tavily

Search the web via the Tavily API and return concise results.

1|Updated Jun 6, 2026
One-click install
npx skills add https://github.com/phillipgan/myagent --skill tavily-phillipgan
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tavily
Source: https://github.com/phillipgan/myagent/tree/main/skills/tavily-search
Command: npx skills add https://github.com/phillipgan/myagent --skill tavily-phillipgan

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of inefficient web search, providing AI-optimized results that are concise and relevant for AI agents.

Core Features & Use Cases

  • AI-Optimized Search: Leverages the Tavily API to return clean, relevant search results optimized for AI agents.
  • Concise Results: Designed to deliver concise information for quick analysis and decision-making.
  • Use Case: When you need to quickly find specific information for a research task or to inform a decision, this Skill can streamline the search process by providing relevant snippets directly.

Quick Start

Execute the search command with your query, e.g., search "latest AI research".

Frequently Asked Questions about tavily

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

FAQPage Schema
How do I get concise web search results for an AI agent?

You can retrieve concise web search results for an AI agent by executing a search command with your query, which uses the Tavily API to return clean, relevant snippets optimized for quick analysis and decision support.

Do I need an API key to perform AI-optimized web search?

Yes, performing an AI-optimized web search requires setting the TAVILY_API_KEY environment variable to authenticate API requests and retrieve relevant search results.

What is the best way to streamline information retrieval for research tasks?

Streamlining information retrieval for research tasks involves using an AI-optimized search engine that returns concise, relevant snippets directly, bypassing the need to parse full web pages manually.

How do I execute a web search query using this information retrieval tool?

To execute a web search query, run the search command followed by your specific query string, such as `search "latest AI research"`, to fetch concise and relevant information.

Can I use this for quick decision support during automated workflows?

Yes, this tool is designed specifically for AI agents to fetch concise information rapidly, making it suitable for providing quick decision support during automated workflows.