Document Processing

Handles the full spectrum of office document work: extracting text and tables from PDFs, merging and splitting files, OCR for scanned documents, creating Word docs and PowerPoint decks from scratch, and manipulating Excel spreadsheets. Built on solid tools like pdfplumber for PDFs, pandoc for Word conversions, and pandas for Excel analysis. The OOXML unpacking approach for deep Word and PowerPoint edits is clever, letting you modify the raw XML when higher-level libraries fall short. Covers both Python and JavaScript implementations depending on the task. If you're building document workflows or need to automate report generation, this gives you working code for most common scenarios without hunting through multiple library docs.

Install to Claude Code

npx -y skills add dirnbauer/webconsulting-skills --skill document-processing --agent claude-code