skills.rest
47network
47networkCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

table-extractor

Extract tabular data from documents and images into structured cells or Markdown tables.

5|Updated Apr 15, 2026
Search Tags:#ocr#markdown#document-processing#extract#table#data-ingestion
One-click install
npx skills add https://github.com/47network/Sven --skill table-extractor-47network
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: table-extractor
Source: https://github.com/47network/Sven/tree/main/skills/ocr/table-extractor
Command: npx skills add https://github.com/47network/Sven --skill table-extractor-47network

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Detects and extracts tabular data from documents and images. Outputs structured cell data or Markdown-formatted tables. Handles merged cells, headers, and multi-page tables.

Core Features & Use Cases

  • Detects tabular data in documents and images and outputs structured cells or Markdown tables.
  • Handles merged cells, headers, and multi-page tables across formats like PDFs and images.
  • Use cases include data extraction for reporting, data ingestion, and table-driven analyses.

Quick Start

Extract tables from a document or image and output them as structured data and/or Markdown-formatted tables.

Frequently Asked Questions about table-extractor

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

FAQPage Schema
How do I extract tables from scanned PDFs and images into structured data?▼

Extracting tables from scanned PDFs and images is done by detecting tabular structures and outputting structured cells or Markdown tables. This handles merged cells, headers, and multi-page continuations for accurate data ingestion.

Can I convert extracted document tables directly into Markdown format?▼

Yes, converting extracted document tables directly into Markdown format is supported. The to_markdown action processes tabular data from documents and images, returning a Markdown table representation alongside row and column counts.

Does table extraction work with merged cells and multi-page tables?▼

Yes, table extraction works with merged cells and multi-page tables. It detects complex tabular structures across multi-page continuations in documents and images, preserving headers and cell layouts for structured data output.

What is the best way to get structured data from OCR outputs and screenshots?▼

The best way to get structured data from OCR outputs and screenshots is using a table extraction process that detects tabular structures. It returns structured cell data and Markdown tables, useful for screenshots with tables or scanned documents.

What formats and table structures are supported for data ingestion?▼

Supported formats for data ingestion include documents and images like scanned PDFs. The table extraction supports complex structures including merged cells, headers, and multi-page tables, outputting structured cell data or Markdown tables.

Related Skills

Explore More Data & Analytics Skills→
nyxoraAInyxoraAI
5

ocr-and-documents

Convert PDFs and scanned images into machine-readable text using OCR.

Community
Advanced
h4vzzh4vzz
33

data-cleaning

Clean raw datasets into analysis-ready tables using pandas, pyjanitor, and great_expectations.

Community
Advanced
BagelHoleBagelHole
46

ai-pipeline-orchestration

Orchestrate AI/ML pipelines for ingestion, training, inference, and RAG indexing.

Community
Advanced
dkyazzentwatwadkyazzentwatwa
86

table-extractor

Extract tables from PDFs and images into CSV, Excel, and JSON.

Community
Intermediate