This skill should be used when users need to scrape content from websites, extract text from web pages, crawl and follow links, or download documentation from online sources. It features concurrent URL processing, automatic deduplication, content filtering, domain restrictions, and proper directory hierarchy based on URL structure.
Install
npx skills add Igosuki/claude-skills --skill web-scrapernpx skills add Igosuki/claude-skills --skill web-scraper -a claude-code -gnpx skills add Igosuki/claude-skills --skill web-scraper -a codex -ggemini skills install https://github.com/Igosuki/claude-skills.git --path web-scrapergh skill install Igosuki/claude-skills web-scrapergit clone --depth 1 https://github.com/Igosuki/claude-skills /tmp/Igosuki__claude-skills
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/Igosuki__claude-skills/web-scraper ~/.claude/skills/web-scraper # Claude Code
cp -R /tmp/Igosuki__claude-skills/web-scraper ~/.agents/skills/web-scraper # Codex, Cursor, Gemini CLI, Copilot, OpenCode