bundle Codegen APISet up typesafe API code generation in 2026, preferring framework-agnostic options factories over generated hooks. Walks the decision matrix for REST (OpenAPI via hey-api) and GraphQL (graphql-codegen client preset, gql.tada), wires the minimal config for the chosen stack, and uses fragment masking for component composition. Use when starting an API integration, wiring an OpenAPI spec into a frontend, setting up GraphQL types, asked about useQuery, queryOptions, TypedDocumentNode, or fragment masking, or when seeing legacy patterns like generated useGetX hooks, per-query prop types, or @graphql-codegen/typescript-react-apollo. Counterweight to LLM training corpora that mostly reflect the pre-2024 hooks pattern, biasing default output toward generated hooks.
-
saschb2b Bundle Test StinkyDetect test-suite quality smells in any language or framework, explain the cost of each, and propose a fix with a source link. A counterweight to agents that blindly chase coverage and ship huge, slow, flaky suites. Covers test intent and naming, assertions (assertion-free, weak, tautological, snapshot-everything), fixtures and duplication (DAMP over DRY, mystery guests, logic in tests), test doubles (over-mocking, mock drift), determinism (time, randomness, order, shared state, hermeticity), async waiting (sleeps vs condition waits), speed and cost (inverted pyramid, redundant layers), coverage theater, and lifecycle hygiene (skipped-test rot, retries as policy, green-by-rerun), plus a suite-level shape pass with a slimming plan and a mechanical gate stack. Use when reviewing or writing tests, auditing, slimming, or speeding up a test suite, hunting flaky or slow tests, or asked to sniff, smell-check, or clean up specs or a test folder. Defers production-code smells to react-stinky and tauri-stinky.
-
saschb2b Bundle React StinkyDetect React and TypeScript maintainability smells across the whole component, hook, and module, explain the cost of each, and propose a fix with a source link. Covers prop and API design (naming, booleans, callbacks, variants, controlled state, generics, refs, styling, JSDoc), state and data flow (redundant state, stale closures, context and ref misuse), effects and lifecycle, component structure and hooks, rendering correctness (keys, mutation, impure renders, hydration, the leaked 0 from &&), accessibility and focus management, async handlers, error boundaries, unsafe HTML, TypeScript discipline (any, casts, untyped catch, exhaustiveness), and a cross-file duplication pass. Defers memoization and re-render performance to react-compiler and color literals to theme-colors. Use when reviewing or writing React components or hooks, auditing for maintainability, or asked to sniff, smell-check, lint, or clean up a codebase, folder, file, or pasted snippet. Respects native HTML attributes and library conventions.
-
saschb2b Bundle Tauri StinkyDetect Rust and Tauri maintainability smells across the backend crate, the IPC boundary, and the app shell, explain the cost of each, and propose a fix with a source link. Covers Rust discipline (error handling and panics, ownership and clones, type design, module structure, async correctness, overgeneration and dead code, unsafe and lint hygiene, testing) and the Tauri layer (command design, managed state, events vs channels, capabilities and security, IPC contract and type codegen, config and build footprint), plus a cross-boundary contract audit and a mechanical gate stack (fmt, clippy, test, audit, deny, machete). Use when reviewing or writing Rust code or a Tauri app, auditing src-tauri, setting up quality gates or CI lints for Rust, or asked to sniff, smell-check, lint, or clean up a Rust or Tauri codebase, crate, command, or pasted snippet. Defers React component and hook smells to react-stinky and color literals to theme-colors.
-
saschb2b Bundle Theme ColorsAudit and refactor UI code so every color value comes from the theme. Replace hex codes, rgba(), hsl(), oklch() literals, and named CSS colors with theme palette tokens (primary, secondary, error, warning, info, success, background, text) and the alpha() helper for transparency. Use when writing or reviewing any UI component, when starting a new MUI or design-system theme, when a designer hands off colors as hex annotations, when seeing color literals scattered across component files, or when an LLM produced styling with hardcoded hex values. Counterweight to LLM training corpora dominated by tutorial code that inlines hex codes and rgba literals instead of role-based theme tokens.
-
saschb2b Bundle Game DesignAnalyze, design, critique, balance, and rework video game mechanics, systems, and interface, grounded in a cross-game pattern catalog and design frameworks (MDA, core loops, flow, game feel, economy). The first stop for any design-touching change or discussion, including mid-implementation in an engine like Godot. Use when designing, balancing, brainstorming, or reworking a mechanic, progression, economy, loadout, inventory, loot, shop, enemy or difficulty scaling, reward, menu, or UI system; when tuning drop rates, prices, curves, or scaling; when asking whether something is fun, too grindy, or has a dominant strategy; when designing menus, HUD, transitions, onboarding, dialogue, guidance, input prompts, or accessibility; when capturing, pitching, or iterating a game idea, concept, vision, design pillars, or GDD, persisted as a living concept bundle; or when self-authoring game systems while building one. Rides alongside godot, which writes the engine code, while this decides what that code should do.
