home / skills / openai / skills / doc

doc skill

/skills/.curated/doc

This skill helps you read, create, and validate DOCX layouts using python-docx and rendering tools to ensure professional formatting.

npx playbooks add skill openai/skills --skill doc

Review the files below or copy the command above to add this skill to your agents.

Files (6)
SKILL.md
2.9 KB
---
name: "doc"
description: "Use when the task involves reading, creating, or editing `.docx` documents, especially when formatting or layout fidelity matters; prefer `python-docx` plus the bundled `scripts/render_docx.py` for visual checks."
---


# DOCX Skill

## When to use
- Read or review DOCX content where layout matters (tables, diagrams, pagination).
- Create or edit DOCX files with professional formatting.
- Validate visual layout before delivery.

## Workflow
1. Prefer visual review (layout, tables, diagrams).
   - If `soffice` and `pdftoppm` are available, convert DOCX -> PDF -> PNGs.
   - Or use `scripts/render_docx.py` (requires `pdf2image` and Poppler).
   - If these tools are missing, install them or ask the user to review rendered pages locally.
2. Use `python-docx` for edits and structured creation (headings, styles, tables, lists).
3. After each meaningful change, re-render and inspect the pages.
4. If visual review is not possible, extract text with `python-docx` as a fallback and call out layout risk.
5. Keep intermediate outputs organized and clean up after final approval.

## Temp and output conventions
- Use `tmp/docs/` for intermediate files; delete when done.
- Write final artifacts under `output/doc/` when working in this repo.
- Keep filenames stable and descriptive.

## Dependencies (install if missing)
Prefer `uv` for dependency management.

Python packages:
```
uv pip install python-docx pdf2image
```
If `uv` is unavailable:
```
python3 -m pip install python-docx pdf2image
```
System tools (for rendering):
```
# macOS (Homebrew)
brew install libreoffice poppler

# Ubuntu/Debian
sudo apt-get install -y libreoffice poppler-utils
```

If installation isn't possible in this environment, tell the user which dependency is missing and how to install it locally.

## Environment
No required environment variables.

## Rendering commands
DOCX -> PDF:
```
soffice -env:UserInstallation=file:///tmp/lo_profile_$$ --headless --convert-to pdf --outdir $OUTDIR $INPUT_DOCX
```

PDF -> PNGs:
```
pdftoppm -png $OUTDIR/$BASENAME.pdf $OUTDIR/$BASENAME
```

Bundled helper:
```
python3 scripts/render_docx.py /path/to/file.docx --output_dir /tmp/docx_pages
```

## Quality expectations
- Deliver a client-ready document: consistent typography, spacing, margins, and clear hierarchy.
- Avoid formatting defects: clipped/overlapping text, broken tables, unreadable characters, or default-template styling.
- Charts, tables, and visuals must be legible in rendered pages with correct alignment.
- Use ASCII hyphens only. Avoid U+2011 (non-breaking hyphen) and other Unicode dashes.
- Citations and references must be human-readable; never leave tool tokens or placeholder strings.

## Final checks
- Re-render and inspect every page at 100% zoom before final delivery.
- Fix any spacing, alignment, or pagination issues and repeat the render loop.
- Confirm there are no leftovers (temp files, duplicate renders) unless the user asks to keep them.

Overview

This skill handles reading, creating, and editing .docx documents with an emphasis on formatting and layout fidelity. It favors python-docx for structured edits and a render-and-inspect workflow to verify visual output. Use the bundled render helper or system tools to convert DOCX to images for page-by-page review. Follow the render loop after meaningful changes to ensure a client-ready document.

How this skill works

I make structural edits with python-docx (headings, styles, tables, lists) and keep outputs organized in a temporary workspace. For visual verification I render DOCX -> PDF -> PNGs using libreoffice/pdftoppm or the included scripts/render_docx.py (requires pdf2image and Poppler). If rendering tools are unavailable, I extract text as a fallback and flag layout risk. After fixes, I re-render and inspect pages at 100% zoom before finalizing.

When to use it

  • When layout, pagination, tables, or diagrams must match a target visual
  • When producing client-ready .docx files with consistent typography and styles
  • When you need programmatic edits: bulk updates, templating, or structured content
  • When you must validate that charts, tables, and visuals are legible in rendered pages
  • When automated rendering and page-level inspection are required before delivery

Best practices

  • Prefer python-docx for edits; keep higher-level formatting in styles rather than inline tweaks
  • Render after each meaningful change and inspect at 100% zoom to catch clipping or layout breaks
  • Use tmp/docs/ for intermediate files and output/doc/ for final artifacts; keep filenames descriptive
  • Install libreoffice, poppler/pdftoppm and pdf2image for reliable rendering; report missing deps if unavailable
  • Avoid nonstandard Unicode hyphens and placeholder tokens; ensure citations are human-readable

Example use cases

  • Convert a filled template into a branded proposal with consistent styles and correct pagination
  • Programmatically update tables and figures across a multi-page report, then verify layout visually
  • Review and fix a DOCX with broken table wrapping or clipped images before client delivery
  • Extract text as a fallback when rendering is not possible, while noting layout risk to the requester
  • Produce final deliverables placed under output/doc/ and clean up tmp/docs/ after approval

FAQ

Which tools are required for full visual rendering?

LibreOffice (soffice) and Poppler (pdftoppm) plus the Python package pdf2image. Alternatively use the bundled scripts/render_docx.py which depends on pdf2image and Poppler.

What if I cannot install system tools in this environment?

I will extract text with python-docx as a fallback and explicitly call out layout and pagination risks, and provide installation instructions for local rendering.