web-scraper

This web scraping skill automates intelligent data extraction through adaptive reconnaissance phases that automatically select the most efficient scraping strategy. It detects website frameworks, validates every selector and API endpoint before reporting, and includes self-critiquing reports with gap analysis. The skill guides implementation from simple HTTP-based extraction through browser automation and anti-blocking techniques, then helps productionize scrapers as TypeScript Apify Actors. Developers benefit from framework-aware detection that skips irrelevant patterns, quality gates that avoid unnecessary work, and iterative implementation that adds complexity only when needed.

Add the skill directory to Claude Code's skills folder. Request scraping by providing a URL—Claude automatically phases through reconnaissance, validation, and implementation. For Apify Actor deployment, ask Claude to convert the scraping logic to an Actor, which guides TypeScript setup, template selection (Cheerio vs Playwright), schema configuration, and testing.