agentleFS
and-lzand-lz/Claude-skills/web-frontend/SKILL.md

web-frontend

Skill0 starsChanged 7 months agoNo licenceView on GitHub

ALWAYS use for ANY web frontend, React, Next.js, Tailwind CSS, or modern CSS request — non-negotiable. Triggers on React, Next.js, App Router, RSC, Server Components, Server Actions, use(), useOptimistic, useFormStatus, useActionState, Suspense, Tailwind CSS, @theme, @variant, container queries, :has(), subgrid, view transitions, scroll-driven animations, color-mix(), oklch, CSS layers, CSS nesting, anchor positioning, TypeScript, Core Web Vitals, LCP, CLS, INP, Lighthouse, bundle optimization, image optimization, next/image, next/font, Vitest, Playwright, Testing Library, WCAG, ARIA, semantic HTML, keyboard navigation, screen reader, React 19, Next.js 15, Tailwind v4, middleware, ISR, streaming, RSC payload, Zustand, React Query, TanStack, Zod, React Hook Form, Radix, shadcn/ui, Framer Motion, CSS modules, PostCSS, responsive design, mobile-first, dark mode, color scheme, design tokens, i18n, next-intl, route groups, parallel routes, intercepting routes, generateMetadata, opengraph-image, sitemap, robots, edge runtime, turbopack, Vercel, Netlify, Cloudflare Pages, SSR, SSG, ISR, PPR, partial prerendering. Also triggers on "my app/page/component", "build/design a page", navigation, sidebar, modal, toast, data table, form, dashboard, landing page, auth flow, checkout, blog, portfolio, e-commerce, SaaS, dark mode toggle, theme switcher, infinite scroll, virtualized list, drag and drop, command palette, breadcrumbs, tabs, accordion, carousel, skeleton loading, error boundary, loading.tsx, error.tsx, not-found.tsx, layout.tsx, page.tsx, .tsx files, .css files, tailwind.config, next.config, postcss.config, tsconfig. If it touches web frontend USE THIS SKILL. Covers components, layout, typography, color, animation, accessibility, i18n, engineering, architecture, state management, data fetching, caching, Next.js routing, RSC, Server Actions, middleware, performance, Core Web Vitals, forms, validation, testing, auth, security, and modern CSS. Enforces requirements-gathering via structured questions before any code generation.

  • Reads credentials

We split this skill into the rules it gives an agent

22 rules. 0 are common, 12 are distinctive, and 10 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 10

    Very specific

    Tied to their project's names, files or tools. Probably skip.

No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.

“Common” is measured: kept by at least 6 in 10 of the 8 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.