web-dev-frontend

Frontend third of the web-development toolkit — design systems, components, animation, accessibility, UX review, SEO, performance, content, and frontend testing. Use when the user asks to build, design, restyle, animate, or audit a website, landing page, dashboard, component, or any frontend interface; to fix contrast or a11y issues; to improve Core Web Vitals; or to pick a frontend tool. Contains the full frontend skill catalog plus the frontend-only MCP toolchain (chrome-devtools, lighthouse, context7, playwright, lucide, next-devtools, excalidraw, images, firecrawl, perplexity).

O que é web-dev-frontend?

web-dev-frontend is a Claude Code agent skill that frontend third of the web-development toolkit — design systems, components, animation, accessibility, UX review, SEO, performance, content, and frontend testing. Use when the user asks to build, design, restyle, animate, or audit a website, landing page, dashboard, component, or any frontend interface; to fix contrast or a11y issues; to improve Core Web Vitals; or to pick a frontend tool. Contains the full frontend skill catalog plus the frontend-only MCP toolchain (chrome-devtools, lighthouse, context7, playwright, lucide, next-devtools, excalidraw, images, firecrawl, perplexity).

Funciona com✓Claude Code~Codex CLI✓Cursor✓OpenCode
npx skills add https://github.com/yashoramabhat-hash/web-dev-skills/tree/HEAD/skills/web-dev-frontend

Installed? Explore more Programação e Desenvolvimento skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →

Perguntar na sua IA favorita

Abre um novo chat com esta habilidade de agente já pré-carregada.

Documentação

web-dev-frontend — frontend design, UI and experience skills

Frontend third of the web-development toolkit. Siblings: web-dev-backend (APIs, data, auth, infra) and web-dev-security (web & app security).


Step 1 — Pick the area

If the request is about…Section
Visual design, layout, components, styling, brandUI — Design systems, tokens & visual direction
Animation, scroll effects, transitions, videoUI — Animation & motion
Contrast, screen readers, keyboard, WCAG, UX reviewUI — Accessibility & UX review
SEO, Core Web Vitals, Lighthouse, deploy, monitoringUI — SEO, performance & delivery
Copy, docs, blog, decks, spreadsheetsUI — Content, copy & docs
Tests, reviews, debugging, verification for the UI layerQuality — Frontend testing & review
MCPs, planning, git, docs, researchTooling — Frontend workflow

Rule: load 1–3 skills, never the whole catalog. The hub skill first, then its sub-skills.


Step 2 — Pick the MCP

TaskMCPNotes
Inspect live page — DOM, computed CSS, console, networkchrome-devtools32 tools. The ground truth for "what the browser actually sees". Also get_css_styles, evaluate_script, lighthouse_audit. Needs pageId — call list_pages first.
Accessibility + performance + SEO auditlighthouse11 tools: get_accessibility_score, get_performance_score, get_seo_analysis, get_core_web_vitals, compare_mobile_desktop.
Click through flows, screenshots, authplaywright25 tools. Multi-breakpoint capture, console logs.
Up-to-date library docscontext7resolve-library-id then query-docs. React/Tailwind/shadcn/Next APIs.
Icon searchlucide7 tools. Real icon sets + React usage examples.
Next.js specificsnext-devtoolsnextjs_index finds running dev servers; nextjs_docs.
Diagrams / wireframesexcalidraw26 tools. Canvas server on http://127.0.0.1:3100.
Stock photosimagesNeeds PEXELS / UNSPLASH / PIXABAY key in opencode.jsonc.
shadcn/ui componentsshadcn-registry7 tools. Search shadcn + custom registries, get the exact npx shadcn add command, audit checklist.
Generate images / video / audiofal9 tools, 600+ models. Needs FAL_KEY. For hero visuals, mockup assets, voiceover.
Find design referencesexa3 tools. Neural web search + clean markdown fetch. Needs EXA_API_KEY.
Figma file → codefigma-officialOfficial remote MCP (https://mcp.figma.com/mcp), OAuth on first use. Also figma-developer-mcp (local, needs a key).
Scrape / read target pagesfirecrawl28 tools. JS-rendered pages, site maps.
Research current APIs / writeupsperplexity4 tools.

