Agent skill · software engineering · claude-office-skills
pdf-to-docx
Convert PDF files to editable Word documents using pdf2docx
Why this skill is useful
Adds specific commands and advanced options for using pdf2docx that the AI wouldn't reliably generate on its own.
What it needs
Requires pdf2docx, pdf2image, pytesseract installed locally. About 5k tokens when loaded. Last updated 2026-01-31. 363 stars on the source repository.
What this skill does
PDF to Word Skill Overview This skill enables conversion from PDF to editable Word documents using pdf2docx - a Python library that preserves layout, tables, images, and text formatting. Unlike OCR-based solutions, pdf2docx extracts native PDF content for accurate conversion. How to Use 1. Provide the PDF file you want to convert 2. Optionally specify pages or conversion options 3. I'll convert it to an editable Word document Example prompts: "Convert this PDF report to an editable Word document" "Turn pages 1-5 of this PDF into Word format" "Extract this scanned document as editable text" "Convert this PDF contract to Word for editing" Domain Knowledge pdf2docx Fundamentals Conversion Options Advanced Options Handling Different PDF Types Native PDFs (Text-based) Scanned PDFs (Image-based) Python Integration Batch Conversion Parsing PDF Structure Best Practices 1. Check PDF Type: Native PDFs convert better than scanned 2. Preview First: Test with a few pages before full conversion 3. Handle Tables: Complex tables may need manual adjustment 4. Image Quality: Images are extracted at original resolution 5. Font Handling: Some fonts may substitute to system defaults Common Patterns Convert with Progress Extract Tables Only Examples Example 1: Contract Conversion Example 2: Selective Page Conversion Example 3: PDF Report to Editable Template Example 4: Bulk Invoice Processing Limitations Scanned PDFs require OCR preprocessing Complex layouts may not convert perfectly Some fonts may not be available Watermarks are included in conversion Protected/encrypted PDFs need password Installation Resources GitHub Repository Documentation PyPI Package
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills claude-office-skills/pdf-to-docx