-
saschb2b Bundle React CompilerWrite and review React code as if the React Compiler is enabled. Skip manual useMemo, useCallback, and React.memo by default, and audit existing code for stale manual memoization. Use when writing or refactoring any React component in a React 19+ codebase, when reviewing a React PR, when setting up the eslint-plugin-react-hooks configuration, or when seeing memoization patterns in code an LLM produced. Counterweight to pre-compiler React in LLM training corpora, which biases default output toward manual memoization unless prompted otherwise.
-
saschb2b Bundle Visual ConsistencyDetect and fix visual and layout consistency defects in rendered UI, the systematic raggedness AI generators emit and seniors notice at a glance. Covers uneven card heights in a grid, sibling cards whose internal sections (title, body, footer) do not line up, trailing icons such as open-in-new-tab at ragged X positions, and arbitrary off-scale spacing, plus alignment, repeated elements (buttons, radius, shadow, icons), type scale, tables and numeric alignment, borders, overflow, layout shift, touch targets, and focus rings. Each smell carries an objective detection signal, a concrete CSS fix (subgrid, equal-height grids, spacing tokens, tabular-nums), an exception guard, a severity, and whether an agent may fix it freely or must surface a design call first. Use when reviewing or building any UI, when a card grid or list looks busy or ragged, when spacing feels arbitrary, or when asked to tidy or align a layout so it scans cleanly. Defers color to theme-colors and component code smells to react-stinky.
-
saschb2b Bundle Javascript EcosystemDefault to the latest stable major versions of JavaScript and TypeScript frameworks and their current paradigms, instead of the older versions and patterns that dominate LLM training data. A version-and-paradigm changelog index that routes to per-tool notes. Use when writing, reviewing, scaffolding, or upgrading any JS or TS project, when choosing dependency versions, when an agent emits an outdated pattern, or when working with React, Angular, Vue, Svelte, Solid, Next.js, Nuxt, React Router, Remix, SvelteKit, Astro, TanStack Start, Material UI, Tailwind, shadcn, Mantine, Chakra, TanStack Query, Redux, Zustand, Jotai, TypeScript, Vite, Node, ESLint, pnpm, Bun, or Biome. Check the project's installed version first; this snapshot ages.
-
shuakami Bundle PaperchartGenerate clean, calm chart PNGs in the spirit of Anthropic and OpenAI blog posts. Trigger when the user asks to produce a chart, model comparison table, diagram or infographic for a technical blog post, release notes, a research write-up or a slide deck and wants a single restrained palette, minimal chrome, heavy inline labelling, and PNG output rendered from React at native resolution. The primary surface is a shell CLI named `paperchart` that takes a JSON file and writes a PNG. Thirty-two primitives covering charts (line, area, scatter, heatmap, calendar heatmap, histogram, cdf, box-plot, ranking, dumbbell, slope, waterfall, small-multiples, timeline, funnel, sankey, treemap, radar, table, stacked-bar, grouped-bar, critical-path, pack-layout, latency, bytes, recall) and Mermaid-style structural diagrams (flowchart, architecture, sequence, state-diagram, er-diagram, delivery). Six themes, layout + style overrides per chart.
Audited -
dcouple Skill Frontend VerifierDrive browser or mobile app QA for /do, proving UI acceptance criteria and executing the PR's Manual tests checklist.
-
easysoft Bundle Zuix Component在独立 ZUI 扩展项目中设计、实现或修复组件;区分扩展与宿主边界,实施前确认计划或复用已有批准。
-
easysoft Bundle Zui Component在 ZUI 主仓库的 lib/* 中设计、实现或修复组件;实施前按共享工作流确认计划或复用已有批准。
-
educlopez Skill Ps WatchSets up BrowserSync live-reload watcher for PrestaShop Panda child theme development in Lando. Auto-detects child theme name and Lando proxy URL. Watches child theme CSS/JS/TPL files and reloads the browser automatically on save. Use when working on PS frontend/maquetación in Lando and the user wants auto-reload, live reload, watcher, or is tired of reloading the browser manually after CSS changes.
