Agent skill · creative production · aradotso
nature-academic-skills
nature-academic-skills — an agent skill for coding agents.
Why this skill is useful
Provides specific matplotlib configurations and Nature journal standards for academic figures and prose that the AI wouldn't reliably generate on its own.
What it needs
Requires matplotlib, numpy, scipy installed locally. About 8k tokens when loaded. Last updated 2026-07-09. 70 stars on the source repository.
What this skill does
bash git clone https://github.com/Yuan1z0825/nature-skills.git .claude/skills/nature-skills bash For figure generation only cp nature-skills/nature-figure/SKILL.md .claude/skills/nature-figure.md For prose polishing only cp nature-skills/nature-polishing/SKILL.md .claude/skills/nature-polishing.md bash pip install matplotlib numpy scipy bash pip install cairosvg # SVG → PDF conversion pip install svgutils # panel assembly python import matplotlib.pyplot as plt import matplotlib as mpl import numpy as np REQUIRED: must appear before any figure creation plt.rcParams['font.family'] = 'sans-serif' plt.rcParams['font.sans-serif'] = ['Arial', 'DejaVu Sans', 'Liberation Sans'] plt.rcParams['svg.fonttype'] = 'none' # text stays as <text> nodes, not paths python Primary output: SVG (always) fig.savefig('figure1.svg', bboxinches='tight', dpi=300) Secondary output: PNG raster preview (always include alongside SVG) fig.savefig('figure1.png', bboxinches='tight', dpi=300) python NATUREPALETTE = { 'blue': '#4878CF', 'green': '#6ACC65', 'red': '#D65F5F', 'purple': '#B47CC7', 'cyan': '#77BEDB', 'orange': '#EE854A', 'pink': '#D0759F', 'yellow': '#C4AD66', 'lightblue': '#8ABBE5', 'darkgreen': '#3A9E5F', } COLORS = list(NATUREPALETTE.values()) python FONTSIZES = { 'panellabel': 8, 'axistitle': 7, 'ticklabel': 6, 'legend': 6, } python import matplotlib.pyplot as plt import matplotlib.gridspec as gridspec import numpy as np --- Mandatory rcParams --- plt.rcParams['font.family'] = 'sans-serif' plt.rcParams['font.sans-serif'] = ['Arial', 'DejaVu Sans', 'Liberation Sans'] plt.rcParams['svg.fonttype'] = 'none' NATUREPALETTE = { 'blue': '#4878CF', 'green': '#6ACC65', 'red': '#D65F5F', 'orange': '#EE854A', } COLORS = list(NATUREPALETTE.values()) --- Figure layout (Nature single-column: 89 mm; double: 183 mm) --- fig = plt.figure(figsize=(7.2, 4.0)) # 183 mm wide ≈ 7.2 inches gs = gridspec.GridSpec(1, 3, figure=fig, wspace=0.45, hspace=0.4) Panel a: bar chart (overview) axa = fig.addsubplot(gs[ …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aradotso/nature-academic-skills