What problem does it solve? Editing .docx, .xlsx, and .pptx files programmatically usually requires Office installations or heavy libraries; this Skill lets an agent create, read, proofread, and modify Office documents through a single dependency-free CLI binary. ## Core Features & Use Cases - Layered editing model: L1 read/inspect (view, get, query, validate), L2 DOM operations (add, set, move, remove, batch), and L3 raw XML for anything the DOM layer cannot express. - Live preview and review: watch mode renders documents in a browser with click-to-select, and marks let humans review proposed edits before they are applied. - Specialized sub-skills: loadable rule sets for pitch decks, academic papers, financial models, data dashboards, and Morph-animated presentations. - Use Case: Ask the agent to build a Q4 report deck — it creates the .pptx, adds slides and styled shapes, validates the result, and previews it in the browser for your review. ## Quick Start Ask the agent to create a PowerPoint file named slides.pptx with a title slide reading "Q4 Report" and a text shape stating revenue grew 25%.