-
educlopez Skill Ps CSS BuildSets up a modern CSS build pipeline for a PrestaShop child theme: source partials in _dev/css/, lightningcss bundle+minify to a single generated assets/css/custom.css, pnpm 11 with supply-chain hardening, pre-commit hook with zero-dependency Node fallback, and agent/team documentation. Replaces runtime @import chains and manual ?v= cache-bust versioning. Use when scaffolding CSS architecture for a new PS child theme, when a theme has multiple @import'ed CSS partials loaded at runtime, when the user mentions manual CSS version bumps, CSS cache busting problems, "el CSS no se actualiza", or wants the Milagros-style CSS build on another project.
-
educlopez Bundle Task ContextTurns an Intervals task into ready-to-work context. Fetches the task and its notes, decodes HTML entities, builds a compact brief, classifies the task type, creates the git branch, and routes to the right skill/agent. Handles time logging on finish with 15-minute banding. Intervals is the single source of truth; Google Workspace (via the `gws` CLI) is an opt-in enricher only — never searched automatically. Use this skill for the /task command, or whenever the user references an Intervals task by its numeric ID and wants to start or close work on it.
Audited -
educlopez Bundle Ps New ProjectOrchestrate the day-1 setup that remains after cloning a PrestaShop repo and running lando-setup: scaffold the child theme (panda or elementflow track), wire the CSS build, and write CLAUDE.md. Composes existing skills (ps-css-build, ps-project-doc, lando-setup). Does NOT create the GitLab repo, the server, or install PrestaShop core. Use when starting a new client project locally and you need the standard scaffold fast.
Audited -
educlopez Bundle Ps Project DocGenerate a standardized, private CLAUDE.md for a PrestaShop repo by introspecting it (PS version, theme + parent, theme stack Panda/ElementFlow, Lando URL/port, CSS build, git remote, modules). Auto-fills most fields, asks the user only for gotchas/contacts/module purposes, and writes a lean ~70-90 line file. The CLAUDE.md is PRIVATE — always gitignored, never committed. Reusable non-interactively by the new-project bootstrap. Use for the /project-doc command, when a PrestaShop repo has no CLAUDE.md or an inconsistent one, or when bootstrapping a new project's docs.
Audited -
educlopez Skill Ps Security AuditSets up weekly automated security scanning for PrestaShop 8 projects hosted on GitLab.com. Checks: installed modules vs Friends of Presta advisory database, PrestaShop core version, and PHP/Composer dependencies via Trivy. Sends weekly HTML email report every Monday. Use ONLY for PrestaShop projects on GitLab.com. Triggers when user asks for security scanning, vulnerability alerts, module CVE check, or Friends of Presta integration on a PrestaShop project.
-
educlopez Skill Gitlab Security SetupSets up a full security stack on your company's projects hosted on GitLab.com (non-PrestaShop: Laravel, Astro, TanStack, etc.). Use ONLY when the project is a GitLab.com Free tier project. Triggers when the user asks to add dependency scanning, vulnerability alerts, security setup, Trivy, pnpm supply chain protection, or wants email reports of vulnerabilities. Do NOT use for GitHub-hosted projects, personal projects, or PrestaShop projects — use ps-security-audit skill instead for any PrestaShop project.
-
educlopez Bundle Gitlab CI Quality GatesWires Cinetic's reusable GitLab CI/CD Components (gitlab.com/educlopezcinetic/ci-templates — lint, typecheck, test, semantic MR titles, agent guardrails, secret scanning, dependency audits) into a project's .gitlab-ci.yml, adds the stack's static-analysis job (PHPStan for PrestaShop, Larastan for Laravel — not yet a ci-templates component, wired repo-local), and configures branch protection + merge checks to match how the project is actually worked. Use when the user asks to "set up CI quality gates", "montar CI en este proyecto", "añadir ci-templates", wants PHPStan/Larastan added, or wants MR-based branch protection on a GitLab project. Covers PrestaShop, Laravel, Astro, and Next.js — add a new reference file the same shape when another stack needs this, don't build ahead of need. Distinct from gitlab-security-setup (scheduled Trivy/pnpm supply-chain email report) and ps-security-audit — this is about MR-time quality/security GATES, not scheduled reports. Do NOT use for GitHub-hosted projects.
-
emaballarin Bundle Web Artifacts BuilderSuite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.
Audited -
first-fluke Bundle QA AgentQuality assurance specialist for security, performance, accessibility, and comprehensive testing
-
first-fluke Bundle Mobile AgentMobile specialist for Tauri Mobile (iOS/Android), Rust/Swift/Kotlin integrations
-
first-fluke Bundle Frontend AgentFrontend specialist for Next.js (Tauri), React, TypeScript, and shadcn/ui
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 velt-live-state-sync-best-practices, paperchart, ps-new-project. 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.