Matlab

This gives Claude the ability to write and explain MATLAB and GNU Octave code for numerical computing tasks. It covers matrix operations, linear algebra, plotting, differential equations, signal processing, and data analysis. The skill includes detailed references for everything from basic array manipulation to ODE solvers and 3D visualization. What's practical here is that it works with both commercial MATLAB and the free Octave interpreter, so you can generate scripts without needing a license. The execution guides show you how to actually run the code it produces. Good fit if you're doing scientific computing, need to prototype numerical algorithms, or want help converting between MATLAB and Python syntax.

skills.sh installs: 2.1K
GitHub stars: 56.6K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add k-dense-ai/scientific-agent-skills --skill matlab --agent claude-code

Installs into .claude/skills of the current project.

Files

MATLAB and GNU Octave

Use this skill to design or review numerical code, migrate MATLAB releases, prepare reproducible projects, and plan trusted execution. MATLAB and GNU Octave are distinct products: compatibility is partial, not a license or behavior guarantee.

Review scope

Reviewed against current MathWorks R2026b documentation and GNU Octave 11.3.0 sources on 2026-10-01. The bundled Engine planner and MATLAB examples retain an explicit R2026a baseline. R2026b supports CPython 3.10-3.14; do not reuse the R2026a Engine package for it. MATLAB/Octave examples are illustrative and were not executed in this review; the Python helpers have local synthetic tests. This skill uses local runtime APIs, with no remote service endpoint or API key.