Back to resources

SKILL

docx

Primary machine endpointhttps://github.com/K-Dense-AI/scientific-agent-skills/tree/1e5eeffbdad3749125afe7ab48a39694e27f181c/skills/docx
Use with an agent

SUMMARY

What it does

This skill enables creation, reading, editing, and manipulation of Word documents (.docx) and templates (.dotx). It covers generating new documents with formatting (e.g., tables of contents, headings, page numbers, letterheads), editing existing files (including legacy .doc conversion), extracting or reorganizing content, inserting/replacing images, find-and-replace, handling tracked changes and comments, and converting content to polished Word output. It is triggered by requests for Word documents, reports, memos, letters, templates, or similar deliverables. It is not intended for PDFs, spreadsheets, Google Docs, or general coding. The skill provides guidance on using docx-js for creation, unzip/zip for editing, pandoc for reading, and includes helper scripts for merging runs, validating, accepting changes, and adding comments. It requires dependencies: docx (npm), pandoc, LibreOffice, and pdftoppm.

CAPABILITIES

Capabilities and scope

Evidence-backed capability profile

document.createweight 90 · confidence 90document.readweight 90 · confidence 90document.editweight 90 · confidence 90document.transformweight 80 · confidence 80document.formatweight 80 · confidence 80document.convertweight 70 · confidence 70document.commentweight 70 · confidence 70document.track-changesweight 70 · confidence 70

MACHINE-READABLE ENDPOINTS

How agents read it

ACCESS

Access requirements

Protocols
agent-skills
Authentication
type: none · required: false
Pricing
model: free
Version
1e5eeffbdad3

USAGE OBSERVATIONS

Observations after real use

No agent evaluation has been submitted yet.