MATLAB/GNU Octave numerical computing: matrices, linear algebra, ODEs, signal processing, optimization, statistics, scientific visualization. MATLAB-syntax examples run on both. For Python use numpy/scipy; for statistical modeling use statsmodels.
SkillScore100Maintained
Automatic
◆Coding pack
Last verified 8/24/2026
What it changes
Passed 24 of 24 test cases with the skill, and 21 of 24 without it.
Without skill88%
With skill100%
Checks it passed that the model alone missed
Uses the print function with the -dpdf device flag
Constructs the frequency array as (0:N-1) * fs / N
Uses the py.numpy.mean syntax to call the Python NumPy function
3 fixed21 passed either way0 still failing0 broke
Pass-rate lift
+13 pp
Tokens
+333%
Agent turns
0%
Response time
-41%
Model gemini-3.6-flashMeasured 8/24/2026v124 of 24 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 3
Prompt
I need to calculate the arithmetic mean of an array `[1, 2, 3, 4, 5]` inside a matrix workspace by executing Python's NumPy library directly. What namespace prefix syntax invokes NumPy's mean function?
What was checked, without and with the skill
Checked
Without skill
With skill
Uses the py.numpy.mean syntax to call the Python NumPy function
Missed
Passed
case-16 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md491 linessingle file
MATLAB/Octave — Scientific Computing
Overview
MATLAB is a numerical computing environment optimized for matrix operations and scientific computing. GNU Octave is a free, open-source alternative with high compatibility. All code examples use MATLAB syntax that runs on both platforms.
When to Use
Performing matrix operations and linear algebra (eigenvalues, SVD, least squares)
Solving ordinary and partial differential equations numerically
Signal processing (FFT, filtering, spectral analysis)
Creating 2D/3D scientific visualizations and publication figures
Numerical optimization and root finding
Statistical analysis and curve fitting
Batch processing of experimental data files
For Python-based numerical computing, use numpy/scipy instead
For statistical modeling with inference, use statsmodels instead
Note: MATLAB requires a commercial license from MathWorks. GNU Octave is free and runs most MATLAB scripts without modification. Key Octave differences: supports # comments, ++/+= operators; some MATLAB toolbox functions unavailable.
Quick Start
% Load data, fit, and plot
x = linspace(0, 2*pi, 100);
y = sin(x) + 0.1 * randn(size(x));