docx-processing-openai

Installation
SKILL.md

DOCX reading, creation, and review guidance

Reading DOCXs

  • Use soffice -env:UserInstallation=file:///tmp/lo_profile_$$ --headless --convert-to pdf --outdir $OUTDIR $INPUT_DOCX to convert DOCXs to PDFs.
    • The -env:UserInstallation=file:///tmp/lo_profile_$$ flag is important. Otherwise, it will time out.
  • Then Convert the PDF to page images so you can visually inspect the result:
    • pdftoppm -png $OUTDIR/$BASENAME.pdf $OUTDIR/$BASENAME
  • Then open the PNGs and read the images.
  • Only do python printing as a last resort because you will miss important details with text extraction (e.g. figures, tables, diagrams).

Primary tooling for creating DOCXs

  • Create and edit DOCX files with python-docx. Use it to control structure, styles, tables, and lists. Install it with pip install python-docx if it's not already installed.
  • After every meaningful batch of edits—new sections, layout tweaks, styling changes—render the DOCX to PDF:
    • soffice -env:UserInstallation=file:///tmp/lo_profile_$$ --headless --convert-to pdf --outdir $OUTDIR $INPUT_DOCX
  • Convert the PDF to page images so you can visually inspect the result:
    • pdftoppm -png $OUTDIR/$BASENAME.pdf $OUTDIR/$BASENAME
  • Inspect every PNG before moving on. If you see any defect, fix the DOCX and repeat the render → inspect loop until all pages look perfect.
Installs
2
First Seen
Feb 11, 2026
Security Audits
docx-processing-openai — swn94/awesome-legal-skills