tavily-extract
Extract clean markdown or text content from specific URLs via the Tavily CLI. Use this skill when the user has one or more URLs and wants their content, says "extract", "grab the content from", "pull the text from", "get the page at", "read this webpage", or needs clean text from web pages. Handles JavaScript-rendered pages, returns LLM-optimized markdown, and supports query-focused chunking for targeted extraction. Can process up to 20 URLs in a single call.
Security Assessment
Detected risks:
About tavily-extract
The tavily-extract skill is designed to facilitate the extraction of clean markdown or text content from specified URLs using the Tavily CLI. This skill addresses the need for users to retrieve content from web pages, especially when dealing with JavaScript-rendered pages that may not display their content in a straightforward manner. By providing a streamlined method to extract relevant information, users can efficiently gather data for research, analysis, or content creation without the hassle of manual copying and formatting.
FAQ
How do I install the Tavily CLI?
You can install it by running the command: curl -fsSL https://cli.tavily.com/install.sh | bash && tvly login.
What is the maximum number of URLs I can process at once?
You can process up to 20 URLs in a single call.
What should I do if the content I need is missing?
Try using the 'advanced' extract depth for JavaScript-rendered pages or adjust your query parameters.
Can I save the extracted content to a file?
Yes, you can save the output to a file using the -o or --output option.
Is there a timeout option for slow pages?
Yes, you can set a timeout between 1 to 60 seconds using the --timeout option.
Install tavily-extract
Quick Setup:
- Copy the skill folder to
.claude/skills/ - Claude will automatically detect and use the skill
Repository
tavily-ai/skills