tavily-search

Search the web and return structured JSON results with relevance scores.

1|Updated May 10, 2026
One-click install
npx skills add https://github.com/a2ajinkya/phone-pi --skill tavily-search-a2ajinkya
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tavily-search
Source: https://github.com/a2ajinkya/phone-pi/tree/main/skills/tavily-search
Command: npx skills add https://github.com/a2ajinkya/phone-pi --skill tavily-search-a2ajinkya

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Web research often requires collecting current information from multiple sources quickly; this skill provides fast, structured web search results with relevance scoring and metadata to feed AI workflows.

Core Features & Use Cases

  • Web search using the Tavily CLI with structured JSON output
  • Domain and time-range filters, multiple search depths
  • Use cases: quick background research, fact-checking, and source discovery across domains

Quick Start

Run a basic search with tvly search "your query" --json to retrieve structured 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 structured JSON output from a web search for my AI workflow?

Structured JSON output from a web search is generated by running a query with the Tavily CLI, returning content snippets, relevance scores, and metadata optimized for downstream AI workflows.

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

Yes, web search results can be filtered using optional domain filters and time-range controls to narrow down source discovery and gather current information across specific domains.

What is the best way to collect current information from multiple sources for fact-checking?

Collecting current information for fact-checking is best handled by performing a web search with multiple search depths, returning diverse articles with relevance scores and metadata.

Does Tavily CLI require any external dependencies to perform quick background research?

No external dependencies are required to perform quick background research, as the skill operates independently using the Tavily CLI to retrieve LLM-optimized search results.

How does relevance scoring work in LLM-optimized web search results?

Relevance scoring in LLM-optimized web search results evaluates and ranks retrieved content snippets, providing metadata that helps downstream processing prioritize diverse articles across domains.