matlab-debugging

Name: matlab-debugging
Author: matlab

92installs105forks

How to install matlab-debugging?

matlab/matlab-agentic-toolkit/matlab-debugging

$npx -y skills add matlab/matlab-agentic-toolkit --skill matlab-debugging

Installs into the current project.

Summary

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.

Files · 1

View on GitHub

SKILL.md

1	# Investigating and Debugging MATLAB Code with MCP Tools
2
3	You have access to a live MATLAB session via MCP tools. Use them to actively
4	investigate code — whether debugging errors, understanding behavior, or answering
5	questions about how MATLAB code works. Don't just guess from code alone.
6
7	## When to Use
8
9	- User encounters a MATLAB error message or unexpected result
10	- User wants to set breakpoints or inspect variable state
11	- Tracing why a function produces wrong output
12	- NaN/Inf values appearing unexpectedly
13	- A MATLAB MCP tool returns an error or exception — including runtime errors, syntax errors, undefined function/variable errors, or failed test results
14	- User asks "why is my MATLAB code not working", "help me debug", or shares a MATLAB stack trace
15
16	## When NOT to Use
17
18	- Code quality review without a runtime problem — use `matlab-reviewing-code` instead
19	- Performance profiling — use performance optimization workflows
20	- Writing tests for correctness — use `matlab-testing` instead
21	- Understanding MATLAB APIs or language features without a specific bug
22
23	## Static Analysis vs Runtime Debugging
24
25	Not every issue needs the live MATLAB session. Choose the right approach:
26
27	- Static analysis is enough when: syntax errors, unused variables, obvious
28	logic mistakes, or issues visible from reading the source code alone. Use the
29	`Read` tool and `check_matlab_code`.
30	- Runtime debugging is needed when:
31	- The error depends on actual data values, types, or dimensions
32	- The output is wrong but the code looks correct
33	- The user says "it doesn't work" but the code looks fine — check actual data
34	- You need to know what variables contain at a specific point in execution
35
36	When in doubt, start with static analysis. Escalate to runtime debugging when
37	you can't determine the root cause from source alone.
38
39	## Auto-Trigger on MATLAB Errors
40
41	When a MATLAB MCP tool returns an error (runtime error, syntax error, undefined
42	function/variable, dimension mismatch, failed assertion, etc.), **do not silently
43	move on or guess at a fix**. Instead:
44
45	1. Recognize the error — Look for patterns like `Error using ...`,
46	`Undefined function or variable`, `Index exceeds ...`, `Error in ...`,
47	MATLAB stack traces, or failed test results in MCP tool output.
48	2. Ask the user for permission — Before launching into investigation, offer:
49	> "I noticed a MATLAB error: `<brief error summary>`. I can use the
50	> matlab-debugging skill to dig into this — inspect variables, trace the
51	> call stack, and identify the root cause. Want me to investigate?"
52	3. Proceed only after confirmation — Once the user agrees, follow the
53	investigation workflow below.
54
55	This applies whether the error came from the user running code, or from you
56	running code on the user's behalf (e.g., verifying a fix, running tests).
57
58	## Available Tools
59
60	\| Tool \| Use For \|
61	\|------\|---------\|
62	\| `mcp__matlab__run_matlab_file` \| Run .m scripts — prefer this for executing user scripts and verifying fixes \|
63	\| `mcp__matlab__evaluate_matlab_code` \| Quick diagnostics: inspect variables, evaluate expressions, test small snippets \|
64	\| `mcp__matlab__check_matlab_code` \| Static analysis of .m files (warnings, unused vars, potential issues) \|
65	\| `mcp__matlab__run_matlab_test_file` \| Run a MATLAB test file \|
66	\| `mcp__matlab__detect_matlab_toolboxes` \| List installed toolboxes — use when "Undefined function" may be a missing toolbox \|
67
68	Prefer `run_matlab_file` over `evaluate_matlab_code` for running scripts. Only
69	use `evaluate_matlab_code` for short diagnostic commands (checking a variable,
70	testing an expression, etc.) — not for re-running entire scripts inline.
71
72	## Workflow
73
74	### 1. Understand the Goal
75
76	Determine what the user needs:
77	- Debugging — runtime error, wrong output, unexpected behavior
78	- Understanding — how does this code work, what does this function do
79	- Investigating — why does this variable have this value, where does this data come from
80	- Exploring — what functions are available, how is this codebase structured
81
82	### 2. Gather Information via MATLAB
83
84	Use `mcp__matlab__evaluate_matlab_code` to run diagnostic commands.
85
86	Read source code: Use the `Read` tool for .m files on disk — not MATLAB's
87	`type` or `dbtype`. Only use MATLAB's `which` to locate files you haven't
88	found yet, and `which -all` to check for shadowing.
89
90	Preview large data: Use `varName(1:min(5,end),:)` or `head(T)` to preview
91	slices instead of dumping entire variables.
92
93	Runtime debugging — check desktop mode first:
94
95	Before using breakpoints, check if MATLAB has a desktop:
96	```matlab
97	desktop('-inuse') % true = de

