Skip to content
Get packs

MATLAB and Octave Helper

Review, migrate, and plan MATLAB or GNU Octave numerical code safely, with local inventory and scaffold tools

Source Download skill
Repository
K-Dense-AI/scientific-agent-skills
Stars
55,780
Licence
MIT
Files
15 files

What it does

Once installed, the agent reviews and writes MATLAB or GNU Octave code with safer defaults: explicit array shapes, input validation, reproducible projects, and careful handling of files it has not verified. It treats MATLAB and Octave as different products and asks which release and licence you actually have before assuming a feature works. It can also run small bundled Python tools that inventory MAT-file headers and generate function and test templates, without launching MATLAB or Octave.

Great for

  • Engineers and scientists migrating numerical MATLAB code to GNU Octave or to a newer MATLAB release
  • Developers who want MATLAB functions written with arguments-block validation and deterministic tests
  • Teams preparing reproducible projects with provenance records and pinned release notes

Skip it if

  • People who need the agent to actually run MATLAB or Octave code: the documentation examples were not executed, and the bundled tools never launch either product
  • Anyone opening untrusted .m, .mlx, MEX or MAT files on a machine with sensitive data, since the skill forbids running them but static review cannot prove they are safe
  • Users without a MATLAB licence who assume toolboxes are available; the skill explicitly says not to assume them

Try asking

  • “Review this MATLAB function for shape and validation problems and suggest an arguments block”
  • “Plan a migration of this numerical script from MATLAB R2026a to GNU Octave 11.3.0 and list compatibility gaps”
  • “Inventory the headers of this .mat file and report whether it is a v7.3 HDF5 file”
  • “Generate a function scaffold and matching unit-test skeleton for a new scaleSignal function”
Step-by-step guide: how to use MATLAB and Octave HelperInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 15 original files, the MIT licence and an attribution note.

    matlab.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip matlab.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip matlab.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Tell the agent your exact MATLAB release or Octave version, operating system, and which toolboxes you own, since it will treat availability as unknown otherwise
  • Review any MATLAB or Octave code the agent writes before running it yourself, because its examples were not executed during the skill's review
  • Keep test fixtures synthetic and project-local so results do not depend on your base workspace

What's inside

  • assets/project_manifest_template.json
  • assets/python_compatibility_r2026a.json
  • assets/reproducibility_manifest_template.json
  • references/data-import-export.md
  • references/executing-scripts.md
  • references/graphics-visualization.md
  • references/mathematics.md
  • references/matrices-arrays.md
  • references/octave-compatibility.md
  • references/programming.md
  • references/python-integration.md
  • scripts/_common.py
  • scripts/generate_function_scaffold.py
  • scripts/inventory_mat_file.py
  • SKILL.md

Redistributed unmodified from K-Dense-AI/scientific-agent-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.