Traction scoreGitHub stars can be faked, so popularity alone can be misleading. Traction Score looks for broader signs of recent attention, adoption, and active maintenance.
This skill converts screenshots, scanned documents, and image-based presentations into editable .pptx files. It allows presentation designers and analysts to recover the structure of visual slides, transforming flat images back into manipulatable objects.
The process preserves speaker notes when provided, making it a utility for reconstructing legacy reports or updating slides from static captures rather than authoring new content from scratch.
Compatible AgentsThe repository documents support for these agents. The skills may also work with other agents that can load SKILL.md files, but they may need some setup or small changes.
Follow the documented setup, then try a first task.
Install through a Codex agent session
Installs: Installs the image-to-editable-ppt skill from its GitHub repository. · Codex
Before you start
Codex Full Access is recommended because approval modes may interrupt or block OCR, image generation/editing, file operations, subagent dispatch, and long polling.
Use gpt-5.5 or later when possible; results are not guaranteed on models below gpt-5.5.
Enter the following text in the Codex agent session; it is not a terminal command.
Install the image-to-editable-ppt skill from https://github.com/ningzimu/image-to-editable-ppt-skill
After installation, select `image-to-editable-ppt` using the agent's explicit skill-selection syntax; in Codex, use `$image-to-editable-ppt`.
Installs: Installs the image-to-editable-ppt skill folder from a GitHub Releases archive. · Codex
Before you start
Ability to download and extract the documented GitHub Releases ZIP archive
Codex Full Access is recommended because approval modes may interrupt or block OCR, image generation/editing, file operations, subagent dispatch, and long polling.
Use gpt-5.5 or later when possible; results are not guaranteed on models below gpt-5.5.
Download `image-to-editable-ppt-skill-v*.zip` from the repository's GitHub Releases page.
Extract the archive and place its included `image-to-editable-ppt` folder at `~/.codex/skills/image-to-editable-ppt`.
Installs: Installs the image-to-editable-ppt skill by linking its folder from a local repository checkout. · Codex
Before you start
A local checkout of the image-to-editable-ppt-skill repository
Codex Full Access is recommended because approval modes may interrupt or block OCR, image generation/editing, file operations, subagent dispatch, and long polling.
Use gpt-5.5 or later when possible; results are not guaranteed on models below gpt-5.5.
Platform: A system providing the documented Bash shell, `mkdir`, symbolic links, and `~/.codex/skills` path convention
In a terminal, replace `/path/to/image-to-editable-ppt-skill` with the path to the local repository checkout, while keeping the remainder of the source and destination paths unchanged; then run this complete command block.
One attached slide image, or a local image path replacing `/path/to/slide.png`
If the workflow asks for an OCR token, either provide a Baidu PaddleOCR-VL Access Token for improved text reconstruction or continue with the documented lower-quality offline detector
Use the image-to-editable-ppt skill to rebuild the attached single-slide image as an object-level editable PowerPoint `.pptx`, recovering editable text and simple shapes and keeping positioned visual assets separate where practical. If attaching the image is not convenient, use `/path/to/slide.png` after replacing it with the actual local image path.
Claude
Codex
OpenClaw
Hermes