Use when a research project needs a polished data figure (results chart, paper figure, appendix figure, progress summary plot) made with matplotlib, or a render-inspect-revise pass before treating a figure as final.
79%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Fix and improve this skill with Tessl
tessl review fix ./skills/ds-figure-polish/SKILL.mdUse this skill when a figure matters beyond transient debugging.
This includes:
Do not use this skill for disposable debug plots unless the user explicitly asks for them to be polished.
Research figures should feel academic, restrained, and clear.
The goal is not to make a plot “fancy”. The goal is to make the intended comparison obvious without visual clutter.
Use one dominant message per figure. If multiple unrelated claims are competing inside the same image, split the figure instead of cramming everything into one panel.
First classify the figure:
progress_update
pngpaper_main
pdf or svg plus a png previewappendix
internal_review
Prefer the bundled Matplotlib style asset when plotting in Python:
assets/deepscientist-academic.mplstyle (in this skill's folder; use its absolute path, since the skill folder is linked into the project)If you need a custom script, start from that style instead of inventing a fresh bright theme.
Default visual rules:
Choose the chart by the research question:
Do not use heatmaps or crowded dashboards just because they look “richer”.
Avoid any colormap whose lightness jumps back and forth or whose hue changes overwhelm numeric ordering.
If a figure is intended for progress reporting, paper drafting, appendix use, or durable artifact storage, you must follow this sequence:
Do not treat a figure as final if you have not inspected the rendered result. Do not assume “the code looks fine” means “the figure looks fine”.
When reviewing the rendered figure, check at least:
If any answer is negative, revise before calling the figure complete.
progress_update
pngpaper_main
pdf or svgpng preview for visual review and UI displayappendix
Prefer deterministic export names and record the generating script path.
Whenever a figure is accepted as durable, record:
For paper work, keep a small figure catalog next to the figures (for example Publication/paper/figures/figure_catalog.json) with these fields, and keep it in sync.
If plotting in Python, prefer:
plt.style.use("<absolute path to this skill>/assets/deepscientist-academic.mplstyle")Do not rely entirely on defaults.
Use restrained paper-like sizes by default:
5.2 x 3.2 in3.5 x 2.4 in7.2 x 3.2 inAdjust only when the content truly needs it.
inno-experiment-analysis: decide which results and statistics a figure should show.ml-paper-writing: figure and caption guidance for the paper itself.inno-figure-gen: conceptual diagrams and teaser images (needs an image-generation API key); this skill is for data plots.Adapted from DeepScientist's figure-polish skill (MIT).
OpenLAIR/dr-claw
3456bb4
Also appears in
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.