Guides agents through reading, creating, editing, and converting PDF, Excel, Word, and PowerPoint office documents.
- What it does
- This skill is a reference guide for manipulating office documents in PDF, XLSX, DOCX, and PPTX formats. It lists recommended tools and packages for each format, describes common operations such as merging, splitting, extracting tables, and OCR, and explains internal file structures like the XML-in-ZIP layout of Office files. It also covers Excel formula conventions, Word tracked changes, PowerPoint design principles, and format conversion paths.
- When to use it
- Use it when a task involves reading, creating, editing, merging, converting, or extracting content from PDF, Excel, Word, or PowerPoint files. It is also relevant when choosing libraries or command-line tools for office document work.
- Requirements
- Instructions only; no scripts are shipped. The guide references external tools and packages that would need to be installed separately, including Python libraries (pypdf, pdfplumber, openpyxl, python-docx, python-pptx), JavaScript packages (docx, pptxgenjs), and command-line tools (pandoc, qpdf, pdftotext, LibreOffice, pytesseract, pdf2image).
Document Processing Guide
Work with office documents: PDF, Excel, Word, and PowerPoint.
Format Overview
Key concept: XLSX, DOCX, and PPTX are all ZIP archives containing XML files. You can unzip them to access raw content.
PDF Processing
PDF Tools
Common Operations
Excel Processing
Excel Tools
Critical Rule: Use Formulas
Financial Model Standards
Common Formula Errors
Word Processing
Word Tools
Document Structure
Tracked Changes (Redlining)
Key concept: For professional/legal documents, use tracked changes XML rather than replacing text directly.
PowerPoint Processing
PowerPoint Tools
Slide Structure
Design Principles
Converting Between Formats
Best Practices
Common Packages
