Claude Skill MartBrowse skillsQuick linesLearn by videoTerminal guideWhat is a Skill?
Back to list

MATLAB Hands-On Exercise Builder & Grader

A MATLAB tutoring skill that builds runnable exercises, executes them in MATLAB, compares actual vs. expected output, and gives style feedback.

EducationIntermediate17832AI score 8/10Last updated: Sep 10, 2026

What it does

  • Runs a full practice loop: one-sentence goal → explicit expected outputs and assessment criteria → complete runnable script scaffold with a marked learner section.
  • Bans grading by visual inspection: saves a temporary .m file, applies an execution-safety preflight, then runs check_matlab_code and run_matlab_file and inspects real MATLAB output.
  • Delivers MATLAB Grader–style formative assessment without Grader: variable existence, class/size/value checks, tolerance-based numeric comparison, required/forbidden functions, custom checks for plots, tables, errors and edge cases.
  • Offers seven exercise types — Trace, Edit, Debug, Refactor, Test (matlab.unittest), Analyze, Visualize — favoring the shortest exercise that exposes the misconception.
  • Treats learner code as untrusted: avoids file I/O, network calls, delete, rmdir, shell commands and long simulations unless explicitly required and scoped.

Who it's for

  • MATLAB instructors and TAs running courses or lab sections
  • Educators who want automated formative feedback without a MATLAB Grader license
  • Engineering/science students self-studying MATLAB who want execution-based feedback

Examples

  1. "Create a 5-line exercise on row vs. column vectors" → goal, expected output, scaffold; after the learner fills it in, the script is executed and the size mismatch is pinpointed.
  2. "Grade this student script" → safety preflight, MATLAB run, tolerance-based comparison of expected variables, pass/fail list plus Code Analyzer warnings.
  3. "Give me a matlab.unittest writing drill for this function" → drill assigned, tests executed, missing edge cases identified, one extension prompt offered.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/matlab/agent-skills-playground/HEAD/demos/ai-tutoring/skills/matlab-create-hands-on-exercises/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on Claude Skill Mart.
Copy the demos/ai-tutoring/skills/matlab-create-hands-on-exercises folder from the GitHub repo matlab/agent-skills-playground into my ~/.claude/skills/matlab-create-hands-on-exercises/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/matlab/agent-skills-playground.git && mkdir -p ~/.claude/skills && cp -r agent-skills-playground/demos/ai-tutoring/skills/matlab-create-hands-on-exercises ~/.claude/skills/

This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/matlab/agent-skills-playground.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r agent-skills-playground/demos/ai-tutoring/skills/matlab-create-hands-on-exercises ~/.claude/skills/
  5. Verify the references/ folder (execution-safety.md, exercise-patterns.md, script-assessment-patterns.md) came along.
  6. Configure MATLAB tooling / an MCP server so Claude can call run_matlab_file and check_matlab_code.
  7. Restart Claude Code and try: "Create a hands-on MATLAB exercise on indexing."
View source on GitHubLicense: NOASSERTION