Agent skill

Matlab Evaluation

by isetbio in isetbio/isetbio

Run MATLAB non-interactively from a shell on this machine — locating the MATLAB binary, setting ISETCam/ISETBio paths for a batch session, and invoking -batch evaluation.

MITAuto-check passed

Install Matlab Evaluation

skills CLI
$ npx skills add isetbio/isetbio --skill matlab-evaluation -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install isetbio/isetbio matlab-evaluation --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/isetbio/isetbio.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.github/skills/matlab-evaluation .claude/skills/matlab-evaluation && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
matlab-evaluation
GitHub stars
115
Token cost
~568 tokens
SKILL.md length
235 words
Files
1
Skills in repo
9
Repo updated
First seen
Licence
MIT

At a glance

Run MATLAB non-interactively from a shell on this machine — locating the MATLAB binary, setting ISETCam/ISETBio paths for a batch session, and invoking -batch evaluation.

  • A shell command must execute MATLAB code
  • SKILL.md covers Finding Matlab, Running non-interactively and Working directory
  • Calls rg
  • Use matlab-testing to choose which tests to run

What it does

Matlab Evaluation is an agent skill from isetbio/isetbio. Run MATLAB non-interactively from a shell on this machine — locating the MATLAB binary, setting ISETCam/ISETBio paths for a batch session, and invoking -batch evaluation. Use when a shell command must execute MATLAB code, a test runner, or iePublish; use matlab-testing to choose which tests to run.

Its SKILL.md is about 570 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Tools for modeling image systems engineering in the human visual system front end. The licence is MIT.

When your agent uses it

  • A shell command must execute MATLAB code
  • Use matlab-testing to choose which tests to run

Example prompts

  • “/matlab-evaluation”

What it can do on your machine

Read from SKILL.md and the folder at commit d2924c2. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • rg

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Matlab Evaluation loads about 568 tokens when it runs. Until then it costs about 79 tokens; SKILL.md has 235 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~79
When it runs · the whole SKILL.md, loaded when a task matches
~568

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from isetbio/isetbio at commit d2924c2, republished under its MIT licence (© isetbio). 235 words, ~568 tokens.

Download SKILL.mdSave it as .claude/skills/matlab-evaluation/SKILL.md (or your agent's skills folder).
name
matlab-evaluation
description
Run MATLAB non-interactively from a shell on this machine — locating the MATLAB binary, setting ISETCam/ISETBio paths for a batch session, and invoking -batch evaluation. Use when a shell command must execute MATLAB code, a test runner, or iePublish; use matlab-testing to choose which tests to run.

Matlab Evaluation Workflow

Finding Matlab

MATLAB is not on $PATH on this machine, so call the executable by its full path. Installed releases live in /Applications as MATLAB_R20XXx.app bundles, with the executable at bin/matlab. List them rather than assuming a version, and use the newest unless the user specifies otherwise or it fails for a version-specific reason:

bash
ls /Applications | rg -i '^MATLAB_R'

Running non-interactively

Use -batch, not -r. -batch runs headless, still processes MATLAB's startup files, exits when the statement finishes, and returns a non-zero exit code with the error on stderr if the statement throws. -r needs an explicit exit and a try/catch to avoid hanging or masking failures. Check $? after the call; terminal text alone does not reliably signal failure.

bash
cd ~/Documents/MATLAB/isetbio
/Applications/MATLAB_R2026a.app/bin/matlab -batch "\
addpath(genpath('~/Documents/MATLAB/isetcam')); \
addpath(genpath('~/Documents/MATLAB/isetbio')); \
results = isetbioUnitTest;"
echo "exit: $?"

Personal startup.m path setup is usually guarded by usejava('desktop') and skipped in batch sessions, so add ISETCam and ISETBio explicitly as above. Add only the toolboxes the code needs; never addpath(genpath('~/Documents/MATLAB')), which mixes unrelated projects. Use which functionName to confirm resolution. Unrecognized function or variable usually means a missing path.

Scripts that call pause, input, keyboard, or waitfor block a batch session with nobody to answer. Run unfamiliar code with a time limit — the shell tool's own timeout; macOS has no timeout command unless coreutils is installed.

Working directory

-batch inherits the shell's working directory as MATLAB's pwd. iePublish and some scripts resolve relative paths and write output relative to pwd, so cd to the intended directory first.

© isetbio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .github/skills/matlab-evaluation of isetbio/isetbio.

Open the folder on GitHubat commit d2924c2

Compare with similar skills

Matlab Evaluation next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Matlab Evaluation compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Matlab Evaluation this skillisetbio/isetbio115—~568Automated safety check: PassMIT
MatlabK-Dense-AI/scientific-agent-skills48k1 repos~4.1kAutomated safety check: NotesMIT
Evaluating Machine Learning Modelsjeremylongshore/tons-of-skills-marketplace2.8k—~914Automated safety check: PassMIT
Arize Evaluatorgithub/awesome-copilot40k2 repos~8.1kAutomated safety check: NotesMIT
Matlab Interpret Machine Learning Modelmatlab/matlab-agentic-toolkit1.1k—~8.1kAutomated safety check: PassCustom licence
LLM Evaluationdavila7/claude-code-templates32k13 repos~3.5kAutomated safety check: PassMIT

Similar skills

  • Matlab

    K-Dense-AI/scientific-agent-skills

    Builds, reviews, migrates, and plans MATLAB or GNU Octave numerical workflows.

