tavily-cli

The `tavily-cli` skill enables advanced web search, content extraction, site crawling, URL discovery, and deep research directly from the command line. It addresses the challenge of gathering accurate, comprehensive information from the web efficiently, going beyond simple search queries. By leveraging Tavily's CLI, users can fetch and extract content from URLs, map site structures, crawl large sections of websites, and perform multi-source research with citations. This is especially useful for scenarios where agents or standard web tools may fall short in organizing and delivering structured, LLM-optimized information.

Key capabilities of the skill include executing targeted web searches, extracting page content from specific URLs, discovering URLs within a domain, bulk crawling sections of a site, and conducting in-depth research with source references. Each functionality is accessible through specific commands (`search`, `extract`, `map`, `crawl`, `research`) and supports structured JSON output for easy integration with downstream workflows. Additionally, commands can save results to files and read input from standard input, providing flexibility for automation and scripting. The CLI also provides robust authentication options via API keys or OAuth and clear exit codes for error handling.

This skill is ideal for developers, researchers, content analysts, and data engineers who require efficient web data retrieval and analysis. Use cases include finding articles on a topic, extracting documentation or knowledge from web pages, mapping unknown site structures, bulk downloading sections of websites, and conducting thorough research with citations. It is particularly valuable for those who need structured, agent-ready output for AI workflows or want to automate large-scale information gathering and processing tasks from external websites.