ningzimu/image-to-editable-ppt-skill

★ 16PythonAudience · pm founderComplexity · 3/5LicenseSetup · moderate

Mindmap

mindmap
  root((ppt-skill))
    Inputs
      Slide images
      Multi-page PDF
      Image-based PPTX
    Output
      Editable PPTX
    Architecture
      Main agent
      Page sub-agents
      Quality checker
    What transfers
      Text boxes
      Simple shapes
      Speaker notes
    Limitations
      No pixel-perfect
      Complex graphics as images

mindmap root((ppt-skill)) Inputs Slide images Multi-page PDF Image-based PPTX Output Editable PPTX Architecture Main agent Page sub-agents Quality checker What transfers Text boxes Simple shapes Speaker notes Limitations No pixel-perfect Complex graphics as images

Click or tap to explore — scroll the page freely

Things people build with this

USE CASE 1

Convert a PDF export of a client presentation back into an editable .pptx so you can update content without retyping every slide.

USE CASE 2

Turn a folder of slide images from a conference into an editable PowerPoint you can remix and repurpose.

USE CASE 3

Extract speaker notes from an image-based .pptx while recovering the text and shapes as editable elements.

Tech stack

PythonOpenAI Codex API

Getting it running

Difficulty · moderate Time to first run · 30min

Requires a Codex Plus or Max membership, not compatible with standard ChatGPT accounts.

Use freely for any purpose including commercial projects, as long as you keep the copyright notice.

In plain English

This is a skill for Codex (an AI coding assistant from OpenAI) that converts slide images, multi-page PDFs, and image-based PowerPoint files into editable .pptx files. The goal is to take a presentation that exists only as images and recover as much editable structure as possible: text becomes real text boxes you can edit, simple shapes become native PowerPoint shapes, and complex visual elements are saved as separate image assets. The skill uses a multi-agent architecture. A main agent breaks the input into individual pages and assigns each page to its own sub-agent. These page sub-agents work in parallel to reconstruct the slides, which speeds up processing for presentations with many pages. The main agent then checks the quality of each page, schedules repairs if needed, and assembles the final .pptx file. No third-party OCR service is required, the reconstruction is done visually using the models available within Codex. The supported inputs are a single image, a collection of multiple images, a multi-page PDF, or an image-based PowerPoint file. In all cases the output is a .pptx file with the original page order preserved. If the input was a .pptx file, speaker notes from the original slides are copied over unchanged. For complex visual elements such as photographs, illustrations, or decorative graphics, the tool saves them as independent image assets rather than attempting to recreate them as editable shapes. Fully pixel-perfect reproduction is not guaranteed, some text and elements may shift slightly in position. This skill is designed specifically for Codex and has been tested with Codex Plus and Max memberships. It is not intended for generating new PowerPoint content from scratch. The project is written in Python, documented primarily in Chinese with an English README also available, and is licensed under MIT.

Copy-paste prompts

Prompt 1

I'm using the image-to-editable-ppt Codex skill. Help me write a Codex prompt that converts a 20-slide PDF pitch deck into an editable .pptx.

Prompt 2

The skill couldn't reconstruct a complex chart on slide 5. Suggest a prompt to ask the sub-agent to save it as an image asset instead.

Prompt 3

I want to extend this Codex skill to also extract tables from slides into a separate Excel file. Outline the extra agent step needed.

Open on GitHub → Explain another repo

← ningzimu on gitmyhub — every repo by this author, as a profile.

Verify against the repo before relying on details.