matlab-agentic-toolkit-setup
MATLAB Agentic Toolkit Setup
Automated onboarding for the MATLAB Agentic Toolkit. Detects MATLAB, downloads and installs the MCP server binary, configures your AI coding agent, and verifies everything works.
Tested platform: Claude Code. Automated platforms: GitHub Copilot, Gemini CLI (with manual fallback provided). Experimental platforms: Codex, Amp are provided as-is; setup will guide you through each step and provide manual fallback instructions if anything fails.
This skill does NOT require the MATLAB MCP server — it uses shell commands for everything until the final verification step.
Welcome Message
Before doing any work, print a welcome message to the user. This sets expectations for what's about to happen and why they may be asked to approve actions. Use a friendly, personal tone with "I" statements. The message should cover:
Welcome! My goal is to get you set up with the MATLAB Agentic Toolkit so you
can use MATLAB tools and skills with your agent for your projects.
Here's what I'll do:
More from matlab/matlab-agentic-toolkit
matlab-debugging
Diagnose MATLAB errors and unexpected behavior. Breakpoints, workspace inspection, try-catch diagnostics, and common error patterns. Use when debugging functions, tracing errors, inspecting variables, or diagnosing runtime failures.
5matlab-review-code
Review MATLAB code for quality, performance, maintainability, and adherence to MathWorks coding standards. Uses check_matlab_code and matlab_coding_guidelines. Use when reviewing code, checking style, finding code smells, assessing quality, or preparing code for handoff or publication.
5matlab-install-products
Deterministic workflow to download MATLAB Package Manager (mpm) and install MathWorks products from the OS command line with consistent, repeatable behavior. Use when installing MATLAB, Simulink, toolboxes, or support packages via command line, or setting up scripted installations for CI/CD, containers, or fleet provisioning.
5matlab-model-serdes-systems
>
5matlab-create-live-script
Create plain-text MATLAB Live Scripts (.m files) with rich text formatting, LaTeX equations, section breaks, and inline figures. Use when generating tutorials, analysis notebooks, reports, documentation, or educational content. Requires R2025a+.
5matlab-testing
Generate and run MATLAB unit tests using matlab.unittest and matlab.uitest. Parameterized tests, fixtures, mocking, coverage analysis, CI/CD with buildtool, app testing with gestures. Use when creating tests, writing test classes, running test suites, checking coverage, testing apps, or validating MATLAB code.
4