tavily-search

Search the web with domain filtering, time ranges, and JSON output.

2|Updated Mar 26, 2026

Search Tags:#search #web #tavily #json-output #domain-filter #llm-optimized

Ready to run

npx skills add https://github.com/calvingit/skills --skill tavily-search-calvingit

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tavily-search
Source: https://github.com/calvingit/skills/tree/main/external-skills/Tool/tavily-search
Command: npx skills add https://github.com/calvingit/skills --skill tavily-search-calvingit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides fast, structured web search results optimized for LLM consumption, including content snippets, relevance scores, and metadata to feed downstream reasoning.

Core Features & Use Cases

LLM-optimized web search results with content snippets and relevance scores
Domain filtering, time ranges, and multiple search depths
CLI-based search via tvly with options for include-raw-content, include-domains, and JSON output

Quick Start

Run tvly search with your query and request JSON output for easy ingestion.

Frequently Asked Questions about tavily-search

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

FAQPage Schema

How do I get JSON web search results optimized for LLM consumption?▼

You can get LLM-optimized web search results by running a CLI-based search and requesting JSON output, which structures content snippets and relevance scores for easy ingestion.

What is the best way to perform web research with domain filtering and time ranges?▼

The best way to perform web research with domain filtering and time ranges is using a CLI search tool that supports include-domains and time range options to scope queries precisely.

Can I include raw content and metadata when gathering articles from the web?▼

Yes, you can include raw content and metadata when gathering articles by enabling specific options in the CLI search command to retrieve full content alongside relevance scores.

Does the tavily-search Skill support multiple search depths for discovering sources?▼

Yes, tavily-search supports multiple search depths for discovering sources, allowing you to adjust the query scope to retrieve either basic or more detailed structured web results.

Why use a CLI-based search tool instead of a standard search engine for LLM workflows?▼

A CLI-based search tool is used instead of a standard search engine for LLM workflows because it directly outputs structured JSON with content snippets and metadata, avoiding manual HTML parsing.