If an MCP call fails, fall back to the CLI equivalent, then say so in the output.


Step 3 — The loop

  1. Scope — target, stack, what "done" means (visual fidelity, a11y score, Lighthouse score).
  2. Inspect first — capture the current DOM, computed CSS and a screenshot via chrome-devtools or playwright before changing anything. Never redesign blind.
  3. Design — establish tokens (type scale, spacing, colour) before writing components.
  4. Build — real components, real states (hover, focus, empty, error, loading). No placeholder grey boxes.
  5. Verify — lighthouse for a11y + performance, chrome-devtools for console/network errors, playwright for before/after screenshots at 3 breakpoints.
  6. Report — what changed, before/after evidence, scores.

Non-negotiables

  • Inspect before you redesign. Capture DOM, computed styles and a screenshot first.
  • No visual claim without a before/after screenshot.
  • Contrast must pass WCAG AA (4.5:1 body, 3:1 large text) — verify with lighthouse, never eyeball.
  • Real assets over placeholders. No emoji as UI icons.
  • One accent colour doing the work. Use the project's component library instead of hand-rolling.
  • Zero console errors before "done".
  • Respect prefers-reduced-motion for anything animated.
  • Match the existing design system before inventing a new one.

Step 4 — Full catalog

UI — Design systems, tokens & visual direction (31)

  • design-system — アクセシビリティ、レスポンシブネス、テーマ設定、コンポーネント群、トークンを備えた本番環境対応デザインシステムの構築。Figma、Storybook、コンポーネントライブラリ統合。
  • design — (no description)
  • theme-factory — Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pag...
  • brand — (no description)
  • brand-guidelines — Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having...
  • brand-discovery — Run a structured, resumable multi-session brand identity interview across 8 modules (purpose, positioning, au...
  • brand-voice — Build a source-derived writing style profile from real posts, essays, launch notes, docs, or site copy, then...
  • unslop — Turns vibecoded, AI-looking UI into a designed interface with its own character. Finds a direction from the p...
  • impeccable — Use when the user wants to design, redesign, shape, critique, audit, polish, simplify, harden, animate, or ot...
  • hallmark — Design skill for websites and new pages that look designed, not generated. Use when the user asks to build or...
  • shadcn — Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, inc...
  • daisyui — Official daisyUI component-library skill for Tailwind CSS. When you write HTML or JSX code, you must use it...
  • magic-ui — Use this skill when users want to add, customize, or troubleshoot Magic UI components in React/Next.js projec...
  • migrate-radix-to-base — Migrates React projects and components from Radix UI to Base UI. Use when asked to migrate from radix, move t...
  • composition-patterns — (no description)
  • react-bits — Animated React components library — 215+ free motion components and backgrounds (text animations, cursor/hove...
  • react-view-transitions — (no description)
  • canvas-design — Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill whe...
  • banner-design — (no description)
  • ui-styling — (no description)
  • ui-ux-pro-max — (no description)
  • smart-filter — (no description)
  • slides — (no description)
  • liquid-glass-design — iOS 26 Liquid Glass design system — dynamic glass material with blur, reflection, and interactive morphing fo...
  • vercel-react-best-practices — React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when...
  • react-native-skills — (no description)
  • swiftui-patterns — SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance o...
  • taste — Creative-direction layer for music videos and short-form edits in the angelcore / cloud-trance / hyperpop fam...
  • taste-application — Generate new video against a distilled style pack and cut it into a finished piece - plan takes from the refe...
  • taste-distillation — Measure a set of reference videos into a reusable style pack - colour grade as a 3D LUT, cut rhythm as a shot...
  • taste-skill — (no description)

UI — Animation & motion (14)

