jelly-pdf

Extract text and tables from PDFs and manipulate documents via Python CLI.

Updated Aug 23, 2026

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

Ready to run

npx skills add https://github.com/dev-jelly/jelly-dotclaude --skill jelly-pdf

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: jelly-pdf
Source: https://github.com/dev-jelly/jelly-dotclaude/tree/main/skills/jelly-pdf
Command: npx skills add https://github.com/dev-jelly/jelly-dotclaude --skill jelly-pdf

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill automates PDF document processing, including text extraction, table extraction, merging, splitting, and form handling, reducing manual data wrangling and document toil.

Core Features & Use Cases

Automated PDF processing: extract text and tables, fill forms, and create new PDFs at scale.
Batch workflows: handle large volumes of PDFs efficiently without manual intervention.
Use Case: convert hundreds of invoices into a structured CSV with extracted fields like invoice number, date, and total amount.

Quick Start

Run the Quick Start guides from the PDF Processing Guide to operate on your PDFs, e.g., process a file named 'invoice-q3.pdf'.

Frequently Asked Questions about jelly-pdf

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

FAQPage Schema

How do I extract text and tables from PDF files automatically?▼

Text and table extraction from PDFs is automated using pdfplumber and pypdf libraries to parse document content into structured formats. This Skill processes PDF pages to identify and extract text blocks and tabular data, enabling large-scale document analysis without manual review.

Can I fill PDF forms programmatically with Python?▼

Form filling works for both fillable and non-fillable PDFs using Python libraries like pypdf and reportlab. This Skill supports JSON-based field definitions to map data into form fields and generate completed documents at scale for batch workflows.

What's the best way to merge, split, and rotate multiple PDFs?▼

PDF manipulation—merging, splitting, rotating, and watermarking—is handled by pypdf and qpdf through scriptable operations. This Skill automates batch document operations, allowing you to process hundreds of files without manual intervention.

How can I extract structured data from invoices and convert to CSV?▼

Document processing extracts fields like invoice number, date, and amount using text extraction and bounding-box validation, then outputs results as structured CSV. This Skill handles batch invoice conversion, transforming unstructured PDF data into queryable records.

Do I need OCR to extract data from scanned PDFs?▼

Scanned PDFs require OCR; this Skill integrates pytesseract and pdf2image to convert image-based pages to text before extraction. Bounding-box validation and image-based validation aids help ensure accuracy on low-quality or complex document layouts.

Can this Skill handle batch processing of large PDF volumes?▼

Batch workflows process hundreds of PDFs efficiently through CLI and scriptable operations using dependencies like pypdf, pdfplumber, and pdftk. This Skill is designed for large-scale document automation, reducing manual data wrangling across document sets.