Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/chart-image-generator
Generate publication-quality chart images from research data
Passed 18 of 24 test cases with the skill, and 11 of 24 without it.
and 7 more in the full report
7 fixed11 passed either way6 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 7 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am building a scatter plot function with an overlaid linear regression line. I usually render regression lines in solid black with line width 2.0. What specific line color and dashed style should be used for the fitted regression line?
| Checked | Without skill | With skill |
|---|---|---|
| Uses #CC6677 as the regression line color. | Missed | Passed |
| Applies a dashed line style (--) to the regression line. | Missed | Passed |
The instructions your model reads when the skill loads.
A skill for generating publication-quality chart images from research data using Python visualization libraries. Covers chart type selection, styling for academic journals, multi-panel layouts, color accessibility, and export at the correct resolution and format for submission.
Creating figures for academic publications requires more than just plotting data. Journals have specific requirements for resolution (typically 300-600 DPI), file format (TIFF, EPS, PDF, or high-resolution PNG), font sizes (often 8-12pt in the final printed figure), line weights, and color accessibility. This skill automates the production of figures that meet these standards, reducing the time researchers spend on manual formatting and ensuring consistency across all figures in a manuscript.
The skill supports common chart types used in academic research: scatter plots, bar charts, line plots, box plots, violin plots, heatmaps, forest plots, Kaplan-Meier curves, and multi-panel composite figures. All examples use matplotlib and seaborn with a custom academic styling configuration.
import matplotlib.pyplot as plt
import matplotlib as mpl
def set_academic_style():
"""
Configure matplotlib for publication-quality figures.
Matches common requirements for Nature, Science, PLOS, IEEE journals.
"""
plt.rcParams.update({
# Font settings
'font.family': 'sans-serif',
'font.sans-serif': ['Arial', 'Helvetica', 'DejaVu Sans'],
'font.size': 8,
'axes.titlesize': 9,
'axes.labelsize': 8,
'xtick.labelsize': 7,
'ytick.labelsize': 7,
'legend.fontsize': 7,
# Line and marker settings
'lines.linewidth': 1.0,
'lines.markersize': 4,
'axes.linewidth': 0.5,
'xtick.major.width': 0.5,
'ytick.major.width': 0.5,
test cases passed, vs 11 / 24 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.