scientific-visualization

Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib/seaborn/plotly with publication styles. For quick exploration use seaborn or plotly directly.

1.13x

Quality

67%

Does it follow best practices?

Impact

94%

1.13x

Average score across 3 eval scenarios

Securityby

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./scientific-skills/scientific-visualization/SKILL.md

Evaluation results

90%

24%

Preparing a Figure for Nature Methods Submission

Journal-specific figure export and style configuration

Criteria

Without context

With context

Publication style applied

100%

Journal export function used

100%

No JPEG output

100%

Vector or high-res raster format

100%

Nature single-column width

100%

Sentence case axis labels

100%

Units in axis labels

50%

100%

Spines removed

100%

No grid lines

100%

Legend frameon False

100%

Colorblind palette used

94%

Gene Expression Analysis Dashboard for a Genomics Paper

Colorblind-safe palettes and heatmap colormap selection

Criteria

Without context

With context

Okabe-Ito or colorblind palette

100%

No jet or rainbow colormap

100%

Diverging colormap for heatmap

100%

No red-green diverging map

100%

Heatmap centered at zero

100%

Labeled colorbar present

100%

Redundant encoding in scatter

100%

Grayscale version saved

100%

Axes labeled with units

75%

62%

Spines removed or despine

57%

No unnecessary grid

100%

99%

Clinical Trial Results Figure for a Cell Press Journal

Statistical rigor and multi-panel layout conventions

Criteria

Without context

With context

GridSpec layout

100%

Bold panel labels A/B/C

100%

Panel labels uppercase

100%

Error bars present

100%

Error bar type defined

100%

Individual data points shown

100%

Significance markers present

100%

Cell double-column width

100%

Sample size in caption

100%

Bar chart starts at zero

100%

No 3D effects

100%

Axes labeled with units

83%

Colorblind-safe palette

100%

Repository: K-Dense-AI/claude-scientific-skills
Commit: 7a1d69c

Evaluated: 24 days ago
Agent: Claude Code
Model: Claude Sonnet 4.6

Table of Contents

Preparing a Figure for Nature Methods Submission Gene Expression Analysis Dashboard for a Genomics Paper Clinical Trial Results Figure for a Cell Press Journal

Is this your skill?

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.