tavily

Name: tavily
Availability: InStock
Author: autorun

Extract web content and search results via the Tavily API.

1|Updated Apr 14, 2026

Search Tags:#API #web search #content retrieval #fallback #web content extraction

Ready to run

npx skills add https://github.com/autorundev/autorun-skills --skill tavily-autorundev

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: tavily
Source: https://github.com/autorundev/autorun-skills/tree/main/tavily
Command: npx skills add https://github.com/autorundev/autorun-skills --skill tavily-autorundev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires requests, python-dotenv, and includes scripts (resource) components.

What problem does it solve?

This Skill automates the extraction of web content and search queries using the Tavily API, providing a fallback when WebFetch fails or encounters issues.

Core Features & Use Cases

Content Extraction: Extract text from URLs and convert it into markdown format.
Web Search: Execute web searches and present up to 5 search results.
Fallback: Automatically uses Tavily API when WebFetch returns errors.
Use Case: If your AI encounters a website that WebFetch cannot fetch or parse, Tavily will step in to retrieve and process the content.

Quick Start

Execute a search for 'example query' with the tavily skill.

Frequently Asked Questions about tavily

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

FAQPage Schema

How do I extract web content from a URL when WebFetch fails to parse the page?▼

To extract web content when WebFetch fails, this Skill uses the Tavily API to fetch the URL and convert the retrieved text into markdown format, serving as an automated fallback mechanism for inaccessible pages.

How does web search and content retrieval work with the Tavily API?▼

Web search and content retrieval with the Tavily API works by executing search queries and returning up to 5 results with relevant snippets, while requiring a TAVILY_API_KEY environment variable to authenticate API access.

Do I need an API key to perform web content extraction and search queries?▼

Yes, you need an API key to perform web content extraction. You must configure the TAVILY_API_KEY environment variable in your python-dotenv setup to authenticate requests and enable the Tavily API fallback operations.

What is the best way to get markdown formatted text from web pages that block standard fetching?▼

The best way to get markdown formatted text from blocked web pages is using an API fallback service, which handles URL extraction and content conversion to bypass standard fetching limitations and retrieve the text.

Can I use this web search fallback for large-scale content retrieval exceeding five results?▼

You cannot use this web search fallback for large-scale content retrieval exceeding five results, as the search functionality is currently limited to presenting a maximum of 5 search results with snippets per query.

Why does WebFetch return errors on certain websites and how can I retrieve their content?▼

WebFetch returns errors on certain websites due to parsing limitations or access restrictions, and you can retrieve their content by triggering the Tavily API fallback to extract and convert the web content into markdown.