processing-pdfs

Extract text and tables from PDFs using Python libraries.

Updated Jan 26, 2026

Search Tags:#automation #pdf #python #data-extraction #form-filling #pdf-processing #document-automation

Ready to run

npx skills add https://github.com/indiosmo/skills --skill processing-pdfs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: processing-pdfs
Source: https://github.com/indiosmo/skills/tree/main/skills/processing-pdfs
Command: npx skills add https://github.com/indiosmo/skills --skill processing-pdfs

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

PDF forms and documents often require manual, repetitive processing. This Skill consolidates extraction, creation, merging, and annotation of PDFs into an automated workflow.

Core Features & Use Cases

Text and Table Extraction: retrieve text and tabular data from PDFs into usable formats.
PDF Creation, Merging, and Annotation: generate new PDFs, combine multiple documents, and apply annotations or form-related data.
Form Handling: extract metadata about fillable fields, validate bounding boxes, and fill or annotate forms at scale.

Quick Start

Run the extraction workflow on a sample PDF using uv run scripts/extract_form_field_info.py <input.pdf> <fields.json> to generate field metadata.

Frequently Asked Questions about processing-pdfs

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract text and tabular data from PDF files using Python?▼

To extract text and tables from PDFs, this Skill uses Python libraries like pypdf and pdfplumber to parse document contents into usable structured formats at scale.

What's the best way to automate filling and annotating PDF forms at scale?▼

Automating PDF form filling and annotation is handled by retrieving field metadata, validating bounding boxes, and applying form data via pypdf to generate annotated outputs.

Can I use pypdf to merge multiple PDF documents and generate new files?▼

Yes, you can use pypdf to merge multiple PDF documents and generate new files, combining separate pages and applying annotations into a single output file.

Do I need pdf2image and Pillow to process PDFs for data extraction?▼

You need pdf2image and Pillow to process PDFs when rendering pages as images for visual validation, while pypdf and pdfplumber handle direct text extraction.

How does automated PDF processing handle contracts, invoices, and reports?▼

Automated PDF processing handles contracts, invoices, and reports by parsing document structures, extracting field metadata, and validating form data to automate repetitive workflows.