pdf

Extract text and tables from PDFs into CSV or JSON.

Updated Aug 23, 2026

Search Tags:#automation #document processing #data extraction #pdf #form filling #text extraction #table extraction

Ready to run

npx skills add https://github.com/MaxDehaut/default-repository --skill pdf-maxdehaut

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/MaxDehaut/default-repository/tree/main/.claude/skills/pdf
Command: npx skills add https://github.com/MaxDehaut/default-repository --skill pdf-maxdehaut

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, pdf2image, Pillow, and includes scripts (resource) components.

What problem does it solve?

PDF processing is tedious when extracting text/tables, filling forms, and transforming documents manually.

Core Features & Use Cases

Automated text and table extraction from PDFs using Python libraries.
PDF creation, merging, splitting, rotating, watermarking, and form filling.
Use Case: Automate invoice processing and contract archival workflows.

Quick Start

Provide a sample PDF and ask the skill to extract all text and tables, exporting the results as structured data.

Frequently Asked Questions about pdf

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

FAQPage Schema

How do I extract tables and text from PDF documents into structured data?▼

Automated PDF extraction parses document streams and renders pages using pdfplumber and pypdf. It captures text and tables, transforming them into structured data formats like CSV and JSON for analytics workflows.

Can I automate invoice processing and contract archival workflows?▼

You can automate invoice processing and contract archival workflows using end-to-end PDF automation. The Skill captures form data, manipulates documents, and exports structured data for administrative and analytics tasks.

Does PDF form filling and document manipulation support merging and watermarking?▼

Yes, PDF form filling and document manipulation support merging, splitting, rotating, and watermarking. These features enable comprehensive document transformation alongside automated archival workflows.

What is the best way to parse scanned PDFs when text extraction fails?▼

When standard text extraction fails, the best way to parse scanned PDFs is using OCR. The Skill relies on pdf2image and Pillow to render pages and perform OCR, robustly handling scanned document streams.

What are the limitations of automated PDF table extraction?▼

Limitations of automated PDF table extraction include complex or irregular table structures that may require OCR fallback. The Skill includes robust validation and error handling to manage parsing failures and edge cases.