extract

Name: extract
Availability: InStock
Author: stevessr

Extract clean markdown or text from URLs via Tavily's extraction API.

Updated Dec 1, 2025

Search Tags:#markdown #api #content #web #extract #tavily #urls

Ready to run

npx skills add https://github.com/stevessr/dotsfiles --skill extract-stevessr

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: extract
Source: https://github.com/stevessr/dotsfiles/tree/main/dot_agents/skills/extract
Command: npx skills add https://github.com/stevessr/dotsfiles --skill extract-stevessr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, curl, and includes scripts (resource) components.

What problem does it solve?

Extract content from URLs using Tavily's extraction API to obtain clean markdown or text without manual copy-paste, enabling rapid content reuse.

Core Features & Use Cases

Extracts content from one or more URLs into clean markdown or text
Supports query-focused reranking and chunking per source for targeted extraction
Works with both static and dynamic pages via depth control and optional timeouts

Quick Start

Provide a JSON payload with the URLs to extract and optional parameters to tailor depth and chunking.

Frequently Asked Questions about extract

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

FAQPage Schema

How do I extract content from URLs into clean markdown?▼

To extract content from URLs into clean markdown, provide a JSON payload with the target URLs to the extraction API. It returns clean, structured markdown or text without requiring manual copy-paste, supporting both single and multiple URLs.

Can I extract content from JavaScript-heavy web pages?▼

Yes, you can extract content from JavaScript-heavy web pages by adjusting the extract_depth parameter in your JSON payload. This depth control enables the extraction API to properly render and capture dynamic content from complex web sources.

Do I need an API key to extract web content from URLs?▼

Yes, you need a valid Tavily API key to authenticate extraction requests. The extraction API requires this key to process your JSON payload containing URLs and optional parameters, returning structured results or errors based on the request validity.

What is the best way to extract targeted chunks of content from multiple URLs?▼

The best way to extract targeted chunks from multiple URLs is to use query-based reranking and chunks_per_source parameters. This instructs the extraction API to segment and prioritize specific content from each source URL based on your query.

Does this content extraction tool support curl and jq?▼

Yes, the content extraction tool relies on curl and jq as dependencies to automate API requests and process JSON responses. These components handle the HTTP communication and parse the structured markdown or text results returned by the extraction API.