
Web Search
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.
- skills.sh installs
- 376
- GitHub stars
- 2
- last updated
- Aug 21, 2026
Install
$ npx -y skills add yejinlei/web-search-skill --skill web-search --agent claude-codeInstalls into .claude/skills of the current project.
Files
Web Search Skill
A powerful web search skill supporting multiple search engines without requiring API keys.
Features
- π Multi-Engine Support: Baidu (Playwright), Bing, DuckDuckGo
- π No API Key Required: Uses browser automation and web scraping
- π Smart Fallback: Automatically switches engines when one fails
- π Structured Results: Returns clean search results with title, URL, and snippet
- π High Performance: Async support with Playwright browser automation
Usage
Basic Search
result = main({
"action": "search",
"query": "Python tutorial",
"num_results": 5
})
Deep Search
result = main({
"action": "deep_search",
"query": "machine learning latest research",
"num_results": 5
})
Web Page Crawling
result = main({
"action": "crawl",
"url": "https://example.com"
})
Input Parameters
Sponsors
Details
- Repository
- github.com/yejinlei/web-search-skill
- Category
- Backend & APIs
- First seen
- Jun 3, 2026