pdf

Merge, split, extract text, fill forms, and OCR PDFs.

Updated Mar 27, 2026

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

Ready to run

npx skills add https://github.com/qiushiyan/harbor-eval-experiments --skill pdf-qiushiyan

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: pdf
Source: https://github.com/qiushiyan/harbor-eval-experiments/tree/main/task-data-analysis-report/environment/skills/pdf
Command: npx skills add https://github.com/qiushiyan/harbor-eval-experiments --skill pdf-qiushiyan

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill simplifies PDF management and data extraction tasks, streamlining workflows and reducing manual effort.

Core Features & Use Cases

PDF Processing: Offers a comprehensive suite of operations including merging, splitting, extracting text, and more.
Form Filling: Supports automated filling of fillable PDF forms, reducing manual data entry.
Use Case: Picture a scenario where you need to combine multiple PDF documents, extract specific information from a batch of scanned PDFs, or fill out a PDF form programmatically. This Skill can handle these tasks with ease.

Quick Start

Use the pdf skill to combine the documents 'doc1.pdf', 'doc2.pdf', and 'doc3.pdf' into a single file 'merged.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 from scanned PDF files?▼

To extract text from scanned PDFs, this solution uses pytesseract for OCR alongside pdfplumber. It converts image-based document pages into searchable text, enabling data extraction from batches of scanned files without manual transcription.

What's the best way to merge multiple PDF documents into one file?▼

Merging multiple PDF documents is handled natively using the pypdf library. You can combine files like 'doc1.pdf' and 'doc2.pdf' into a single 'merged.pdf' output, automating document consolidation workflows with precision.

Can I automate filling out PDF forms programmatically?▼

Automated PDF form filling is fully supported to reduce manual data entry. The Skill programmatically populates fillable PDF form fields, streamlining form digitization and bulk data entry tasks across multiple documents.

Does this PDF processing approach require additional Python dependencies?▼

Comprehensive PDF manipulation requires pypdf, pdfplumber, reportlab, and pytesseract. These dependencies enable merging, text extraction, form filling, and OCR capabilities within your Python environment for complete document processing.

Why use pdfplumber instead of just pypdf for text extraction?▼

Pdfplumber excels at extracting text and data from complex PDF layouts, while pypdf handles structural operations like merging and splitting. This Skill leverages both dependencies to ensure precise data extraction across various document structures.

What are the limitations of using OCR for PDF data extraction?▼

OCR via pytesseract is limited by the quality of the source scanned PDFs. While it automates text extraction from images, low-resolution or heavily distorted documents may result in inaccurate data recognition and require manual verification.