Claude Skill MartBrowse skillsWhat is a Skill?
 
← Back to list

MATLAB & GNU Octave Workflow Assistant

An expert skill for designing, reviewing, migrating and safely planning MATLAB/Octave numerical workflows.

Dev & CodingAdvanced★ 33,030⑂ 3,248AI score 8/10Last updated: Aug 9, 2026

What it does

Guides Claude through building and reviewing numerical code for MATLAB (pinned to R2026a) and GNU Octave 11.3.0, including release migration and reproducible project setup.

  • Language and data checklist: arguments blocks, 1-based column-major indexing, implicit expansion pitfalls, floating-point tolerances, and pinned RNG algorithm/seed.
  • Tables, timetables, missing data: retime/synchronize, type-specific missing sentinels (NaN, NaT, <missing>), explicit import options for production data.
  • Hard safety boundary: never executes untrusted .m, .mlx, MEX, MAT files or project startup actions; static inspection comes first.
  • Local helper CLIs: static code scanning, MAT header inventory, argv execution planning, reproducibility hashing, and function/test scaffolding — all network-free and non-executing.
  • Python interop: pyenv, MATLAB Engine version compatibility, and conversion semantics for NumPy/pandas types.

Who it's for

  • Engineers and researchers maintaining or reviewing MATLAB codebases
  • Teams migrating legacy code to a newer release or to free Octave
  • Scientists who need publication-quality figure export and provenance records
  • Anyone who must inspect untrusted .m or .mat artifacts safely

Examples

  1. "Scan this repo's .m files and list risky patterns like eval, system, or dynamic addpath" → runs scripts/scan_m_code.py and summarizes remediation.
  2. "What will break moving R2018b code to R2026a?" → a plan using codeIssues/codeCompatibilityReport plus implicit-expansion and graphics API change notes.
  3. "Tell me what's inside data.mat without loading it" → inventory_mat_file.py reports headers and datasets while flagging object-deserialization risk.

· · · Install guide · · ·

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 skills/matlab folder from the GitHub repo K-Dense-AI/scientific-agent-skills into my ~/.claude/skills/matlab/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/K-Dense-AI/scientific-agent-skills.git /tmp/scientific-agent-skills && mkdir -p ~/.claude/skills && cp -r /tmp/scientific-agent-skills/skills/matlab ~/.claude/skills/matlab

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

  1. Open a terminal and go to your working directory.
  2. Clone the repository: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy just this skill: cp -r scientific-agent-skills/skills/matlab ~/.claude/skills/matlab
  5. Confirm Python 3.11+ is available for the bundled CLIs: python3 --version
  6. Optional: for deeper MAT-file inventory, install backends in your project environment with pip install scipy h5py.
  7. Restart Claude Code and try a prompt such as "review my MATLAB function" or "check Octave compatibility".
  8. Note: the skill never launches MATLAB or Octave for you — you must confirm your license and run any generated command yourself.
View source on GitHub ↗License: MIT