skills.rest
lgili
lgiliCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

PDF Reader

Extract text, tables, and images from PDFs into Markdown, CSV, and PNG.

Updated Apr 7, 2026
Search Tags:#pdf#markdown#images#pdfplumber#extraction#text#tables
One-click install
npx skills add https://github.com/lgili/skillex --skill pdf-reader-lgili
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: PDF Reader
Source: https://github.com/lgili/skillex/tree/main/skills/pdf-reader
Command: npx skills add https://github.com/lgili/skillex --skill pdf-reader-lgili

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pymupdf, pdfplumber, Pillow, and includes scripts (resource) and references (resource) components.

What problem does it solve?

PDF documents often contain valuable content locked in binary formats. This skill extracts text, tables, and embedded images into editable Markdown, GitHub-friendly tables, and PNG exports for downstream processing.

Core Features & Use Cases

  • Extract text from digital PDFs with layout awareness and multi-column support.
  • Export tables as GitHub-flavored Markdown or CSV for data analysis.
  • Save embedded images as PNGs with color-space handling and optional decorative-filtering.
  • Use cases include archiving reports, digitizing forms, and building datasets from PDFs (digital or scanned).

Quick Start

Run the PDF Reader on a sample PDF to generate a Markdown document, a CSV table file, and PNG images.

Frequently Asked Questions about PDF Reader

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

FAQPage Schema
How do I extract text from multi-column PDF layouts without breaking the reading order?▼

Extracting text from multi-column PDFs requires layout awareness to maintain reading order. This skill processes digital and scanned documents to output structured text, preserving the original column flow.

What is the best way to export tables from PDF documents into CSV or Markdown?▼

The best way to export tables from PDFs into CSV or Markdown is using a tool that preserves table structures. This skill extracts tabular data and saves it as GitHub-flavored Markdown or CSV files for data analysis.

Can I extract embedded images from PDFs and save them as PNG files?▼

Yes, you can extract embedded images from PDFs and save them as PNG files. This skill manages image color spaces and applies optional decorative-filtering to export only meaningful graphics from your documents.

Does pdfplumber work well for extracting structured data from scanned PDFs?▼

Pdfplumber is used alongside PyMuPDF to handle scanned PDFs and extract structured data. The combined approach enforces text-layer detection to manage multi-column layouts and export clean Markdown or CSV outputs.

Why does my PDF text extraction return unstructured or misaligned content?▼

PDF text extraction returns misaligned content when tools lack proper layout awareness. This skill solves that by enforcing text-layer detection and preserving table structures, ensuring accurate multi-column text extraction.

Related Skills

Explore More Data & Analytics Skills→
koolamusickoolamusic
9

pdf

Extracts text and tables from PDF documents.

Community
Advanced
anneschuthanneschuth

parse-organogram

Extracts Dutch ministerial organogram hierarchies and personnel assignments into JSON proposals.

Community
Intermediate
tomlupotomlupo

pdf-reader

Extract text, images, tables, and metadata from PDF documents.

Community
Advanced
NeoLabs-SystemsNeoLabs-Systems
23

ocr-and-documents

Extract text from PDFs and scanned documents using OCR.

Official
Intermediate