@tavily-ai

tavily-search wraps the tavily cli to query the web with llm-optimized snippets and relevance scores, supporting depth tuning, domain filtering, date ranges, and structured json output for downstream processing.

crawl extracts multi-page website content via the tavily api, supporting depth-limited traversal, path filtering, and semantic instructions. returns markdown or saves local files, with tuning for context-window vs data-collection workflows.

extract retrieves clean markdown or text from specified URLs via tavily's api, supporting query-focused reranking, javascript-heavy pages, and batch operations up to 20 urls per request.

web search via tavily api with configurable depth, domain filtering, and time-range constraints. returns ranked results with content snippets and relevance scores optimized for llm processing.

tavily-best-practices documents tavily search api integration with sdks and method reference, but lacks actionable guidance and failure scenario coverage needed for production implementations.

tavily-map uses the tavily cli to enumerate urls on a website without parsing content, useful for rapid site topology discovery before selective crawling.

tavily-research invokes the tavily CLI to perform structured web research with citation, but the skill definition stops abruptly before describing when to use it, input/output contracts, or decision criteria.

Programmatic web search with context isolation. Use this skill for any research task where you need to search the web, filter results, and extract specific…

Comprehensive research grounded in web data with explicit citations. Use when you need multi-source synthesis—comparisons, current events, market analysis,…

Crawl websites and extract content from multiple pages via the Tavily CLI. Use this skill when the user wants to crawl a site, download documentation, extract…

Web search, content extraction, crawling, and deep research via the Tavily CLI. Use this skill whenever the user wants to search the web, find articles,…

Extract clean markdown or text content from specific URLs via the Tavily CLI. Use this skill when the user has one or more URLs and wants their content, says…