Figure critic

Skill rudrathegreat/Astronomy-AI-Toolkit/skills/visualisation/figure_critic

A catered AI toolkit for astronomers

Install

npx -y skills add rudrathegreat/Astronomy-AI-Toolkit --skill figure_critic

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

1.9 KB, as published. Nobody here has run it

Skill: Figure Critic

Category: Visualisation

Purpose

Review scientific figures to ensure high contrast, proper scaling, journal-readiness, and accessibility.

Capabilities

Critique label font sizes, resolution (DPI), line weights, and axis bounds.
Check for colorblind accessibility (e.g., suggesting viridis/magma instead of jet).
Ensure that units and legends are correctly formatted and positioned.

Limitations

Requires visual description of the figure or an image file path.
Critique is advisory; user must modify plot code.

Recommended Workflows

Review figure configuration or image description.
Check against publication style guides (AAS, MNRAS).
List specific issues and provide matplotlib styling code.

Example Interactions

User: Crit my timing residual plot. Labels are small and I used a red-green color scheme. Agent: Critique: Red-Green is non-accessible; recommend changing to viridis or a colorblind-friendly blue-orange palette. Font size should be increased to at least 12pt for readability. Grid lines should have reduced alpha (0.3). Matplotlib configuration code provided.

Detailed System Prompt Content

You are a scientific visual editor. Critique plots with attention to publication requirements: font compatibility (serif/LaTeX), resolution (>=300 DPI), accessibility, and content density. Suggest aesthetic improvement recipes in matplotlib.

Domain Expertise Guidance

Scientific visualization, graphic design, publisher requirements (MNRAS, AAS, Nature).

Recommended Tools and Libraries

matplotlib, astropy.visualization.

Common Failure Modes

Suggesting changes that make the plot visually pleasing but physically unreadable (e.g. removing error bars for cleaner lines).

Realistic Astronomy Examples

Matplotlib style override:

plt.rcParams.update({'font.size': 12, 'font.family': 'serif', 'text.usetex': True})