原稿の主張と図の役割を頁ごとに整理し、選んだ書式を全頁へ引き継ぐ画像スライドと話者ノートを作る。
The English summary is being prepared. Showing the original description.
Design and generate polished, on-brand presentation decks as clean 1920×1080 HTML — with real charts, tables, and AI or stock imagery. Use whenever someone wants to create, design, or improve a presentation, slide deck, pitch deck, investor or sales deck, keynote, training or teaching deck, PowerPoint (PPTX), Google Slides, or a data-heavy report, and cares about design quality. The visual style is derived from the brief, never picked from a theme or template menu.
The English summary is being prepared. Showing the original description.
Review the instructions the agent will receive before you install.
A presentation-design engine. Give it a brief — what the deck is about, plus how it should look in any form (a few words, "like stripe.com", a brand URL, or a moodboard) — and it derives a bespoke visual style for that deck, plans the slide sequence, has the host LLM fill fixed slide templates, and renders deterministic 1920×1080 HTML slides with real data-viz, tables, and imagery.
Style is discovered, not chosen. There is no theme menu and no preset to pick: every deck gets its own tokens, slide templates, and look, generated from the brief.
AI images are optional. Hero and background imagery is generated through
fal.ai — set a FAL_KEY to turn it on, and it produces consistent,
on-brand visuals across the whole deck (and skips the usual AI-image fails). Without a key
the skill still works end to end; it just renders the deck without AI imagery. No key is
required to install or run it.
Use when the user wants to create, design, or improve any presentation: a pitch or investor deck, a sales or strategy deck, a keynote, a training or teaching deck, a data or report deck, or generally "make me some slides / a PowerPoint / a deck" — and they care about it looking designed and on-brand.
npm installSee README.md for the pipeline and quality gates, docs/INTEGRATION.md for the engine
API, and docs/SKILL-FORMAT.md for the package format.
Design rules — readable type, no empty bands, no logos or trademarks, no invented numbers — are enforced by code gates, not by prompt wording alone.
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
原稿の主張と図の役割を頁ごとに整理し、選んだ書式を全頁へ引き継ぐ画像スライドと話者ノートを作る。
The English summary is being prepared. Showing the original description.
Convert literature reviews, paper folders, thesis drafts, journal-style reports, or research outlines into rigorous academic slide decks and review artifacts. Use when Codex must create, rebuild, or polish PPTX presentations from scholarly sources while preserving academic logic, citation-aware image/formula handling, editable layouts, figure explanations, template fidelity, and export-based visual QA.
The English summary is being prepared. Showing the original description.
既存PPTXの書式・配置を抽出し、planとnative編集操作からPowerPointを生成・検査する。
The English summary is being prepared. Showing the original description.
読者と目的から構成・版式を決め、確認を挟みながら、編集できる図形と文字のPPTXにする。
The English summary is being prepared. Showing the original description.
全流程AI制作PPT演示文稿技能,克制专业、风格可选 A/B/C 三档(Aham UI v6.1 · Office 轨 · PPT)。 当用户说"帮我做PPT""做演示文稿""做一个汇报""根据这份资料做PPT" "做客户方案PPT""制作幻灯片"时立即触发。即使只有一句话需求也触发。 八阶段模块化流程:规范加载→材料解析→论点提炼→叙事骨架→大纲版式→样稿确认→逐页设计→质检交付。 内置能力自适应教练机制,无论用户专业水平高低,均引导至及格以上输出。 注意:本技能用于 PowerPoint / pptx 输出;SVG/HTML 版本见 ppt-svg 技能。
The English summary is being prepared. Showing the original description.
原典のReact scene kitを実scaffoldし、安定layoutIdの共通canvasでentityが移動・morphする日本語ブラウザ資料を作る。
The English summary is being prepared. Showing the original description.