This skill should be used when the user asks to plot data, create charts, visualize data, generate graphs, or display histograms, scatter plots, heatmaps, bar charts, or any data visualization. Also use when the agent needs to visualize data to understand patterns, debug numerical output, or present analysis results. Use even for quick "show me this data" requests.
For fast, terminal-native plots from data. No image rendering needed.
python3 -c "
import plotext as plt
plt.scatter([1,2,3,4], [1,4,9,16])
plt.title('Example')
plt.show()
"
Use for: quick exploration, piped data, when speed matters more than beauty.
For publication-quality plots rendered inline via Kitty graphics protocol. CRITICAL: Always set the backend BEFORE importing matplotlib:
MPLBACKEND='module://matplotlib-backend-kitty' python3 -c "
import matplotlib.pyplot as plt
import numpy as np
x = np.linspace(0, 10, 100)
plt.plot(x, np.sin(x))
plt.title('Sine Wave')
plt.savefig('/dev/stdout', format='png')
plt.show()
"
Use for: rich plots, multiple subplots, custom styling, when visual quality matters.
For interactive, resizable plots.
gnuplot -e "set terminal kitty; plot sin(x)"
Use for: mathematical functions, interactive exploration, when user wants to resize/zoom.