Processing docx

Skill telagod/code-abyss/skills/processing-docx

Processes Word document files (.docx). Creates, edits, annotates, tracks revisions, analyzes OOXML structure, and preserves formatting for contracts, policies, academic papers, and business documents. Use when working with .docx files or Word documents. Do NOT use for PDFs, spreadsheets, presentations, or plain text files.From its SKILL.md

Install

npx -y skills add telagod/code-abyss --skill processing-docx

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

SKILL.md

2.6 KB, 581 tokens by cl100k_base, as published. Nobody here has run it

DOCX Processing

.docx is a ZIP archive of XML and resources. Different tasks have different tools and workflows.

Workflow Decision

Intent	Workflow	Reference
Read/analyze text only	pandoc → markdown	raw-xml-access.md
Read structure, comments, media, formatting	unpack → raw XML	raw-xml-access.md
Create new document	docx-js (JS/TS)	docx-js.md
Edit own document, simple changes	Document library (Python)	ooxml.md
Edit someone else's document	Redlining (tracked changes)	redlining.md
Legal / academic / business / gov docs	Redlining — REQUIRED	redlining.md
Visual analysis	soffice → PDF → pdftoppm	raw-xml-access.md

Text Extraction (Quick)

pandoc --track-changes=all path-to-file.docx -o output.md
# --track-changes=accept/reject/all

Create New Document

MANDATORY — READ ENTIRE FILE: docx-js.md (~500 lines). NEVER set range limits.
Create JS/TS file using Document, Paragraph, TextRun components.
Export with Packer.toBuffer().

Edit Existing Document (Own, Simple)

MANDATORY — READ ENTIRE FILE: ooxml.md (~600 lines). NEVER set range limits.
python ooxml/scripts/unpack.py <office_file> <output_dir>
Run Python script using Document library.
python ooxml/scripts/pack.py <input_dir> <office_file>

Edit Someone Else's Document → Redlining

See redlining.md for full 6-step workflow with batching strategy and RSID preservation.

Code Style

Write concise code, no verbose variable names, no unnecessary print statements.

Dependencies

Package	Install	Purpose
pandoc	`apt install pandoc`	Text extraction
docx	`npm i -g docx`	Create new docs
LibreOffice	`apt install libreoffice`	PDF conversion
Poppler	`apt install poppler-utils`	`pdftoppm` for images
defusedxml	`pip install defusedxml`	Secure XML parsing

What ships with it: 59 files

1151.4 KB alongside SKILL.md, 11 of them executable

ooxml/

docx-js.md16.1 KB
ooxml.md22.8 KB

19 more files not listed here. See all 59 in the repository.

Gives 0 of the 12 instructions most pdf office docs skills give in 581 tokens

Counted across 569 of the 585 authors here whose files we hold, read 2026-09-06

Ensure every slide fits inside one viewportin 20 of 569, across 11 files
Check for product marketing context firstin 15 of 569, across 5 files
Ask for the minimum neededin 15 of 569, across 5 files
Set the API key environment variablein 15 of 569, across 10 files
Support keyboard and touch navigationin 14 of 569, across 5 files
Match the buyer stagein 13 of 569, across 3 files
Split overflowing content into multiple slidesin 12 of 569, across 3 files
Set page size explicitly for consistent resultsin 12 of 569, across 5 files
Convert documents to markdown using pandocin 12 of 569, across 6 files
Read STYLE_PRESETS.md before generatingin 12 of 569, across 7 files
Send multipart POST requests to the APIin 12 of 569, across 7 files
Use smart quotes for new contentin 11 of 569, across 4 files

Said here and by no other author read

Read the entire docx-js file

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.