pdf

Process, manipulate, and extract data from PDF documents using Python scripts.

3|Updated Apr 2, 2026

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

Ready to run

npx skills add https://github.com/legout/pi-config --skill pdf-legout

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/legout/pi-config/tree/main/installed-skills/pdf
Command: npx skills add https://github.com/legout/pi-config --skill pdf-legout

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This skill solves the challenge of interacting with PDF documents, whether you need to extract data from complex tables, fill out static or dynamic forms, or perform batch operations like merging and splitting files.

Core Features & Use Cases

Advanced Form Automation: Handles both fillable PDF forms and non-fillable documents using coordinate-based annotation.
Data Extraction: Provides robust tools for pulling text and tabular data from documents, including OCR support for scanned files.
Use Case: Use this skill to process a batch of scanned invoices by extracting text via OCR, identifying key fields, and programmatically filling out a summary report.

Quick Start

Use the pdf skill to extract all text and table data from the document named report.pdf.

Frequently Asked Questions about pdf

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

FAQPage Schema

How do I extract text from scanned PDF files that are not searchable?▼

To extract text from scanned PDF files, this skill uses OCR via pytesseract and pdf2image to convert document pages into images, recognize the text characters, and retrieve the data programmatically for further document processing.

Can I fill out PDF forms programmatically even if the document is not fillable?▼

Yes, you can fill out PDF forms programmatically. For non-fillable documents, the skill applies coordinate-based annotation using reportlab to overlay text precisely, while standard fillable forms are handled directly through pypdf.

What is the best way to extract tabular data from a PDF document?▼

The best way to extract tabular data from a PDF document is using pdfplumber, which provides robust tools for identifying and pulling structured table data accurately from complex layouts.

Does this tool support batch operations like merging and splitting PDF pages?▼

Yes, this tool supports batch operations like merging and splitting PDF pages. It utilizes pypdf to automate document manipulation, allowing you to process multiple files and reorganize pages efficiently.

How do I process a batch of invoices by extracting data and filling a summary report?▼

To process a batch of invoices, you extract text via OCR, identify key fields from the document data, and then programmatically fill out a summary report by applying coordinate-based form filling to generate the final output.