codex-visio-paper-figure-skill
Redraws a paper figure as a native Visio .vsdx of editable shapes and text, then exports PNG, SVG, PDF and PPTX from it.
- 1,184 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- PowerShell scripts run with the execution policy bypassed and drive Visio and PowerPoint through COM.
- The skill rewrites working files; the README requires a backup of the original `.vsdx`.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/codex-visio-paper-figure-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- PowerShell scripts run with the execution policy bypassed and drive Visio and PowerPoint through COM.
- The skill rewrites working files; the README requires a backup of the original `.vsdx`.
This is third-party code. Review the repository files before installing.
What it does
A Codex skill that rebuilds an image, screenshot or generated figure as an editable Microsoft Visio file. The result is assembled from native shapes, text, lines, groups and styles rather than embedding the picture: the finished `.vsdx` must not contain a large source PNG or JPG. For complex multi-panel diagrams, panel boundaries are calibrated first and elements are drawn in panel-local 0 to 1 coordinates; the `RectRel`, `TextRel`, `OvalRel` and `LineRel` helpers with `Assert-RelBox` and `Assert-RelPoint` checks raise an error when an element leaves its panel. PNG, SVG, PDF and PPTX are exported from one saved `.vsdx`, so formats stay consistent.
Who it is for. Paper authors on Windows with Visio who need editable model, architecture and flow diagrams instead of pictures.
Good fit when
- An AI-generated model diagram must become a file where each block is editable.
- A paper figure must be restored from a PNG or screenshot.
- An existing `.vsdx` needs recoloring with consistent fonts and line weights.
- You must check whether a `.vsdx` merely embeds one whole picture.
- SVG, PDF or PPTX is exported from the finished file for a journal or talk.
Not a fit when
- Windows and Microsoft Visio are unavailable: full redrawing relies on Visio COM.
- You need charts with real data: the README advises building them with a script.
- Inserting a picture into Visio or treating it as a raster is enough.
Example request
Use visio-image-rebuilder to rebuild this picture as `model.vsdx` from native shapes and export SVG, PDF and PPTX.Limitations
Full operation needs Windows, Microsoft Visio and PowerShell, plus PowerPoint for PPTX export. Without Visio only `.vsdx` package inspection and limited XML edits are possible. The author uses only Visio, so Draw.io and other editors need the interface adapted by you. Scripts run with `-ExecutionPolicy Bypass` and drive Visio and PowerPoint through COM. Best suited to model, architecture and flow diagrams.
How to disable. Delete the `visio-image-rebuilder` folder from the Codex skills directory `%USERPROFILE%\.codex\skills\` and restart Codex. Created `.vsdx` files and exports stay as ordinary files.
FAQ
How does the result differ from embedding a picture?
The `.vsdx` keeps native shapes, text, groups and arrows that can be edited individually. A whole source picture in the file counts as a failure.
Which formats can I get?
PNG, SVG, PDF and PPTX, all exported from one saved `.vsdx`.
How are shifted blocks avoided?
Panels are calibrated first, then elements are drawn in local coordinates; checks raise an error when an element leaves its panel.
Does it work without Visio?
Partly: you can inspect `.vsdx` structure and make limited XML edits, but full redrawing needs Visio.
What is planned for the next version?
More ready helpers for cubes, heatmaps, graphs and mini charts, plus reading image size and exporting a shape inventory.
Discussion
No questions or reviews yet.
Related
SkillsA Codex skill that rebuilds a slide from an image or PDF into PowerPoint where text, tables and arrows stay editable objects.
Image to Editable PPT
Image to Editable PPT Skill
A Codex skill that rebuilds slides from images, PDFs and image-based PPTX files into an editable PowerPoint deck
A set of Codex skills for research work: image to editable Office shapes and VBA, and paper to a PPTX deck
A Codex plugin that redraws a scientific figure from a reference on the live draw.io canvas step by step, then validates and exports the file
A skill that turns an academic PDF figure into a self-contained SVG and an editable PPTX, then checks it pixel by pixel.
Skill turns the agent into a deck producer: brief, storyboard, slide posters, QA and a PDF or editable PPTX.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| codex-visio-paper-figure-skill (this card) | no | 1,184 | |
| drawio-skill | no | 10,743 | makes editable draw.io diagrams from text and code; this skill rebuilds a figure from an image in Visio |
| Paper Figure to Figma | no | 159 | redraws a paper figure into Figma or PowerPoint; here the result is a native Visio file |
README in short
Version 1.1.1 added panel calibration and overlap guards, 1.1 added multi-format export. Acceptance requires editable text and shapes with no whole source picture left in the file.