  • gsap-core — Official GSAP skill for the core API — gsap.to(), from(), fromTo(), easing, duration, stagger, defaults, gsap...
  • gsap-frameworks — Official GSAP skill for Vue, Svelte, and other non-React frameworks — lifecycle, scoping selectors, cleanup o...
  • gsap-performance — Official GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use w...
  • gsap-plugins — Official GSAP skill for GSAP plugins — registration, ScrollToPlugin, ScrollSmoother, Flip, Draggable, Inertia...
  • gsap-react — Official GSAP skill for React — useGSAP hook, refs, gsap.context(), cleanup. Use when the user wants animatio...
  • gsap-scrolltrigger — Official GSAP skill for ScrollTrigger — scroll-linked animations, pinning, scrub, triggers. Use when building...
  • gsap-timeline — Official GSAP skill for timelines — gsap.timeline(), position parameter, nesting, playback. Use when sequenci...
  • gsap-utils — Official GSAP skill for gsap.utils — clamp, mapRange, normalize, interpolate, random, snap, toArray, wrap, pi...
  • remotion-video-creation — Best practices for Remotion - Video creation in React. 29 domain-specific rules covering 3D, animations, audi...
  • video-editing — AI-assisted video editing workflows for cutting, structuring, and augmenting real footage. Covers the full pi...
  • tasteforge-video — Use for file-driven multimodal image, video, and 3D-asset discovery; taste interviews; distill or apply workf...
  • lemo-opuscar — Direct and produce a short film made entirely in code, in one of the styles of the Lemo-Opuscar library (e.g...
  • manim-video — Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, th...
  • slack-gif-creator — Knowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tool...

UI — Accessibility & UX review (7)

  • accessibility — Audit and improve web accessibility following WCAG 2.2 guidelines. Use when asked to "improve accessibility"...
  • web-design-guidelines — Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibilit...
  • browser-qa — Run automated post-deploy UI verification with a browser automation MCP (claude-in-chrome, Playwright, or Pup...
  • ui-demo — Record polished UI demo videos using Playwright. Use when the user asks to create a demo, walkthrough, screen...
  • webapp-testing — Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend...
  • playwright-best-practices — Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, co...
  • audit-website — Audit a website with the squirrelscan CLI and fix the findings in code. Runs SEO, performance, security, tech...

UI — SEO, performance & delivery (11)

  • seo — Audit, plan, and implement SEO improvements across technical SEO, on-page optimization, structured data, Core...
  • vercel-optimize — Use for Vercel cost and performance optimization on deployed projects, especially Next.js, SvelteKit, Nuxt, a...
  • canary-watch — Use this skill to monitor and verify a deployed URL after releases — checks HTTP endpoints, SSE streams, stat...
  • production-audit — Local-evidence production readiness audit for shipped apps, pre-launch reviews, post-merge checks, and "what...
  • benchmark — Measure performance baselines and detect regressions across browser Core Web Vitals (LCP, INP, CLS, page weig...
  • benchmark-optimization-loop — Convert 'make it faster' requests into a bounded measured optimization loop — baseline first, generate one-hy...
  • benchmark-methodology — Score a scoped competitor set into comparable profile cards: nine weighted dimensions (positioning, voice, vi...
  • web-artifacts-builder — Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web tec...
  • latency-critical-systems — Optimize and verify latency-sensitive systems — realtime dashboards, market data feeds, streaming agents, exe...
  • data-throughput-accelerator — Diagnose and accelerate large data movement — ingestion, backfill, export, ETL, warehouse loading, manifest c...
  • deploy-to-vercel — Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app...

