tavily-search

Search the web and return LLM-optimized results with snippets and relevance scores.

Updated Feb 14, 2026
One-click install
npx skills add https://github.com/liutao96/skill --skill tavily-search-liutao96
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tavily-search
Source: https://github.com/liutao96/skill/tree/main/tavily-search
Command: npx skills add https://github.com/liutao96/skill --skill tavily-search-liutao96

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Enables fast, accurate web information gathering by returning LLM-optimized search results with snippets and relevance scores.

Core Features & Use Cases

  • Web search with LLM-optimized results and relevance scoring
  • Domain and time-range filtering, including recent-news queries
  • Structured JSON output for easy downstream processing

Quick Start

Ask Tavily to search the web for your query and return structured JSON results.

Frequently Asked Questions about tavily-search

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get LLM-optimized web search results with content snippets and relevance scores?

LLM-optimized web search returns content snippets and relevance scores by querying the web and structuring the output for direct use in language model pipelines. This approach provides fast, accurate information gathering.

Can I filter web search results by specific domains and time ranges?

Yes, you can filter web search results by domain and time range. The search functionality includes domain filtering and time-range constraints to narrow results to specific sources or recent publication dates.

Does Tavily search support structured JSON output for downstream processing?

Tavily search supports optional JSON output for easy downstream processing. This structured format allows you to parse search results, snippets, and relevance scores programmatically without extracting raw text.

What do I need to run a web search query using Tavily?

To run a Tavily web search query, you need the tvly command-line tool available on your system PATH. This executable processes your search string and applies depth, time-range, and domain filters.

When should I use LLM-optimized search over standard web search for article discovery?

Use LLM-optimized search for article discovery when you need relevance scores and content snippets formatted for language model pipelines. It is suited for information gathering, article discovery, and recent news lookup across topics.

Can I query recent news across topics using domain filtering and depth controls?

Yes, you can query recent news across topics using domain filtering and depth controls. The search applies time-range and domain filters to recent-news queries, returning LLM-optimized results with relevance scores.