This is a practical web scraping tool that hits Baidu, Bing, and DuckDuckGo without needing API keys. It uses Playwright for browser automation and falls back through engines if one fails, which is handy when you need real-time search results in a Claude workflow. The deep search mode grabs extra content from result pages, and there's a basic crawl action for single URLs. Worth noting it downloads Chromium on first run (about 100MB) and the Baidu-first strategy makes sense for Chinese language queries but might not be ideal if you're primarily searching English content. The structured JSON output with titles, URLs, and snippets is clean and easy to parse.
npx skills add https://github.com/yejinlei/web-search-skill --skill web-search