tavily

Search the web and extract URL content into markdown.

Updated Apr 8, 2026
One-click install
npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill tavily-johnnywhitemike
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tavily
Source: https://github.com/JOHNNYWHITEMIKE/openclaw/tree/main/openclaw/.openclaw/openclaw/extensions/tavily/skills/tavily
Command: npx skills add https://github.com/JOHNNYWHITEMIKE/openclaw --skill tavily-johnnywhitemike

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Tavily reduces the time spent searching for reliable information online and manually copying relevant content by providing search, optional AI-summarized results, and targeted webpage extraction.

Core Features & Use Cases

  • Quick web search: Perform fast, straightforward queries via the web_search workflow when you just need results.
  • Advanced research search: Use tavily_search for configurable depth, topics, time ranges, domain constraints, and optional answer summaries.
  • Targeted content extraction: Use tavily_extract to fetch and convert the content of specific URLs into clean markdown, optionally chunked and relevance-ranked to a query.

Use case example: You need recent, domain-restricted research on a specific topic (e.g., “AI regulation in the EU during the last month”)—run tavily_search, then extract only the most relevant parts from the best matching URLs with tavily_extract.

Quick Start

Use the tavily skill to run an advanced web search for your query, then extract content from the specific URLs you choose.

Frequently Asked Questions about tavily

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

FAQPage Schema
How do I extract clean content from a specific webpage URL for research?

To extract clean content from a specific webpage URL for research, you can use targeted extraction workflows that fetch webpages and convert their content into readable markdown, optionally chunking and ranking the text by relevance to your query.

Can I filter web search results by domain and time range?

You can filter web search results by domain and time range using advanced research search parameters, allowing you to include or exclude specific domains and set time constraints to refine the returned information.

What is the best way to get AI-summarized answers for a quick web search?

The best way to get AI-summarized answers for a quick web search is to run a fast query workflow that returns relevant results and optionally includes an AI-generated answer summary alongside the raw links.

How do I perform a deep web search on a specific topic with configurable parameters?

You can perform a deep web search on a specific topic by using an advanced search workflow that supports configurable search depth, topic filtering, domain constraints, and time ranges to gather comprehensive evidence.

Does web content extraction work with domain filtering to gather targeted evidence?

Yes, web content extraction works with domain filtering to gather targeted evidence by first running a search with domain constraints, then extracting readable content from the best matching URLs.

Why use query-focused extraction instead of a general web search?

You should use query-focused extraction instead of a general web search when you already have specific URLs and need to convert their full content into clean markdown, extracting only the chunks most relevant to your query.