Office Docs

Extract text and tables from .docx and .xlsx using local scripts (no external deps).

rtgs2017 f803336 3 files · 11.0 KB Updated

File contents

Office Docs (docx + xlsx)

This skill provides lightweight, dependency-free extraction for Office documents using the scripts in tools/.

DOCX

Extract paragraphs and tables from a .docx file:

python tools/docx_extract.py "/path/to/file.docx" --output "/path/to/output.txt"

XLSX

Extract sheet data from a .xlsx file:

python tools/xlsx_extract.py "/path/to/file.xlsx" --output "/path/to/output.txt" --format csv

Notes

  • If --output points to a directory, each sheet is written to its own file.
  • If --output is a file and there are multiple sheets, the script prefixes each sheet with # Sheet: <name>.

rtgs2017/nagaagent/tree/main/apiserver/skills_templates/office-docs commit f803336029

Frequently asked questions

npx skillmds add rtgs2017/office-docs