pdf

Process, manipulate, and extract data from PDF documents using Python scripts.

Updated May 5, 2026
One-click install
npx skills add https://github.com/iani-kuli/harness_bro --skill pdf-iani-kuli
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/iani-kuli/harness_bro/tree/main/.claude/skills/curated/pdf
Command: npx skills add https://github.com/iani-kuli/harness_bro --skill pdf-iani-kuli

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires pypdf, pdfplumber, reportlab, pdf2image, pytesseract, pandas, pillow, numpy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This skill solves the challenge of interacting with PDF documents, which are notoriously difficult to manipulate, fill, or extract data from programmatically.

Core Features & Use Cases

  • Advanced Form Automation: Handles both native fillable fields and non-fillable documents using coordinate-based annotation.
  • Data Extraction: Provides robust tools for pulling text, tables, and images from complex document layouts.
  • Document Manipulation: Supports merging, splitting, rotating, and encrypting PDF files for professional workflows.

Quick Start

Use the pdf skill to extract all text and tables from the document named report.pdf and save the results to a new file.

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 complex PDF documents?

To extract text and tables from PDF documents, this skill utilizes pdfplumber for structured table parsing and pypdf for text extraction. It automates pulling data from complex layouts and exporting the parsed results to a new file.

Can I automate fillable PDF form filling without native AcroForm fields?

Yes, you can automate PDF form filling for non-fillable documents. The skill handles native fillable fields and supports coordinate-based annotation to place text precisely on flat documents using reportlab.

What is the best way to parse scanned PDFs using OCR in Python?

The best way to parse scanned PDFs using OCR is combining pdf2image to rasterize pages and pytesseract for text recognition. This skill orchestrates these dependencies to extract text from scanned document images automatically.

Does this approach support merging, splitting, and encrypting PDF files?

Yes, this approach supports merging, splitting, and encrypting PDF files. It provides robust document manipulation capabilities through pypdf, allowing you to manage professional workflows like rotating and securing documents programmatically.

Do I need pandas and numpy installed to process PDF tables?

Yes, you need pandas and numpy installed as dependencies. They are required to structure and manipulate the tabular data extracted from PDF documents using pdfplumber, ensuring accurate data handling for downstream workflows.