    48k GitHub starsUsed in 1 repo~4.1k tokens
    Research & ScienceAuto-check: notes
  • Evaluating Machine Learning Models

    jeremylongshore/tons-of-skills-marketplace

    Build this skill allows AI assistant to evaluate machine learning models using a comprehensive suite of metrics.

    2.8k GitHub stars~914 tokensUpdated today
    Data & AnalyticsAuto-check passed
  • Arize Evaluator

    github/awesome-copilot

    Official

    Handles LLM-as-judge evaluation workflows on Arize including creating/updating evaluators, running evaluations on spans or experiments, managing tasks, trigger-run operations, column mapping, and…

    40k GitHub starsUsed in 2 repos~8.1k tokens
    AI & LLM EngineeringAuto-check: notes
  • Matlab Interpret Machine Learning Model

    matlab/matlab-agentic-toolkit

    Interpret and explain a trained tabular machine-learning model (classification or regression) in MATLAB.

    1.1k GitHub stars~8.1k tokensUpdated today
    Data & AnalyticsAuto-check passed
  • LLM Evaluation

    davila7/claude-code-templates

    Master comprehensive evaluation strategies for LLM applications, from automated metrics to human evaluation and A/B testing.

    32k GitHub starsUsed in 13 repos~3.5k tokens
    AI & LLM EngineeringAuto-check passed
  • Agent Evaluation

    sickn33/agentic-awesome-skills

    Evaluate agent behavior with versioned cases and explicit verifiers.

    47k GitHub starsUsed in 1 repo~2k tokens
    Agent WorkflowsAuto-check passed

More from isetbio/isetbio

All 9 skills in this repo
  • Matlab Environment

    isetbio/isetbio

    Configure or troubleshoot a local MATLAB and VS Code environment for ISETBio.

    115 GitHub stars~558 tokensUpdated 12 days ago
    Auto-check passed
  • Matlab Testing

    isetbio/isetbio

    Develop, run, diagnose, or report ISETBio MATLAB tests. An agent skill from isetbio/isetbio.

    115 GitHub stars~884 tokensUpdated 12 days ago
    Auto-check passed
  • Retinal Mosaic Data

    isetbio/isetbio

    Work with ISETBio cone and midget-RGC mosaic data, including loading, generating, migrating, caching, or reviewing lattices, serialized cMosaics, pre-baked mRGCMosaics, and compute-ready mosaics.

    115 GitHub stars~1.5k tokensUpdated 12 days ago
    Auto-check passed
  • Create, move, review, publish, or test ISETBio tutorials, examples, and data-generation scripts.

    115 GitHub stars~560 tokensUpdated 12 days ago
    Auto-check passed
  • Sdr Mosaic Data

    isetbio/isetbio

    Create, publish, organize, or fetch the ISETBio retinal mosaic data deposit in the Stanford Digital Repository (SDR).

    115 GitHub stars~1.6k tokensUpdated 12 days ago
    Auto-check passed
  • Matlab Script Review

    isetbio/isetbio

    Review existing ISETBio MATLAB tutorial, example, or demo scripts without implementing behavior.

    115 GitHub stars~655 tokensUpdated 12 days ago
    Auto-check passed

Questions about Matlab Evaluation

What does Matlab Evaluation do?

Run MATLAB non-interactively from a shell on this machine — locating the MATLAB binary, setting ISETCam/ISETBio paths for a batch session, and invoking -batch evaluation. Matlab Evaluation is an agent skill from isetbio/isetbio. Run MATLAB non-interactively from a shell on this machine — locating the MATLAB binary, setting ISETCam/ISETBio paths for a batch session, and invoking -batch evaluation.

When should I use Matlab Evaluation?

Matlab Evaluation fits situations like: A shell command must execute MATLAB code; use matlab-testing to choose which tests to run.

How do I install Matlab Evaluation in Claude Code?

Run `npx skills add isetbio/isetbio --skill matlab-evaluation -a claude-code`. Or copy the skill folder (.github/skills/matlab-evaluation in isetbio/isetbio) into .claude/skills/matlab-evaluation in your project. Claude Code loads it when a task matches its description.

How do I install Matlab Evaluation in Codex?

Run `npx skills add isetbio/isetbio --skill matlab-evaluation -a codex`. Or copy the skill folder (.github/skills/matlab-evaluation in isetbio/isetbio) into .agents/skills/matlab-evaluation in your project. Codex loads it when a task matches its description.

Can I use Matlab Evaluation in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add isetbio/isetbio --skill matlab-evaluation -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/matlab-evaluation, .gemini/skills/matlab-evaluation, .github/skills/matlab-evaluation and .opencode/skills/matlab-evaluation in your project.

What does Matlab Evaluation need to run?

Going by SKILL.md and its folder, Matlab Evaluation needs the command-line tools its instructions call (rg).

Does Matlab Evaluation access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Matlab Evaluation safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Matlab Evaluation use?

Matlab Evaluation is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Matlab Evaluation use?

About 568 tokens (SKILL.md is roughly 2.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Matlab Evaluation?

Skills that share tags, products or a category with Matlab Evaluation: Matlab (K-Dense-AI/scientific-agent-skills, 48k stars), Evaluating Machine Learning Models (jeremylongshore/tons-of-skills-marketplace, 2.8k stars), Arize Evaluator (github/awesome-copilot, 40k stars) and Matlab Interpret Machine Learning Model (matlab/matlab-agentic-toolkit, 1.1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Matlab Evaluation?

isetbio (a GitHub organization) maintains it in isetbio/isetbio, which has 115 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on September 25, 2026.

Source: isetbio/isetbio on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.