pdf

Extract text, tables, and images from PDF documents using Python libraries.

Updated Dec 26, 2025
One-click install
npx skills add https://github.com/jsolarz/doc-toolkit --skill pdf-jsolarz
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/jsolarz/doc-toolkit/tree/main/.skills/pdf
Command: npx skills add https://github.com/jsolarz/doc-toolkit --skill pdf-jsolarz

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDF documents are notoriously difficult to edit or extract data from, often requiring expensive software or hours of manual copying. This Skill provides a complete automation toolkit to process, generate, and analyze PDFs using open-source Python libraries and command-line tools.

Core Features & Use Cases

  • Text and Table Extraction: Pull structured data from invoices, reports, or contracts using pdfplumber and OCR.
  • Document Generation: Create professional PDFs programmatically for proposals, invoices, or documentation.
  • Form Automation: Fill both fillable and non-fillable PDF forms with validated data and precise bounding boxes.

Quick Start

Use the pdf skill to extract all tables from the attached file 'report.pdf' and compile them into a single spreadsheet.

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 invoices automatically?

PDF table extraction automates pulling structured text and tabular data from invoices using pdfplumber and OCR. You can process binary PDF streams to retrieve archival data and compile it into spreadsheets without manual copying.

Can I fill non-fillable PDF forms with validated data using Python?

Filling non-fillable PDF forms is possible by applying validated data with precise bounding boxes. The Skill uses Python libraries to parse coordinates and inject form data into both fillable and flat PDF documents.

What's the best way to generate PDF reports programmatically without manual formatting?

Programmatic PDF generation creates professional documents for proposals and reports using reportlab. You can build documents from scratch by defining layouts in Python, bypassing the need for expensive editing software.

Do I need pypdf and pdfplumber installed to parse binary PDF streams?

Yes, pypdf and pdfplumber are required dependencies to parse binary PDF streams and extract structured content. The environment also uses Pillow and pdf2image to handle image extraction and conversion tasks.

Does this PDF automation approach work for high-volume administrative workflows?

PDF automation applies directly to high-volume administrative workflows like invoice processing and form digitization. It validates form field coordinates and processes archival data retrieval without manual intervention.

What are the limitations of extracting text from scanned PDF documents?

Extracting text from scanned PDFs requires OCR because standard parsing reads embedded text streams, not images. The toolkit addresses this by converting pages with pdf2image before applying optical character recognition.