Working with office documents like PDFs, Excel spreadsheets, Word files, and PowerPoint slides is a common task. This guide helps you process these files using code. You can extract text, merge documents, and convert formats easily.
Each document type has its own tools and methods. For example, you can unzip XLSX files to see the XML inside. PDFs can be read with pypdf or pdfplumber. Excel files work best with pandas or openpyxl.
Word and PowerPoint files also have special tools like python-docx and pptxgenjs. You can even work with tracked changes in legal documents. The guide covers common operations for all major office formats.
Global
mkdir -p ~/.claude/skills/document-processingProject
mkdir -p .claude/skills/document-processingLark Sheetslarksuite/cli
Create, edit, and manage Lark spreadsheets with simple commands
Lark Slideslarksuite/cli
Create and edit Lark slides easily Manage pages add charts use templates
Lark Markdownlarksuite/cli
Easily create, edit, diff, and patch Markdown files in cloud storage
Pptxanthropics/skills
Create, edit, and read any presentation file with ease and style
Pdfanthropics/skills
Read, edit, merge, split, and protect PDF files with simple Python code
Docxanthropics/skills
Build, edit, and polish Word documents automatically with code and scripts
Xlsxanthropics/skills
Create, edit, and fix spreadsheet files with zero errors and professional formatting
Slideshowheygen-com/hyperframes
Create an interactive slideshow with hotspots, fragment reveals, and branching paths