Paper Figure to Figma skill
paper-figure-to-figma
Skill that redraws a paper figure as editable Figma or PowerPoint, keeping labels as text and shapes as vectors.
- 161 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent writes layers into a Figma file or creates a PowerPoint file, and the figure and links go to the selected services.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/paper-figure-to-figmaDetects 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.
- The agent writes layers into a Figma file or creates a PowerPoint file, and the figure and links go to the selected services.
This is third-party code. Review the repository files before installing.
What it does
Paper Figure to Figma takes an image of a research figure and rebuilds it in Figma as layers. Labels stay text, shapes, arrows and curves stay vectors, and gradients and transparency are kept. Only input and output photographs remain raster layers. The agent compares the draft with the original first as a whole, then in enlarged details, and corrects differences. When a paper link, PDF or source files are supplied, the agent looks for matching original artwork and builds from it; without a source it works from the screenshot. Since version 0.2.5 the skill also delivers a native `.pptx`, with Figma remaining the default.
Who it is for. Authors of papers and theses who hold a needed figure only as an image and must change its labels, fonts and layout for a journal or talk.
Good fit when
- A figure from a PDF exists only as a raster and its labels must be translated or moved.
- A journal asks for Times New Roman and one font size across all panels.
- Talk slides are built from a finished figure and its objects must be selectable one by one in PowerPoint.
- A Figma frame is revised after reviewer comments without touching approved elements.
Not a fit when
- The figure carries measured data: a human verifies numbers and labels after redrawing, the skill does not confirm them.
- Figma write access is unavailable and PowerPoint cannot be run on Windows.
- A pixel-for-pixel copy is expected: the skill reproduces appearance and promises no universal fidelity.
Example request
Use $paper-figure-to-figma to reconstruct the attached figure in my Figma file, review it whole and in detail, and send a link to the editable frame.Limitations
The skill has been verified only with Codex. Figma output needs a connection with edit access to the design file. Native PowerPoint works on Windows with desktop PowerPoint and the `pywin32` package. Complex illustrations are built from SVG, geometry or traced contours, so similarity is approximate and scientific text and connections need manual checking. Original lookup by paper title is limited to about 90 seconds, after which the skill falls back to the screenshot.
How to disable. Delete the `paper-figure-to-figma` folder from the agent's skills directory, `~/.codex/skills/` by default. The installer with `--update` keeps a copy of the previous version; remove that as well. Revoke Figma access in account settings.
FAQ
Is a separate model API key needed?
No. The skill runs inside the assistant itself, with no VLM key and no original generation prompt.
How do I get PowerPoint instead of Figma?
Ask for PPTX explicitly. Windows, installed PowerPoint and `pywin32` are required; no Figma connection is needed.
How do I update an installed skill?
Run `git pull --ff-only` and `python tools/install_skill.py --update` in the repository folder. The previous installation is backed up.
Is a paper link required?
No. A source is optional; without one the skill redraws the figure from the screenshot.
Which agents are supported?
Verification was done in Codex. The installer's `--dest` flag installs the skill into another assistant's directory if it can view images and call Figma tools.
Discussion
No questions or reviews yet.
Related
SkillsA skill that draws paper figures as vectors: architecture, mechanism and overview figures exported to SVG, PDF and PPTX
A skill that turns an academic PDF figure into a self-contained SVG and an editable PPTX, then checks it pixel by pixel.
Redraws a paper figure as a native Visio .vsdx of editable shapes and text, then exports PNG, SVG, PDF and PPTX from it.
Three skills for paper figures: fig-analyze reads material, fig-draw picks a style and renders, fig-pptx builds an editable PPT.
A skill for scientific papers: vector schematics as SVG and PDF plus the code that draws them, so any element stays editable.
Skill for publication figures: matplotlib charts for papers in one house style, with vector and raster export from sample scripts.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Paper Figure to Figma (this card) | no | 161 | |
| figma-use | no | 615 | operates Figma as a write tool; Paper Figure to Figma adds a research-figure redraw method and a review loop |
| Papermorph | no | 1,622 | converts paper formatting; Paper Figure to Figma rebuilds a single figure as layers |
README in short
The repository holds the skill in `.agents/skills/paper-figure-to-figma`, reconstruction and review prompts, the `tools/install_skill.py` installer and the online Prompt Builder.