web▌

Implement WCAG 2.1 accessibility standards for semantic HTML, keyboard navigation, ARIA attributes, and screen reader support. \n \n Covers semantic HTML structure, keyboard navigation (Tab, arrow keys, ESC), and focus management for modals and interactive components \n Provides ARIA attribute guidance (aria-label, aria-live, aria-hidden, role attributes) with practical React/TypeScript examples \n Includes color contrast requirements (WCAG AA/AAA), visual focus indicators, and testing strategie

Apple's design principles for creating fluid, gesture-driven interfaces on the web.

Web Design Guidelines \n Modern web design principles for responsive layouts, accessibility, and visual hierarchy. \n When to Use \n \n Creating polished web interfaces \n Improving accessibility \n Responsive design patterns \n Visual hierarchy decisions \n \n Source \n This skill references patterns from Vercel's agent-skills .

Web search using the agent's built-in WebSearch tool, no API key required. \n \n Accepts simple query strings and returns relevant web results; best for current information, recent events, fact verification, and real-time research \n Effective queries benefit from specificity, year inclusion for recency, and domain-specific terminology; iterative refinement recommended for broad or multi-perspective searches \n Results cannot access paywalled content and depend on the agent's WebSearch implement

Reverse-lookup glossary for web animation terms based on user descriptions.

Neural search across web, code, and company research without API keys. \n \n Three core tools: web search for news and facts, code search for GitHub and Stack Overflow examples, and company research for business intelligence \n Configurable search depth with type parameter (\"fast\" or \"deep\") for web queries and adjustable token ranges (1000–50000) for code context \n Optional advanced tools available via config update, including domain/date filtering, query expansion, full page crawling, peo

Search the web and extract content via inference.sh CLI.

Expert guidance for building scalable web scrapers and crawlers using Scrapy with best practices for spider development, data extraction, and pipeline management. \n \n Covers spider architecture, CSS/XPath data extraction, Item Pipelines, and middleware development for request/response handling \n Includes strategies for rate limiting, User-Agent rotation, proxy management, and handling JavaScript-rendered content with Scrapy-Splash or Scrapy-Playwright \n Provides error handling patterns, perf

Elite frontend image-direction skill for generating premium, conversion-aware website design references. CRITICAL OUTPUT RULE — generate ONE separate horizontal image FOR EVERY section. A landing page with 8 sections produces 8 images. Never compress multiple sections into one image. Enforces composition variety (not always left-text / right-image), background-image freedom, varied CTAs, varied hero scales (giant / mid / mini minimalist), narrative concept spine, second-read moments, and a single consistent palette across all images. Optimized for landing pages, marketing sites, and product comps that developers or coding models can accurately recreate.

Reliable web scraping with cascading fallbacks, anti-bot bypass, and poison pill detection. \n \n Implements a scraping cascade architecture with four strategies: trafilatura for fast article extraction, requests with rotating user agents, Playwright with stealth mode for JavaScript-heavy sites, and async Playwright for Jupyter notebooks \n Includes poison pill detection to identify paywalls, CAPTCHAs, rate limits, Cloudflare blocks, and login walls using pattern matching and status code analysi