Read, extract, merge, split, and edit PDFs using Python libraries.
npx skills add https://github.com/binfen1/my-skills --skill pdf-binfen1
Please help me install this Agent Skill. Skill: pdf Source: https://github.com/binfen1/my-skills/tree/main/claude-code/pdf Command: npx skills add https://github.com/binfen1/my-skills --skill pdf-binfen1
This PDF processing skill consolidates a wide range of common PDF tasks—reading, text extraction, merging, splitting, rotation, watermarking, form handling, encryption, decryption, image extraction, and OCR—into a single, automated workflow to save time and reduce manual effort.
Ask me to process a PDF, for example to extract text from document.pdf.
High-intent search queries and answers about installing and using this skill.
You can extract text and tables from a PDF by using pdfplumber to parse content and convert it into usable data formats, streamlining automated reading and data extraction workflows.
Yes, you can merge multiple PDFs, split pages, and rotate items using pypdf. This allows you to consolidate documents or extract specific sections for secure and organized sharing.
You can fill both fillable and non-fillable PDF forms, then apply encryption to the document to protect sensitive information. This is achieved through deterministic operations using Python libraries like pypdf.
PDF processing supports OCR to make scanned documents searchable and image extraction to retrieve embedded graphics. It uses pdf2image and related libraries to perform these automated extraction tasks.
The best way to batch process PDFs for watermarking is using on-demand scripts that apply watermarks deterministically. This automates secure sharing across multiple administrative or legal documents efficiently.
davidbeglenboyleExtract text and tables from PDFs into CSV or JSON using Python libraries.
robit-manExtract text, tables, and images from PDFs with OCR support.
manaflow-aiAutomate cmux topology control for windows, workspaces, panes, and surfaces.
phuhao00Extract text, tables, and images from PDFs using OCR.
