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…
PNAS figure preparation: resolution (300-1000 PPI), formats (TIFF/EPS/PDF), strict RGB-only color, Arial/Helvetica fonts, italicized uppercase panel labels, automated image screening.
$ npx -y skills add jaechang-hits/SciAgent-Skills --skill pnas-figure-guide --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/pnas-figure-guideContext preview
The summary Claude sees to decide when to auto-load this skill.
PNAS figure preparation: resolution (300-1000 PPI), formats (TIFF/EPS/PDF), strict RGB-only color, Arial/Helvetica fonts, italicized uppercase panel labels, automated image screening.
name: pnas-figure-guide description: "PNAS figure preparation: resolution (300-1000 PPI), formats (TIFF/EPS/PDF), strict RGB-only color, Arial/Helvetica fonts, italicized uppercase panel labels, automated image screening." 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 **PNAS** (Proceedings of the National Academy of Sciences). PNAS is notable for its **strict RGB-only policy** (CMYK submissions are returned), **italicized uppercase panel labels**, and **automated image screening software**.
**Official reference**: https://www.pnas.org/author-center/submitting-your-manuscript
---
| Image Type | Minimum Resolution | Notes | |---|---|---| | Halftones (color/grayscale photos) | **300 PPI** | At publication size | | Combination artwork (MS Office) | **600-900 DPI** | Mixed text and images | | Line art (bitmap text/thin lines) | **1,000 PPI** | At publication size | | LaTeX figures | — | High-quality PDF or EPS |
from PIL import Image
def check_pnas_resolution(image_path, image_type='halftone'):
"""Check if image meets PNAS resolution requirements.
Args:
image_type: 'halftone' (300), 'combination' (600), or 'lineart' (1000)
"""
min_ppi = {'halftone': 300, 'combination': 600, 'lineart': 1000}
required = min_ppi.get(image_type, 300)
img = Image.open(image_path)
dpi = img.info.get('dpi', (72, 72))
print(f"Type: {image_type} | Required: {required} PPI | Actual: {dpi[0]} PPI")
if dpi[0] >= required:
print("PASS")
else:
print(f"FAIL: Need {required} PPI minimum")
return dpi[0] >= required---
| Format | Accepted | |---|---| | **TIFF** | Yes (preferred for raster) | | **EPS** | Yes (fonts must be embedded) | | **PDF** | Yes (fonts must be embedded) | | **PPT** | Yes | | **3D images** | PRC or U3D with 2D representation (TIFF/EPS/PDF) |
---
**IMPORTANT**: Provide images at **final publication size**, not full-page size.
| Layout | Width | |---|---| | 1 column | **8.7 cm** (3.43 in) | | 1.5 columns | **11.4 cm** (4.5 in / 27 picas) | | 2 columns | **17.8 cm** (7.0 in / 42.125 picas) | | Maximum height | **22.5 cm** (9 in / 54 picas) |
import matplotlib.pyplot as plt
PNAS_WIDTHS = {
'single': 8.7 / 2.54, # 3.43 inches
'middle': 11.4 / 2.54, # 4.49 inches
'double': 17.8 / 2.54, # 7.01 inches
}
PNAS_MAX_HEIGHT = 22.5 / 2.54 # 8.86 inches
def create_pnas_figure(layout='single', aspect_ratio=0.75):
"""Create a Matplotlib figure sized for PNAS."""
width = PNAS_WIDTHS[layout]
height = min(width * aspect_ratio, PNAS_MAX_HEIGHT)
fig, ax = plt.subplots(figsize=(width, height))
fig.set_dpi(300)
return fig, ax---
from PIL import Image
def validate_pnas_color_mode(image_path):
"""PNAS strictly requires RGB. CMYK will be rejected."""
img = Image.open(image_path)
if img.mode == 'CMYK':
print("REJECTED: PNAS does not accept CMYK images")
print("Action: Convert to RGB before submission")
return False
elif img.mode in ('RGB', 'RGBA'):
print("PASS: Image is in RGB mode")
return True
else:
print(f"WARNING: Unexpected mode '{img.mode}'; convert to RGB")
return False
def convert_to_rgb(image_path, output_path):
"""Convert any image to RGB for PNAS submission."""
img = Image.open(image_path)
if img.mode != 'RGB':
img = img.convert('RGB')
print(f"Converted from {img.mode} to RGB")
img.save(output_path)---
| Element | Specification | |---|---| | Approved fonts | **Arial, Helvetica, Times, Symbol, Mathematical Pi, European Pi** | | Font size | **6-8 pt** at final publication size (minimum 2 mm when printed) | | Consistency | Same font for all figures in manuscript | | Text type | **Vector text** preferred (scales cleanly) | | Embedding | **All fonts must be embedded** in EPS and PDF files |
import matplotlib.pyplot as plt
def set_pnas_fonts():
"""Configure Matplotlib for PNAS figure fonts."""
plt.rcParams.update({
'font.family': 'sans-serif',
'font.sans-serif': ['Arial', 'Helvetica'],
'font.size': 7,
'axes.labelsize': 7,
'axes.titlesize': 7,
'xtick.labelsize': 6,
'ytick.labelsize': 6,
'legend.fontsize': 6,
})
def add_pnas_panel_labels(fig, axes):
"""Add PNAS-style italicized uppercase panel labels."""
import string
if not hasattr(axes, '__iter__'):
axes = [axes]
for i, ax in enumerate(axes):
label = string.ascii_uppercase[i]
ax.text(-0.1, 1.1, label,
transform=ax.transAxes,
fontsize=8,
fontstyle='italic',
fontweight='bold',
va='top',
ha='right',
fontfamily='Arial')---
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…