UI — Content, copy & docs (13)

  • article-writing — Write articles, guides, blog posts, tutorials, newsletter issues, and other long-form content in a distinctiv...
  • internal-comms — A set of resources to help me write all kinds of internal communications, using the formats that my company l...
  • doc-coauthoring — Guide users through a structured workflow for co-authoring documentation. Use when user wants to write docume...
  • content-engine — Create platform-native content systems for X, LinkedIn, TikTok, YouTube, newsletters, and repurposed multi-pl...
  • crosspost — Multi-platform content distribution across X, LinkedIn, Threads, and Bluesky. Adapts content per platform usi...
  • writing-guidelines — Review docs/prose for Writing Guidelines compliance. Use when asked to "review my docs", "check writing style...
  • docx — Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or W...
  • pdf — Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting tex...
  • xlsx — Use this skill any time a spreadsheet file is the primary input or output. This means any task where the user...
  • pptx — Use this skill any time a .pptx or .potx file is involved in any way — as input, output, or both. This includ...
  • marketing-campaign — End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle d...
  • investor-materials — Create and update pitch decks, one-pagers, investor memos, accelerator applications, financial models, and fu...
  • content-hash-cache-pattern — Cache expensive file processing results using SHA-256 content hashes — path-independent, auto-invalidating, w...

Quality — Frontend testing & review (16)

  • tdd — Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-gree...
  • tdd-workflow — Test-driven development workflow: write a failing test first, watch it fail, implement the smallest change to...
  • e2e-testing — Playwright E2E testing patterns, Page Object Model, configuration, CI/CD integration, artifact management, an...
  • property-based-testing — Provides guidance for property-based testing across multiple languages and smart contracts. Use when writing...
  • verification-loop — Run a six-phase verification of a Claude Code session's work — build, type check, lint, tests with coverage...
  • code-review — Review the changes since a fixed point (commit, branch, tag, or merge-base) along two axes: Standards (does t...
  • differential-review — >
  • code-tour — Create CodeTour .tour files — persona-targeted, step-by-step walkthroughs with real file and line anchors...
  • codebase-onboarding — Analyze an unfamiliar codebase and generate a structured onboarding guide with architecture map, key entry po...
  • diagnosing-bugs — Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or...
  • click-path-audit — Trace every user-facing button/touchpoint through its full state change sequence to find bugs where functions...
  • codehealth-mcp — Real-time structural Code Health via CodeScene MCP — review before edits, verify score deltas after changes...
  • coding-standards — Baseline cross-project coding conventions for naming, readability, immutability, and code-quality review. Use...
  • karpathy-guidelines — Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code...
  • ai-regression-testing — Regression testing strategies for AI-assisted development. Sandbox-mode API testing without database dependen...
  • eval-harness — Eval-driven development (EDD) framework for AI coding sessions — define capability and regression evals befor...

Tooling — Frontend workflow (13)

  • web-design-mcp — Router for web/UI design and frontend work — use when the user says "web design mcp" or asks to design, build...
  • context-budget — Audits Claude Code context window consumption across agents, skills, MCP servers, and rules. Identifies bloat...
  • plan-canvas — Open plans and HTML artifacts in a local browser canvas where the human annotates elements, chats, and approv...
  • plan-orchestrate — Read a plan document, decompose it into steps, design a per-step agent chain from the ECC catalogue, and emit...
  • git-workflow — Git workflow patterns including branching strategies, commit conventions, keeping history clean and readable...
  • documentation-lookup — Use up-to-date library and framework docs via Context7 MCP instead of training data. Activates for setup ques...
  • terminal-ops — Evidence-first repo execution workflow for ECC. Use when the user wants a command run, a repo checked, a CI f...
  • workspace-surface-audit — Audit the active repo, MCP servers, plugins, connectors, env surfaces, and harness setup, then recommend the...
  • configure-ecc — Run the conversational ECC setup wizard inside the current harness: inventory the install, collect scope (use...
  • ecc-guide — Answer questions about ECC by reading the live repo surface — agents, skills, commands, hooks, rules, install...
  • ecc-recipes — Map a described workflow to the right ECC command group with run-order and stop condition, or browse all comm...
  • automation-audit-ops — Evidence-first automation inventory and overlap audit workflow for ECC. Use when the user wants to know which...

Catalog total: 105 skills.

Individual skills in this repo

This repo contains 2 individual skills — each has its own dedicated page.

Habilidades Relacionadas