
Turns entire documents into PowerPoint decks where every slide is a full-frame generated image. You feed it articles, reports, or outlines, it drafts a deck structure, generates one sample slide for approval, then dispatches parallel subagents to render the rest at 16:9. The orchestration is rigid by design: hard gates before sample approval, mandatory subagent dispatch after approval, and strict backend locking so you don't accidentally mix generation methods mid-deck. Best when you want a visually cohesive presentation and don't need every text box editable. Skip it if you need conventional slide layouts or plan to rearrange elements later.
$ npx -y skills add ningzimu/codex-ppt-skill --skill codex-ppt --agent claude-codeInstalls into .claude/skills of the current project.
This skill creates image-based PowerPoint decks from source material. Each slide is a complete 16:9 generated image. Final images are assembled into .pptx with scripts/assemble_ppt.py.
Use this when the user wants a visually unified presentation and accepts full-slide image pages. Do not use it when every textbox, chart, or shape must remain separately editable.
Prefer the built-in image generation/editing tool. Use scripts/image_gen.py only when the built-in backend is unavailable, lacks a required capability, or the user explicitly asks for API/CLI mode.
Sponsors