tavily-crawl

Crawl websites with Tavily CLI and save each page as Markdown files.

Updated Apr 3, 2026
One-click install
npx skills add https://github.com/BEIRUX/agent-skills --skill tavily-crawl-beirux
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tavily-crawl
Source: https://github.com/BEIRUX/agent-skills/tree/main/tavily-crawl
Command: npx skills add https://github.com/BEIRUX/agent-skills --skill tavily-crawl-beirux

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Crawling websites to collect content across multiple pages is time-consuming and error-prone. This Skill automates site-wide extraction and saves each page as local Markdown files for offline use and documentation portfolios.

Core Features & Use Cases

  • Bulk crawl entire sections (e.g., /docs) and download content for offline access.
  • Save each crawled page as a separate Markdown file for easy reference and editing.
  • Control crawl scope with depth, breadth, and path filtering, and optionally focus on semantic content.

Quick Start

Run a Tavily crawl on a target site and save the results as Markdown.

Frequently Asked Questions about tavily-crawl

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

FAQPage Schema
How do I crawl a website and save multiple pages as Markdown files?

Crawling a website and saving multiple pages as Markdown files is done by running an automated site-wide extraction that fetches content across a domain and writes each page locally. This enables offline access and bulk documentation collection.

Can I control crawl depth and filter specific paths when extracting website content?

Yes, website content extraction supports depth and breadth control along with path filtering to restrict the crawl scope. You can target specific site sections like /docs and apply semantic instructions to focus on relevant content during the extraction process.

What is the best way to download an entire documentation site for offline access?

Downloading an entire documentation site for offline access is best handled by a bulk crawling tool that traverses multiple pages and exports each page as a separate Markdown file. This ensures you have local copies of all documentation for easy reference and editing.

Does Tavily CLI support bulk content extraction across many pages on a domain?

Yes, Tavily CLI supports bulk content extraction across many pages on a domain. It automates multi-page crawling and applies depth, breadth, and path filtering controls to scope the extraction, saving each page as local Markdown output.

How do I extract website content for offline documentation portfolios?

Extracting website content for offline documentation portfolios requires crawling the target site and exporting each page as Markdown. This process collects multi-page content automatically and saves it locally, creating an editable and accessible reference library.

Are there limitations when crawling large websites with deep page structures?

Crawling large websites with deep page structures may require careful configuration of depth and breadth limits to avoid excessive extraction. Path filtering helps restrict the scope to relevant sections, ensuring the crawl remains focused and manageable within the tool's capabilities.