Use when collaborating with humans to produce polished, editable, high-quality PPT decks across business, technical, research, education, product, and operations themes. Supports deck planning, slide archetype selection, diagram/chart/icon asset strategy, preview export, and validation for reusable PowerPoint deliverables.
Use when collaborating with humans to produce polished, editable, high-quality PPT decks across business, technical, research, education, product, and operations themes. Supports deck planning, slide archetype selection, diagram/chart/icon asset strategy, preview export, and validation for reusable PowerPoint deliverables.
Use when collaborating with humans to turn Markdown or lightly structured text into publishable Xiaohongshu image-card posts with explicit cover metadata, stable Chinese typography, browser-based pagination, and visual QA. Supports Markdown cleanup, cover planning, style-direction selection, page-density review, and iteration while keeping proven type-size ranges stable.
Use when collaborating with humans to turn Markdown, DOCX, and structured visual assets into polished Word deliverables with explicit Chinese/English typography, caption policy, asset routing, and mode-aware validation. Supports lightweight and refined workflows, DOCX-to-Markdown cleanup, Markdown-to-DOCX rebuild, typography profile selection, and editable Office-native or Python-generated visual routes.
用于“网页 demo 分段配音 + timeline 驱动录屏 + 后期合成”的 workspace 协作流程：先搭建一个可审计工作目录（cues/timeline/segment_audio/video/subtitles/final），再由人类 + Codex 迭代维护这些文件，按需只重跑局部步骤，最终合成高质量 MP4。适用于强调可复盘、可编辑、清晰度与字幕安全区可控的场景。
Use when collaborating with humans to produce publication-grade complex diagrams in editable PPT, especially for system architecture, dataflow, and user-journey visuals that require shape-level connector validation and reproducible outputs.