skills.rest
ricable
ricableCOMMUNITY
Explore all skills by this author →
GitHub

extract

Extract clean markdown or text from specified URLs using Tavily API access.

Updated Feb 15, 2026
Search Tags:#markdown#research#content ingestion#tavily#url scraping#web extraction
One-click install
npx skills add https://github.com/ricable/mcai --skill extract-ricable
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: extract
Source: https://github.com/ricable/mcai/tree/main/.agents/skills/extract
Command: npx skills add https://github.com/ricable/mcai --skill extract-ricable

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, curl, npx, mcp-remote, and includes scripts (resource) components.

What problem does it solve?

This Skill removes the friction of copying content from web pages by turning one or more URLs into clean markdown or text that is ready to use.

Core Features & Use Cases

  • Targeted URL extraction: Pull content from specific pages when you already know the exact sources you need.
  • Query-focused retrieval: Rerank extracted chunks around a topic so you get the most relevant passages first.
  • JavaScript-heavy pages: Use advanced extraction for dynamic sites, tables, and structured content that basic scraping may miss.
  • Research and content workflows: Collect article text, documentation, or reference material from multiple pages for analysis, summarization, or ingestion.

Quick Start

Run the extract script with a JSON object containing the URLs you want to extract and any optional query or depth settings.

Frequently Asked Questions about extract

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

FAQPage Schema
How do I extract clean markdown from web pages for research workflows?▼

Web content extraction for research workflows pulls targeted content from specific URLs and converts it into clean markdown. It applies query-focused chunk reranking to deliver structured text ready for content ingestion and documentation analysis.

Does Tavily API access work for scraping JavaScript-heavy web pages?▼

Yes, Tavily API access enables advanced extraction from JavaScript-heavy web pages. It processes dynamic sites and structured content that basic scraping misses, requiring either OAuth or API key authentication to retrieve clean markdown output.

What's the best way to scrape multiple URLs for content ingestion?▼

The best way to scrape multiple URLs for content ingestion is passing a JSON object with target links and optional depth settings. This approach validates JSON input and applies query-based chunk reranking to prioritize relevant passages from each page.

Can I rerank extracted web content chunks around a specific topic?▼

You can rerank extracted web content chunks around a specific topic by providing a query parameter in your JSON input. This query-focused retrieval prioritizes relevant passages first, optimizing research and summarization tasks.

Do I need an API key to extract content from dynamic sites?▼

Yes, you need Tavily OAuth or API key access to extract content from dynamic sites. This authentication is required to run advanced extraction on JavaScript-heavy pages and parse the structured response into clean markdown.

Related Skills

Explore More Education & Research Skills→
family3253family3253

tavily-extract

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

Community
Intermediate
smallnestsmallnest
190

markitdown

Convert PDFs, Word, Excel, HTML, and images with OCR into Markdown.

Community
Advanced
superfhpsuperfhp

siyuan

Interact with the SiYuan Notebase API using curl commands.

Community
Intermediate
drillandrillan

extract

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

Community
Intermediate