schematic-figure skill
A skill for scientific papers: vector schematics as SVG and PDF plus the code that draws them, so any element stays editable.
- 169 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent runs Node.js, Chromium and export scripts and writes files into the project folder.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/schematic-figureDetects 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 runs Node.js, Chromium and export scripts and writes files into the project folder.
This is third-party code. Review the repository files before installing.
What it does
schematic-figure draws schematic illustrations for scientific papers: a Figure 1 with a device, a mechanism or an experiment layout. The agent produces SVG and PDF vector files plus the code that builds them and saves everything to `figure/out/`. The repository has two skills: `schematic-figure` and `patent-drawing` for patent drawing sheets. Style is set in words: flat, 3D, Blender render or photoreal. Width matches a journal column, 89 or 183 mm, and checking depth has three levels: draft, standard and full.
Who it is for. Researchers in the natural sciences who need a first draft of a paper figure and several design options in an evening.
Good fit when
- A paper needs a device figure and no illustrator is at hand.
- Three variants of one figure should be built in parallel on a single sheet and the best parts combined.
- A patent drawing sheet with numbered parts is wanted.
- The figure must reuse the colours and line weights of the lab's previous paper.
Not a fit when
- The figure would go out without anyone checking the science.
- Data plots are needed rather than schematics.
- The environment has no Chromium or Node.js 22 or newer.
Example request
Use the schematic-figure skill: draw a lithium-ion cell while charging, in 3D, width 89 mm, depth draft.Limitations
The skill does not replace the person who designs the figure: the README authors call the result a quick first draft, and a human checks the science and details. Node.js 22 or newer and a Chromium browser are required, while Blender and RDKit add 3D renders and molecules. Export to TIFF, EPS and PowerPoint needs Python 3 with Pillow, python-pptx and lxml, plus `pdftops` or Ghostscript for EPS. A novel scientific concept needs a detailed technical description.
How to disable. Delete the `schematic-figure` and `patent-drawing` folders from `~/.claude/skills/`. Finished figures stay in the project's `figure/out/`.
FAQ
Where does the agent save figures?
In `figure/out/` of the folder where the agent runs: SVG, PDF and PNG, sometimes in a subfolder named after the figure.
How do I choose style and size?
In words in the request: “flat”, “in 3D”, “render it in Blender”, “photoreal”, “Width 89 mm” or “Width 183 mm”.
How do I get TIFF or PowerPoint?
Ask the agent to export the figure. This needs Python 3 with Pillow, python-pptx and lxml.
Can several variants run at once?
Yes. The authors suggest requesting three designs with three parallel agents and combining the best on one sheet.
What is needed to run it?
Node.js 22 or newer and a Chromium browser. Blender and RDKit are optional, for 3D renders and molecules.
Discussion
No questions or reviews yet.
Related
SkillsAn image skill for science figures: 24 templates for diagrams and posters in biology, chemistry, physics and maths.
A skill that draws interactive isometric illustrations in SVG, with WebGL shaders and React output, explaining an idea as a working machine
A skill hand-writes SVG feature illustrations by one SPEC.md ruleset, with a single palette serving both light and dark themes.
The skill turns paper text, methods and captions into structured prompts for scientific figures, tuned to the chosen image model.
A skill that assembles ready image prompts in hand-drawn styles from a set of tested recipes: kids drawing, minimal line, crayon, Ghibli look and more
A skill that turns Chinese story copy or a set of ordered images into a vertical hand-drawn animation, a silent diary-comic picture track
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| schematic-figure (this card) | no | 169 | |
| SciPilot Figure | no | 2,789 | advises a plot type from data; schematic-figure draws device and mechanism schematics as vector code |
| Scientific Illustrator | no | 981 | a Codex plugin that redraws a scientific figure from a sample in PowerPoint; here the schematic is built from a description and exported as SVG and PDF |
README in short
The authors compared figures from five papers against a model's output without and with the skill, and the write-up is on the lab's blog. Four papers appeared after the model's training cutoff.