Use Okou generation pipelines for images, presentations, websites, reports, and designs.
Extract a style prompt from a reference picture, show the user pictures made from it, revise until they approve, then save it as their template. Use when a user uploads an image style to reuse, asks to extract a prompt from a picture, wants their own image…
Decide what an uploaded file is — a deck, a Word document, a PDF document, or artwork — and hand it to the template-extraction guide that matches. Use when asked to extract a template from a deck or document, turn a PDF into a Word template, save an image…
Extract and publish a reusable HTML presentation template from PPTX, PPT, PDF, image decks, or page screenshots. Preserve the source's typography, layouts, backgrounds, decoration, and brand framing as editable structures and reusable assets.
Extract a template skill from a Word document for filling slots, reusing structure and expression, or applying its visual style. Use when asked to extract a Word template, build a reference.docx, apply a company template to Markdown, or set up --reference-doc.
Extract a template skill from a PDF document for filling slots, reusing structure and expression, or applying its visual style. Use when asked to extract a PDF template or its styles, turn a PDF into a Word template, or analyse a PDF's layout.
Google Gemini image generation (Nano Banana) via the Gemini API. Use when user mentions "Nano Banana", "Gemini image generation", "gemini-3-pro-image", "gemini-3.1-flash-image", or wants to generate/edit images with Google's native image model.
Generate or edit docx, xlsx and PDF deliverables — Word documents, spreadsheets, reports — including editing a file the user uploaded.