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

MATLAB / GNU Octave Numerical Workflow Skill

Design, review, and migrate MATLAB or Octave code with strict license gating, static-only safety checks, and reproducibility reporting.

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

What it does

  • Forces you to pin down runtime, release, platform, installed toolboxes and license status before proposing code, and never conflates MATLAB R2026a with GNU Octave 11.3.0.
  • Gives concrete engineering checklists: arguments blocks, column-major 1-based indexing, implicit expansion pitfalls, A\b over inv(A)*b, table/timetable and missing-value semantics, RNG pinning, exportgraphics output, MAT version differences.
  • Enforces a hard safety boundary: never execute untrusted .m, .mlx, MEX, MAT files or project startup actions. Bundled Python 3.11+ CLIs are static/dry-run only (code scan, manifest validation, MAT header inventory, reproducibility hashing, function scaffolds).
  • Documents MATLAB↔Python interop for R2026a: pyenv, matlabengine==26.1.12, and conversion caveats for NumPy/pandas/datetime.

Who it's for

  • Engineers and researchers maintaining or migrating legacy MATLAB codebases.
  • Teams evaluating whether a script can run on free Octave instead.
  • Anyone who must triage third-party MATLAB scripts or MAT files before opening them.

Examples

  1. Run python scripts/scan_m_code.py src --root . to flag eval, system, MEX and other code-loading surfaces before review.
  2. Build a publication figure pipeline with tiledlayout plus exportgraphics(ContentType="vector") for deterministic PDF/SVG output.
  3. Produce a reviewed launch plan with plan_batch_command.py matlab script main.m and only execute it after explicit human approval.

· · · 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/K-Dense-AI/scientific-agent-skills/HEAD/skills/matlab/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 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 && mkdir -p ~/.claude/skills && cp -r scientific-agent-skills/skills/matlab ~/.claude/skills/

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

  1. Open a terminal in your working directory.
  2. Clone the repo: git clone https://github.com/K-Dense-AI/scientific-agent-skills.git
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r scientific-agent-skills/skills/matlab ~/.claude/skills/
  5. Verify Python 3.11+: python3 --version (scipy and/or h5py are optional, only for MAT inventory).
  6. Restart Claude Code and ask something like "review this MATLAB function for reproducibility".
  7. Smoke-test a helper: cd ~/.claude/skills/matlab && python scripts/scan_m_code.py --help
View source on GitHub ↗License: MIT