pdf

Extract text and tables from PDFs using pypdf, pdftotext, and pdfplumber.

2|2|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/patronus-ai/skill-inject --skill pdf-patronus-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/patronus-ai/skill-inject/tree/main/data/skills/document-skills/pdf
Command: npx skills add https://github.com/patronus-ai/skill-inject --skill pdf-patronus-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill removes the friction of working with PDFs by giving you reliable steps to extract text/tables and to generate or fill PDFs, including handling form fields.

Core Features & Use Cases

  • Text and table extraction: Extract page text and structured tables using Python tools, especially for reports and semi-structured documents.
  • PDF creation and transformation: Create new PDFs, merge/split documents, rotate pages, and extract metadata for downstream workflows.
  • Form handling: Detect fillable fields and fill them programmatically, or add annotations to non-fillable forms using bounding boxes to place text precisely.
  • Use Case: Turn a folder of policy documents into structured data by extracting text and tables, then filling a form template with generated values while keeping layout accurate.

Quick Start

Ask the Skill to fill a PDF form by first checking whether the PDF has fillable fields, then extracting field locations, then entering your values and producing a filled output 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 and tables from PDF documents programmatically?

Extract text and tables from PDF documents using pypdf and pdfplumber. These Python tools parse semi-structured reports and policy documents, returning structured page text and table data for downstream workflows.

How do I fill a PDF form automatically using Python?

Fill a PDF form automatically by first detecting fillable fields, extracting their coordinates, and then entering values programmatically. For non-fillable forms, add annotations using bounding boxes to place text precisely on the output PDF.

Can I merge, split, and rotate PDF pages at scale?

Merge, split, and rotate PDF pages at scale using pypdf. You can create new PDFs, transform existing documents by rotating pages, and extract metadata to support large-scale document processing workflows.

What's the best way to process non-fillable PDF templates with data?

Process non-fillable PDF templates by adding annotations using bounding boxes to place text precisely. This approach bypasses fillable field detection and directly overlays generated values onto the PDF layout.

Does pdfplumber work for extracting structured tables from semi-structured PDFs?

Yes, pdfplumber works for extracting structured tables from semi-structured PDFs. It parses report documents and returns structured table data, which can be used to fill form templates with generated values while keeping layout accurate.

What Python libraries do I need to generate and manipulate PDF files?

Generate and manipulate PDF files using pypdf, pdfplumber, pdf2image, PIL, and reportlab. These libraries support text extraction, table parsing, image conversion, and PDF creation for automated document processing workflows.