People who liked this also viewed

6 picks

Type

matlab-debugging

92installs105forks

View on GitHub

How to install matlab-debugging?

matlab/matlab-agentic-toolkit/matlab-debugging

$npx -y skills add matlab/matlab-agentic-toolkit --skill matlab-debugging

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Investigating and Debugging MATLAB Code with MCP Tools
2
3	You have access to a live MATLAB session via MCP tools. Use them to actively
4	investigate code — whether debugging errors, understanding behavior, or answering
5	questions about how MATLAB code works. Don't just guess from code alone.
6
7	## When to Use
8
9	- User encounters a MATLAB error message or unexpected result
10	- User wants to set breakpoints or inspect variable state
11	- Tracing why a function produces wrong output
12	- NaN/Inf values appearing unexpectedly
13	- A MATLAB MCP tool returns an error or exception — including runtime errors, syntax errors, undefined function/variable errors, or failed test results
14	- User asks "why is my MATLAB code not working", "help me debug", or shares a MATLAB stack trace
15
16	## When NOT to Use
17
18	- Code quality review without a runtime problem — use `matlab-reviewing-code` instead
19	- Performance profiling — use performance optimization workflows
20	- Writing tests for correctness — use `matlab-testing` instead
21	- Understanding MATLAB APIs or language features without a specific bug
22
23	## Static Analysis vs Runtime Debugging
24
25	Not every issue needs the live MATLAB session. Choose the right approach:
26
27	- Static analysis is enough when: syntax errors, unused variables, obvious
28	logic mistakes, or issues visible from reading the source code alone. Use the
29	`Read` tool and `check_matlab_code`.
30	- Runtime debugging is needed when:
31	- The error depends on actual data values, types, or dimensions
32	- The output is wrong but the code looks correct
33	- The user says "it doesn't work" but the code looks fine — check actual data
34	- You need to know what variables contain at a specific point in execution
35
36	When in doubt, start with static analysis. Escalate to runtime debugging when
37	you can't determine the root cause from source alone.
38
39	## Auto-Trigger on MATLAB Errors
40
41	When a MATLAB MCP tool returns an error (runtime error, syntax error, undefined
42	function/variable, dimension mismatch, failed assertion, etc.), **do not silently
43	move on or guess at a fix**. Instead:
44
45	1. Recognize the error — Look for patterns like `Error using ...`,
46	`Undefined function or variable`, `Index exceeds ...`, `Error in ...`,
47	MATLAB stack traces, or failed test results in MCP tool output.
48	2. Ask the user for permission — Before launching into investigation, offer:
49	> "I noticed a MATLAB error: `<brief error summary>`. I can use the
50	> matlab-debugging skill to dig into this — inspect variables, trace the
51	> call stack, and identify the root cause. Want me to investigate?"
52	3. Proceed only after confirmation — Once the user agrees, follow the
53	investigation workflow below.
54
55	This applies whether the error came from the user running code, or from you
56	running code on the user's behalf (e.g., verifying a fix, running tests).
57
58	## Available Tools
59
60	\| Tool \| Use For \|
61	\|------\|---------\|
62	\| `mcp__matlab__run_matlab_file` \| Run .m scripts — prefer this for executing user scripts and verifying fixes \|
63	\| `mcp__matlab__evaluate_matlab_code` \| Quick diagnostics: inspect variables, evaluate expressions, test small snippets \|
64	\| `mcp__matlab__check_matlab_code` \| Static analysis of .m files (warnings, unused vars, potential issues) \|
65	\| `mcp__matlab__run_matlab_test_file` \| Run a MATLAB test file \|
66	\| `mcp__matlab__detect_matlab_toolboxes` \| List installed toolboxes — use when "Undefined function" may be a missing toolbox \|
67
68	Prefer `run_matlab_file` over `evaluate_matlab_code` for running scripts. Only
69	use `evaluate_matlab_code` for short diagnostic commands (checking a variable,
70	testing an expression, etc.) — not for re-running entire scripts inline.
71
72	## Workflow
73
74	### 1. Understand the Goal
75
76	Determine what the user needs:
77	- Debugging — runtime error, wrong output, unexpected behavior
78	- Understanding — how does this code work, what does this function do
79	- Investigating — why does this variable have this value, where does this data come from
80	- Exploring — what functions are available, how is this codebase structured
81
82	### 2. Gather Information via MATLAB
83
84	Use `mcp__matlab__evaluate_matlab_code` to run diagnostic commands.
85
86	Read source code: Use the `Read` tool for .m files on disk — not MATLAB's
87	`type` or `dbtype`. Only use MATLAB's `which` to locate files you haven't
88	found yet, and `which -all` to check for shadowing.
89
90	Preview large data: Use `varName(1:min(5,end),:)` or `head(T)` to preview
91	slices instead of dumping entire variables.
92
93	Runtime debugging — check desktop mode first:
94
95	Before using breakpoints, check if MATLAB has a desktop:
96	```matlab
97	desktop('-inuse') % true = de

People who liked this also viewed

6 picks

Type