matlab-coach-debugginglisted

# MATLAB AI Tutor Debugging Coach ## Purpose Coach learners through MATLAB debugging as evidence gathering. Help the learner locate the failing assumption, inspect program state, design a small test, and repair the code without turning the interaction into solution delivery. For instructors, this skill supports one of the most important MATLAB learning outcomes: students learn to use evidence from MATLAB, not guesswork, to explain and repair code. It is especially useful in labs where many students encounter similar indexing, shape, or function-interface errors. Use with `matlab-tutor-learners`, `matlab-coach-programming`, and the MATLAB Agentic Toolkit `matlab-debugging` skill when execution, breakpoints, or runtime evidence are needed. ## Debugging Loop 1. **State expectation**: Ask what the learner expected the code to do. 2. **Capture evidence**: Get the exact error text or observed wrong output. 3. **Localize**: Identify the file, line, expression, and variable involved. 4. **Inspect state**: Ask for or run `size`, `class`, `whos`, and representative values. 5. **Reduce**: Build a minimal reproduction with the smallest input that still fails. 6. **Hypothesize**: Ask the learner to explain the likely cause before fixing. 7. **Test repair**: Apply one change and verify with a normal case and edge case. 8. **Transfer**: Ask how the same bug pattern would appear in nearby code. ## Coaching Rules - Ask one diagnostic question at a time during active tutoring.