skills.rest
Anthony9906
Anthony9906COMMUNITY
Explore all skills by this author →
GitHub

tavily-extract

Extract clean markdown or text from up to 20 URLs via the Tavily CLI.

Updated Apr 11, 2026
Search Tags:#automation#markdown#javascript#chunking#extract#web-content#urls
One-click install
npx skills add https://github.com/Anthony9906/agent-skills --skill tavily-extract-anthony9906
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tavily-extract
Source: https://github.com/Anthony9906/agent-skills/tree/main/tavily-extract
Command: npx skills add https://github.com/Anthony9906/agent-skills --skill tavily-extract-anthony9906

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract clean markdown or text content from one or more 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.

Core Features & Use Cases

  • Extract content from one or more URLs (including JS-rendered pages) into clean markdown or text.
  • Return content optimized for LLM consumption and downstream processing.
  • Support query-focused chunking and batch processing of up to 20 URLs per call.
  • Use Case: Research multiple pages to collect concise excerpts for a report.

Quick Start

Run a tvly extract command on one or more URLs to fetch clean content from those pages.

Frequently Asked Questions about tavily-extract

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

FAQPage Schema
How do I extract clean text content from multiple URLs at once?▼

To extract clean text content from multiple URLs, you can use this Skill to process up to 20 URLs in a single call. It fetches the pages and returns LLM-optimized markdown or plain text for downstream processing.

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

Yes, you can extract web content from JavaScript-rendered pages. The Skill handles JS-rendered sites by utilizing the Tavily CLI to retrieve the fully loaded page content and convert it into clean markdown.

Does extracting web content into markdown require installing any dependencies?▼

Yes, extracting web content into markdown requires the tvly CLI to be installed in your environment. This command-line tool is necessary for the Skill to interface with Tavily and pull the page content.

What is the best way to pull targeted excerpts from web pages for a research report?▼

The best way to pull targeted excerpts is using the query-focused chunking feature. By applying query-focused chunking during extraction, the Skill isolates and returns only the most relevant sections of the web content for your report.

Are there limitations on how many URLs I can process in one extraction call?▼

Yes, the limitation is 20 URLs per extraction call. If you need to process a larger batch of web pages, you must divide the URLs into multiple calls to successfully extract their markdown content.

Related Skills

Explore More Content & Communication Skills→
drillandrillan

extract

Extract web page content into Markdown or text via Tavily's API.

Community
Intermediate
Mathews-TomMathews-Tom
310

to-markdown

Convert files and URLs to Markdown using MarkItDown with OCR and transcription.

Community
Advanced
C-Jay69C-Jay69

web-reader

Extract titles, HTML, plain text, and timestamps from public URLs.

Community
Intermediate
appautomatonappautomaton
18

html-to-markdown

Converts HTML or live web pages into structured Markdown with metadata and link inventories.

Official
Intermediate