From code-abyss
Processes .docx files: reads text via pandoc, creates new docs with docx-js, edits with OOXML library or redlining for tracked changes.
How this skill is triggered — by the user, by Claude, or both
Slash command
/code-abyss:processing-docx <file.docx | task><file.docx | task>This skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
`.docx` is a ZIP archive of XML and resources. Different tasks have different tools and workflows.
docx-js.mdooxml.mdooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsdooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsdooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsdooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsdooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsdooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsdooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsdooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsdooxml/schemas/ISO-IEC29500-4_2016/pml.xsdooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsdooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsdooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsdooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsdooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsdooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsdooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsdooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsdooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsd.docx is a ZIP archive of XML and resources. Different tasks have different tools and workflows.
| 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 |
pandoc --track-changes=all path-to-file.docx -o output.md
# --track-changes=accept/reject/all
docx-js.md (~500 lines). NEVER set range limits.Packer.toBuffer().ooxml.md (~600 lines). NEVER set range limits.python ooxml/scripts/unpack.py <office_file> <output_dir>python ooxml/scripts/pack.py <input_dir> <office_file>See redlining.md for full 6-step workflow with batching strategy and RSID preservation.
| 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 |
npx claudepluginhub telagod/code-abyss --plugin code-abyssCreates, edits, and analyzes .docx files using pandoc for text extraction, raw XML access for complex features, docx-js for new documents, and a Python library for editing with redlining support.
Creates, edits, and analyzes .docx files using docx-js for new documents, pandoc for text extraction, Python for OOXML unpacking and editing.