extracting-tables

Extract HTML tables and convert them to Markdown and structured JSON.

26|2|Updated Jun 8, 2026
One-click install
npx skills add https://github.com/xberg-io/plugins --skill extracting-tables
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: extracting-tables
Source: https://github.com/xberg-io/plugins/tree/main/plugins/html-to-markdown/.cursor-plugin/skills/extracting-tables
Command: npx skills add https://github.com/xberg-io/plugins --skill extracting-tables

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of extracting tabular data from HTML content, converting it into both Markdown and structured JSON formats for easy processing and analysis.

Core Features & Use Cases

  • HTML Table Parsing: Extracts tables from HTML content, supporting GFM Markdown tables and structured tables array.
  • Markdown Conversion: Converts parsed tables into inline GFM Markdown tables for human-readable output.
  • JSON Output: Provides structured JSON data for programmatic access and manipulation.
  • Use Case: Ideal for data analysts and engineers who need to extract and process tables from web pages or reports.

Quick Start

Extract tables from an HTML file and output as Markdown and JSON using the 'extracting-tables' skill.

Frequently Asked Questions about extracting-tables

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

FAQPage Schema
How do I extract HTML tables and convert them to Markdown?

To extract HTML tables and convert them to Markdown, this Skill parses HTML content and outputs inline GFM Markdown tables, providing human-readable tabular data for immediate use.

What is the best way to parse HTML tables into structured JSON for data analysis?

Parsing HTML tables into structured JSON is handled by converting extracted structured tables into a JSON array, enabling programmatic access and manipulation for data analysis workflows.

Can I convert web scraping results into both GFM Markdown and JSON simultaneously?

Yes, web scraping results from HTML content can be processed simultaneously to generate both GFM Markdown tables for readable output and structured JSON for data analysis.

Does this table extraction approach require any specific dependencies or parsing libraries?

No specific dependencies are required to perform table extraction. The Skill operates independently to parse HTML content and convert it into Markdown and JSON formats.

What are the limitations when extracting tables from HTML for data analysis?

Limitations involve the complexity of the HTML content being parsed; while it supports standard structured tables, heavily nested or malformed HTML might affect the accuracy of the Markdown and JSON output.