Menu

Individual skill

codex-ppt

0upvotes

Create polished 16:9 presentation decks from a topic, outline, report, or rough notes in two modes: image mode with fully AI-rendered slide images, or editable PPTX mode that first generates approved slide images and then reconstructs each slide through per-slide subagents into editable PowerPoint text boxes and movable visual layers. Includes 10 curated aesthetic presets (Swiss Klein Blue, Monocle Magazine, Apple Keynote Bento, Kenya Hara Zen, Memphis Pop, Neo-Brutalist Zine, Dark Emerald Roadshow, Industrial Cobalt HUD, Clinical Ice Blue, Heritage Parchment Gold) and 12 layout archetypes. Use when the user asks to 自动做PPT, 做PPT, 生成PPT, 创赛PPT, 路演PPT, 指定PPT风格, make slides, create a slide deck, create a fully AI-generated image-based deck, or produce an editable PowerPoint deck.

SKILL.md

Read pinned source

Source commit 2a132f19cbbd0308d71be0f0fefe215ce294100d

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
No
Repository scan complete
No
Skill scan complete
No
Observed behavior
Not checked yet
Last checked
Nov 6, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
53
Repository last updated
Oct 26, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

# Codex PPT

Create a complete presentation as ordered 16:9 slide images, then either compile them into one PDF or use them as the approved visual target for an editable PPTX reconstruction pass. The skill is for deck-making where planning, visual consistency, full-page AI generation, quality review, and delivery format all matter.

## Output Modes

- `image` mode: generate approved slide images. This is the default unless the user asks for editable PowerPoint output; compile a PDF as the standard package unless the user only wants image files.
- `editable-pptx` mode: generate and QA the slide images first, then launch one per-slide reconstruction subagent for each approved image, merge the resulting visual layers and text layers, and build a final editable `.pptx`.

## Default Assumptions

- Output mode defaults to `image`.
- If the user asks for editable PPT, editable PowerPoint, selectable text, movable objects, or "图片转可编辑", use `editable-pptx`.
- In `image` mode, output is the ordered slide image set; compile a PDF unless the user asks to stop at images.
Back to top