sciagent-skill-creator
Scaffold a new SciAgent-Skills entry. Picks pipeline/toolkit/database/guide template, creates skills/{category}/{name}/SKILL.md with valid frontmatter, appends…
Nature figure preparation: resolution (300+ DPI), formats (AI/EPS/TIFF), RGB color, Helvetica/Arial fonts, lowercase panel labels, image integrity requirements.
$ npx -y skills add jaechang-hits/SciAgent-Skills --skill nature-figure-guide --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/nature-figure-guideContext preview
The summary Claude sees to decide when to auto-load this skill.
Nature figure preparation: resolution (300+ DPI), formats (AI/EPS/TIFF), RGB color, Helvetica/Arial fonts, lowercase panel labels, image integrity requirements.
name: nature-figure-guide description: "Nature figure preparation: resolution (300+ DPI), formats (AI/EPS/TIFF), RGB color, Helvetica/Arial fonts, lowercase panel labels, image integrity requirements." license: CC-BY-4.0 compatibility: Python 3.10+, Pillow, Matplotlib metadata: authors: HITS version: "1.0"
This guide provides the complete specifications for preparing figures for submission to **Nature** and Nature Research journals. Following these guidelines ensures smooth processing and high-quality reproduction of your figures in both print and online formats.
**Official reference**: https://www.nature.com/nature/for-authors/formatting-guide
---
| Image Type | Minimum Resolution | Notes | |---|---|---| | All figures | 300 DPI | At maximum print size | | Optimal quality | 450 DPI+ | Recommended for best online display | | Online submission | 300 PPI max | To keep file sizes manageable |
**CRITICAL**: Do NOT artificially increase resolution (upsampling) in image editing software. This does not improve quality and may introduce artifacts.
from PIL import Image
def check_nature_resolution(image_path):
"""Check if image meets Nature's resolution requirements."""
img = Image.open(image_path)
width_px, height_px = img.size
dpi = img.info.get('dpi', (72, 72))
print(f"Image: {image_path}")
print(f"Dimensions: {width_px} x {height_px} px")
print(f"DPI: {dpi[0]} x {dpi[1]}")
if dpi[0] < 300 or dpi[1] < 300:
print("WARNING: Resolution below 300 DPI minimum")
print(f" Need at least 300 DPI for Nature submission")
elif dpi[0] >= 450:
print("PASS: Meets optimal resolution (450+ DPI)")
else:
print("PASS: Meets minimum resolution (300+ DPI)")
# Check file size
import os
size_mb = os.path.getsize(image_path) / (1024 * 1024)
print(f"File size: {size_mb:.1f} MB")
if size_mb > 10:
print("WARNING: File exceeds 10 MB limit")
return dpi[0] >= 300 and dpi[1] >= 300---
| Figure Type | Preferred Format | Alternative | |---|---|---| | Line drawings, graphs, schematics | Adobe Illustrator (AI), EPS, PDF | Vector formats preserve editability | | Photographs, micrographs | Photoshop (PSD), TIFF | High-quality raster | | General purpose | JPEG (300-600 DPI) | Acceptable for most figures | | Extended Data figures | JPEG (preferred), TIFF, EPS | |
---
Nature does not specify fixed column widths for initial submission, but figures should be:
import matplotlib.pyplot as plt
def create_nature_figure(n_panels=1, fig_type='single_column'):
"""Create a Matplotlib figure sized for Nature."""
if fig_type == 'single_column':
fig_width = 3.5 # inches (approx 89 mm)
elif fig_type == 'double_column':
fig_width = 7.0 # inches (approx 178 mm)
else:
fig_width = 5.0 # 1.5 column
fig_height = fig_width * 0.75 # default aspect ratio
fig, axes = plt.subplots(1, n_panels, figsize=(fig_width, fig_height))
fig.set_dpi(450)
return fig, axes---
# Nature-friendly colorblind-safe colors
NATURE_COLORS = {
'blue': '#0072B2',
'orange': '#E69F00',
'green': '#009E73',
'red': '#D55E00',
'purple': '#CC79A7',
'cyan': '#56B4E9',
'yellow': '#F0E442',
'black': '#000000',
}---
| Element | Font | Size | Style | |---|---|---|---| | Body text in figures | Helvetica or Arial | 5-7 pt | Regular | | Panel labels | Helvetica or Arial | 8 pt | **Bold, lowercase** (a, b, c) | | Amino acid sequences | Courier | — | Monospace | | Greek characters | Symbol | — | — |
import matplotlib.pyplot as plt
def set_nature_fonts():
"""Configure Matplotlib for Nature figure fonts."""
plt.rcParams.update({
'font.family': 'sans-serif',
'font.sans-serif': ['Helvetica', 'Arial'],
'font.size': 7,
'axes.labelsize': 7,
'axes.titlesize': 7,
'xtick.labelsize': 6,
'ytick.labelsize': 6,
'legend.fontsize': 6,
'figure.titlesize': 8,
})---
import matplotlib.pyplot as plt import string def ad
Turn your AI coding agent into a life sciences expert — 199 bioinformatics skills for Claude Code covering RNA-seq, single-cell analysis, genomics, proteomics, drug discovery, and more. Boosted BixBench from 65% to 92%. Open source.
Scaffold a new SciAgent-Skills entry. Picks pipeline/toolkit/database/guide template, creates skills/{category}/{name}/SKILL.md with valid frontmatter, appends…
Bayesian modeling with PyMC 5: priors, likelihood, NUTS/ADVI sampling, diagnostics (R-hat, ESS), LOO/WAIC comparison, prediction. Hierarchical, logistic, GP…
Time-to-event modeling with scikit-survival: Cox PH (elastic net), Random Survival Forests, Boosting, SVMs for censored data. C-index, Brier, time-dependent…
Guided statistical analysis: test choice, assumption checks, effect sizes, power, APA reporting. Pick tests, verify assumptions, or format results for…
Python statistical modeling: regression (OLS, WLS, GLM), discrete (Logit, Poisson, NegBin), time series (ARIMA, SARIMAX, VAR), with rigorous inference,…
DL cell/nucleus segmentation for fluorescence and brightfield microscopy. Pre-trained models (cyto3, nuclei, tissuenet) and a generalist flow-based algorithm…