pdf

Extract text and tables from PDFs using Python libraries.

Updated Dec 7, 2025
One-click install
npx skills add https://github.com/92Bilal26/TaskPilotAI --skill pdf-92bilal26
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/92Bilal26/TaskPilotAI/tree/main/.claude/skills/pdf
Command: npx skills add https://github.com/92Bilal26/TaskPilotAI --skill pdf-92bilal26

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdf2image, Pillow.

What problem does it solve?

This Skill automates PDF workflows by enabling extraction of text and tables, creation and modification of PDFs, and automatic form handling, reducing manual data entry and document management time.

Core Features & Use Cases

  • PDF Text & Table Extraction: pull structured data from documents using Python libraries.
  • PDF Creation, Merge & Split: compose new PDFs and reorganize existing ones.
  • Form Filling & Annotations: automatically fill fillable forms or annotate non-fillable PDFs for printing or review.
  • Use Case: streamline invoice processing by extracting line items and totals to CSV, or digitize paper forms for archival.

Quick Start

Use the PDFs skill to process common PDF tasks with the included scripts:

  1. Detect fields in a PDF: python scripts/extract_form_field_info.py input.pdf fields.json
  2. Fill fields with values: python scripts/fill_fillable_fields.py input.pdf fields.json output.pdf
  3. Fill non-fillable forms with annotations: python scripts/fill_pdf_form_with_annotations.py input.pdf fields.json annotated_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 invoices using Python?

PDF form filling is achieved through Python scripts that detect fields using pypdf and output values to a JSON file. For non-fillable forms, the Skill overlays annotations using Pillow and pdf2image to visually populate documents.

How do I automate filling fillable PDF forms with Python?

You can fill fillable PDF forms by running a Python script that reads field mappings from a JSON file and writes the values into the document using pypdf. This automates form digitization and eliminates manual data entry.

Does pypdf support merging and splitting PDF documents in a software pipeline?

The pypdf library supports creating, merging, and splitting PDF documents within automated software pipelines. You can compose new PDFs or reorganize existing archival documents directly through Python scripts.

What is the best way to digitize paper forms for archival using Python?

Digitizing paper forms for archival involves using Python scripts to extract form field information into JSON, then filling the PDF with annotations via pdf2image and Pillow. This renders non-fillable documents for review and printing.

Can I annotate non-fillable PDFs for printing using pdf2image and Pillow?

Yes, you can annotate non-fillable PDFs for printing or review using Python scripts that render pages with pdf2image and apply visual overlays with Pillow. This allows you to populate forms that lack interactive fields.

How do I extract line items and totals from PDFs to CSV for invoice processing?

You can extract line items and totals from PDFs to CSV by running Python scripts that use pypdf to pull structured data from the document. This streamlines invoice processing workflows by outputting actionable data.