pdf

Extract text, tables, and metadata from PDF documents.

Updated Feb 1, 2026

Search Tags:#automation #ocr #pdf #extraction #data-processing #document-management

Ready to run

npx skills add https://github.com/nferrer-dev/claude-dotfiles --skill pdf-nferrer-dev

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/nferrer-dev/claude-dotfiles/tree/main/skills/pdf
Command: npx skills add https://github.com/nferrer-dev/claude-dotfiles --skill pdf-nferrer-dev

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab, pandas, pytesseract, pdf2image.

What problem does it solve?

This skill solves the challenge of programmatically interacting with PDF documents, which are often difficult to parse or modify without specialized software.

Core Features & Use Cases

Document Manipulation: Merge, split, rotate, and password-protect PDF files.
Data Extraction: Extract raw text and structured tables from documents for analysis.
Use Case: A user can automate the conversion of a multi-page scanned report into an Excel spreadsheet by extracting tables and text via OCR and pdfplumber.

Quick Start

Use the pdf skill to extract all tables from the document named report.pdf and save them into a new Excel file.

Frequently Asked Questions about pdf

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

FAQPage Schema

How do I extract tables from a PDF and save them to Excel?▼

To extract tables from a PDF and save them to Excel, you can use this skill to pull structured table data via pdfplumber and pass it through pandas for dataframe conversion. This automates the transformation of multi-page financial or operational reports into spreadsheet-ready formats.

Can I use OCR to extract text from scanned PDF documents?▼

Yes, you can use OCR to extract text from scanned PDF documents. This skill leverages pytesseract and pdf2image to process image-based PDFs, converting visual document pages into machine-readable text for downstream data processing and automated workflows.

What is the best way to merge and split PDF files programmatically?▼

The best way to merge and split PDF files programmatically is using pypdf within this skill. It provides robust utilities for document manipulation, allowing you to combine multiple PDFs into a single file or extract specific pages without manual editing software.

Does this PDF extraction tool support password-protecting documents?▼

Yes, this PDF extraction tool supports password-protecting documents. Beyond data extraction, it provides comprehensive document manipulation utilities including encryption, allowing you to secure sensitive files directly through automated Python workflows.

How do I generate automated PDF reports from extracted data?▼

To generate automated PDF reports from extracted data, this skill utilizes reportlab for programmatic document creation. You can compile extracted text and tables into newly formatted PDF files, enabling end-to-end automated report generation workflows.

Are there limitations when parsing structured tables from complex PDF layouts?▼

While pdfplumber handles structured table extraction from complex PDF layouts, scanned or image-heavy documents require OCR via pytesseract, which may lose some formatting precision. For highly irregular layouts, combining OCR text extraction with manual pandas structuring yields the best results.