Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.
Author
Category
Document ProcessingInstall
Hot:110
Download and extract to your skills directory
Copy command and send to OpenClaw for auto-install:
Download and install this skill https://openskills.cc/api/download?slug=anthropics-skills-pdf&locale=en&source=copy
PDF Processing Skill
Skill Overview
The PDF skill is a comprehensive PDF file processing solution that supports a variety of operations such as reading, extraction, merging, splitting, encryption, and OCR.
Applicable Scenarios
When you need to batch merge or split a large number of PDF files, this skill provides efficient Python libraries and command-line tools to enable automated processing.
Extract text and structured data from PDF reports, invoices, and tables, with support for exporting tables to Excel for analysis.
Perform OCR on scanned PDFs to convert image-based PDFs into searchable, editable text documents.
Core Features
Supports common operations such as merging multiple PDF files, splitting documents by pages, rotating pages, adding/removing watermarks, and setting password protection. These can be accomplished using pypdf or the command-line tool qpdf.
Use pdfplumber to accurately extract text content and table data from PDFs, with support for preserving the original layout and exporting to structured data formats.
Create new PDF documents using reportlab, supporting multi-page report generation; supports filling PDF form fields to enable automated form processing.
Frequently Asked Questions
What operations does the PDF skill support?
The skill supports reading and extracting PDF text/tables, merging/splitting PDFs, rotating pages, adding watermarks, creating new PDFs, filling forms, encrypting/decrypting, extracting images, and OCR text recognition for scanned PDFs.
How do I merge multiple PDF files?
You can use Python's pypdf library or the command-line tool qpdf. Python example: create a PdfWriter object, iterate through each PDF file's pages and add them to the writer, then save the merged file.
How do I extract text from scanned PDFs?
You need to use OCR technology. The recommended approach is to convert the PDF to images using pdf2image, then perform text recognition with pytesseract. Install dependencies with:
pip install pytesseract pdf2image, and you also need to install the system-level Tesseract engine.Which Python libraries should I use for PDF processing?
Different libraries are recommended depending on the task: use pypdf for basic operations (merge/split/encrypt); use pdfplumber for text and table extraction; use reportlab to create new PDFs; use qpdf or pdftotext for command-line batch processing.
How do I fill PDF forms?
See the FORMS.md document. The skill supports filling PDF form fields using pdf-lib (JavaScript) or pypdf (Python); refer to the form handling guide for implementation details.
Does it support command-line PDF processing?
Yes, it supports various command-line tools. Common ones include: qpdf (merge/split/rotate/decrypt), pdftotext (text extraction), pdftk (multi-purpose tool), and pdfimages (image extraction). These tools are suitable for batch processing in scripts.