pdf

Name: pdf
Availability: InStock
Author: bhisoftware

Fill PDF forms and extract text and tables from documents.

Updated Aug 27, 2026

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

Ready to run

npx skills add https://github.com/bhisoftware/page-refresh --skill pdf-bhisoftware

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/bhisoftware/page-refresh/tree/main/library/bhi-claude-skills/pdf-tools
Command: npx skills add https://github.com/bhisoftware/page-refresh --skill pdf-bhisoftware

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates the tedious and time-consuming tasks of filling out PDF forms and extracting data from documents, freeing up valuable time and reducing manual errors.

Core Features & Use Cases

Fillable & Non-Fillable Forms: Handles both types of PDF forms, ensuring compatibility with a wide range of documents.
Data Extraction: Extracts text and tables from PDFs, converting unstructured data into usable formats.
Use Case: Automatically populate client intake forms, extract information from scanned invoices, or convert lengthy reports into searchable text documents.

Quick Start

Use the pdf skill to fill out the form in 'application.pdf' with the provided data.

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 a PDF document?▼

PDF data extraction is handled by pdfplumber and pypdf, which parse document structures to pull text and tables, converting unstructured content into usable formats. It processes both native text and scanned documents programmatically.

Can I automate filling out non-fillable PDF forms?▼

Automating non-fillable PDF forms is supported by converting PDFs to images using pdf2image and programmatically adding text with reportlab. This approach bypasses missing native form fields by overlaying data directly onto the document visual layer.

Does this approach work with scanned PDFs for data extraction?▼

Scanned PDF data extraction works by converting documents to images with pdf2image and applying pytesseract OCR. This optical character recognition process transforms image-based text into searchable, machine-readable data.

What is the best way to programmatically populate client intake PDF forms?▼

The best way to programmatically populate client intake PDF forms is by analyzing field structures and injecting data using pypdf and reportlab. It supports both fillable and non-fillable documents to automate form population accurately.

What are the limitations of using pypdf for PDF manipulation?▼

Limitations of using pypdf for PDF manipulation include difficulty extracting complex table structures, which requires pdfplumber, and handling image-only documents, which requires converting to images and applying additional OCR processing.