pdf

Extract text, tables, and images from PDFs using OCR.

12|3|Updated Jun 17, 2026
One-click install
npx skills add https://github.com/phuhao00/bony-agent --skill pdf-phuhao00
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/phuhao00/bony-agent/tree/main/.agent/skills/pdf
Command: npx skills add https://github.com/phuhao00/bony-agent --skill pdf-phuhao00

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab, pytesseract, pdf2image, pdfjs-dist, pdf-lib, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the challenge of interacting with PDF documents, which are often difficult to edit, parse, or fill out programmatically. It removes the need for manual data entry and complex document manipulation.

Core Features & Use Cases

  • Document Manipulation: Merge, split, rotate, and encrypt PDF files with ease.
  • Data Extraction: Extract text, tables, and images from both native and scanned PDFs using OCR.
  • Form Automation: Fill out complex PDF forms, whether they are natively fillable or require visual coordinate-based annotation.

Quick Start

Use the pdf skill to extract all text from the document named report.pdf and save the output to a text file.

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 scanned PDF documents?

To extract text and tables from scanned PDF documents, you can use OCR processing via pytesseract and pdf2image. This approach handles scanned documents by converting pages to images, allowing accurate data retrieval from non-native PDF structures.

What is the best way to automate filling out non-fillable PDF forms?

The best way to automate filling out non-fillable PDF forms is by using coordinate-based annotation. This method utilizes pdf-lib to visually map and insert data onto specific document locations, bypassing the need for native fillable form fields.

How do I merge, split, and encrypt PDF files programmatically?

You can merge, split, and encrypt PDF files programmatically using document manipulation libraries like pypdf and pdfplumber. These tools enable batch document manipulation, allowing you to easily modify document structures and secure content.

Can I use Python libraries to parse complex PDF tables?

Yes, you can use Python libraries like pdfplumber to parse complex PDF tables. It specializes in accurate data retrieval and table parsing across various PDF structures, ensuring structured data extraction from native documents.

Does automated PDF form filling work with both native and scanned documents?

Automated PDF form filling works with both native and scanned documents. It supports natively fillable forms and applies OCR with coordinate-based annotation for scanned or non-fillable forms, ensuring accurate data entry across complex workflows.