Office Docs
Documentsoffice-docsOffice Docs is an Agent Skill for documents published in the RTGS2017/NagaAgent repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Extract text and tables from .docx and .xlsx using local scripts (no external deps).
QUICK START
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/RTGS2017/NagaAgent/blob/HEAD/apiserver/skills_templates/office-docs/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/office-docs, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
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
--outputpoints to a directory, each sheet is written to its own file. - If
--outputis a file and there are multiple sheets, the script prefixes each sheet with# Sheet: <name>.