How does the query parameter improve extraction results?

The query parameter uses Tavily's intelligence to rerank extracted chunks, ensuring that the most relevant parts of a page are prioritized based on your specific information needs.

Can this skill handle modern, JavaScript-rendered websites?

Yes. By using the 'advanced' extraction depth setting, the skill can effectively process dynamic, JS-heavy pages and single-page applications (SPAs).

What is the maximum number of URLs I can extract at once?

The skill supports batch extraction for up to 20 URLs per request.

Do I need an external API key to use the Extract skill?

Yes, this skill requires a Tavily API key. You can sign up for a key at tavily.com and add it to your ~/.claude/settings.json file.

Tavily Web Content Extractor

Name: Tavily Web Content Extractor
Author: stevessr

bystevessr

0•

网络抓取与数据收集

Extracts clean markdown or text content from specific URLs using the Tavily API without requiring custom scraping scripts.

The Extract skill empowers Claude to retrieve high-quality content from web pages efficiently by leveraging Tavily's specialized extraction engine. It eliminates the complexity of manual scraping by converting raw HTML into clean, LLM-ready markdown or text. This skill is particularly useful for ingesting technical documentation, analyzing research papers, or gathering data from JavaScript-heavy applications, offering advanced features like query-based relevance reranking, multi-URL batching, and configurable extraction depths to ensure the most relevant information is captured.

主要功能

010 GitHub stars

02Clean Markdown and text output optimized for LLM consumption

03Query-based content reranking to focus on specific page sections

04Configurable timeouts and optional image metadata inclusion

05Advanced extraction depth for JavaScript-heavy and dynamic pages

06Batch processing support for up to 20 URLs in a single request

使用场景

01Ingesting technical documentation directly into your workspace for coding assistance

02Analyzing long-form articles or news reports by providing direct URLs to the AI

03Performing market research by extracting content from multiple competitor sites simultaneously

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add stevessr/dotsfiles extract

For use in Claude.ai and ChatGPT

Download Skill