pdf

Extract text and tables from native or scanned PDFs using Python.

5|Updated Nov 18, 2025

Search Tags:#automation #data extraction #pdf #form filling #merge pdf #split pdf

Ready to run

npx skills add https://github.com/krishagel/geoffrey --skill pdf-krishagel

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/krishagel/geoffrey/tree/main/skills/pdf
Command: npx skills add https://github.com/krishagel/geoffrey --skill pdf-krishagel

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Manual PDF processing is slow and error-prone; extracting text, tables, and filling forms at scale is tedious and brittle.

Core Features & Use Cases

PDF text and table extraction: programmatically read and convert content from PDFs.
PDF creation and manipulation: create new PDFs, rotate pages, and merge/split documents.
Form handling: detect fillable fields and fill forms programmatically.

Quick Start

Use the PDF toolset to extract text from a sample document and print the page count.

Frequently Asked Questions about pdf

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

FAQPage Schema

How do I extract text and tables from PDF files programmatically?▼

Text and table extraction from PDFs uses libraries like pdfplumber and pypdf to read native and scanned documents page by page. This skill provides programmatic access to parse structured content, handle OCR-ready extraction, and output data for downstream processing.

Can I automate filling out PDF forms at scale?▼

Yes. This skill detects fillable form fields and populates them programmatically, supporting both fillable and non-fillable forms. You can orchestrate form filling across multiple documents in bulk workflows using Python and standard PDF tooling.

How do I merge, split, and manipulate PDF pages?▼

Merge, split, and page-level operations use pypdf and reportlab to combine documents, extract page ranges, and rotate content. This skill handles multi-document orchestration and programmatic PDF creation for bulk processing tasks.

What's the difference between extracting text from native versus scanned PDFs?▼

Native PDFs contain embedded text readable directly; scanned PDFs are images requiring OCR. This skill prepares extraction workflows for both using pdf2image and Pillow conversion, enabling OCR-ready data pipelines from image-based documents.

Can I create and modify PDFs programmatically without manual intervention?▼

Yes. This skill creates new PDFs, applies transformations like rotation and page reordering, and handles form fields entirely through code. It supports CLI and SDK integrations for automated, scalable PDF I/O workflows.

What's the best approach for extracting data from hundreds of PDFs efficiently?▼

Bulk extraction leverages batch processing with pypdf, pdfplumber, and reportlab to read, parse, and output structured data from many documents simultaneously. This skill satisfies requirements for high-volume programmatic PDF workflows and automated data pipelines.