image-to-editable-ppt-skill
Codex skill for converting slide images, PDFs, and image-based PPTX files into editable PowerPoint decks.
The image-to-editable-ppt-skill is a Codex AI skill that transforms slide screenshots, multi-page PDFs, and image-based PowerPoint files into fully editable PPTX decks. It reconstructs each page by converting readable text into native text boxes, simple shapes into PowerPoint objects, and complex visual elements into separate image assets with source tracking. The skill employs a multi-agent workflow with page workers for parallel processing, OCR-driven text positioning via PaddleOCR-VL, and intelligent image generation using built-in Codex tools or fallback APIs. Best suited for ChatGPT Pro users due to token-intensive iterative refinement cycles that self-check and correct each reconstructed page.
Key Features
Use Cases
- 01Converting screenshot-based presentation slides into editable PowerPoint files for rebranding or updates
- 02Transforming legacy PDF slide decks into modern PPTX format for easier content modification
- 03Reconstructing image-only PowerPoint files to regain text and shape editability
- 04Creating editable versions of single-page visual designs while preserving layout and typography
- 05Batch processing multiple slide images into a unified multi-page editable presentation
- 06Extracting and separating complex visual assets from slides for independent editing
Related Skills
View moresuperpowers
An agentic skills framework & software development methodology that works.
skills
Skills for Real Engineers. Straight from my .agents directory.
skills
Public repository for Agent Skills
ponytail
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
image-to-editable-ppt-skill — FAQ
What is the image-to-editable-ppt-skill?+
It's a Codex AI skill that converts slide images, PDFs, and image-based PowerPoint files into editable PPTX presentations by reconstructing text, shapes, and visual assets. It uses multi-agent collaboration and OCR to accurately restore page structure and formatting.
How do I install the image-to-editable-ppt skill in Codex?+
Tell Codex to install the skill from the GitHub repository at https://github.com/ningzimu/image-to-editable-ppt-skill. The AI will automatically install the editppt CLI tool and dependencies during first execution.
Which AI clients support this skill?+
This skill is designed for Codex with full access permissions. Other agents supporting skill loading, file I/O, CLI execution, and page worker/subagent dispatch may work, but Codex is the primary platform.
Do I need API keys or tokens to use this skill?+
For optimal text restoration, you should obtain a free Baidu AI Studio Access Token for PaddleOCR-VL from https://aistudio.baidu.com/account/accessToken. The skill works without it but uses lower-quality offline text detection. Image generation uses Codex built-in tools; third-party API fallback is optional.
Is the image-to-editable-ppt-skill free to use?+
The skill itself is open-source under the MIT license. However, it consumes significant AI tokens during multi-round iterative reconstruction, recommended for ChatGPT Pro users; Plus users may exhaust their usage quota on a 10-page deck.
How long does it take to convert a presentation?+
Single-page conversions may take over 10 minutes. Multi-page decks are processed in parallel by page workers, but the iterative self-check and correction cycles make this a token-intensive, time-consuming process not suitable for simple editing needs.
How do I install image-to-editable-ppt-skill?+
Open the source repository on GitHub and follow its README. image-to-editable-ppt-skill is a skill — MCP Agents Market links you directly to the official repo.
Is image-to-editable-ppt-skill free?+
image-to-editable-ppt-skill is an open-source project hosted on GitHub. Check the repository for its license and any usage requirements.