matlab-use-machine-learning-apps
Use when the user wants to train, compare, or export machine learning models using Classification Learner or Regression Learner — including opening the app, loading data, training models, evaluating metrics, comparing results, visualizing plots, testing on held-out data, exploring model interpretability, and exporting trained models. Programmatic access to Classification Learner and Regression Learner apps via AppController.
npx skills add matlab/matlab-agentic-toolkit --skill matlab-use-machine-learning-apps --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill provides programmatic access to the Classification Learner and Regression Learner apps through AppController, enabling operations such as opening the apps, loading data, training models, evaluating metrics, comparing results, visualizing plots, testing on held-out data, exploring model interpretability, and exporting trained models.
How it works
- It references AppController at mlearnapp.internal.appcontroller.AppController to drive the learner apps and query their state.
- It exposes an API surface (load on demand) via links to files like api-session-and-models.md, api-metrics-and-options.md, api-plots.md, api-explainability.md, and api-export-and-diagnostics.md for: opening/closing/saving/loading apps, session setup, model creation/training/selection/deletion, model status, and metrics.
- It requires Statistics and Machine Learning Toolbox; optional Toolboxes may be needed for certain exports or deep learning models.
- Setup step instructs adding the skill’s scripts folder to MATLAB path with addpath('<skill-base-directory>/scripts').
- It outlines a User Goals Inquiry that gathers preferences before starting, including end goal, validation scheme, independent test data, performance targets, deployment constraints, and interpretability needs.
- It emphasizes best practices for data handling, feature selection, PCA, model comparison, and interpretability plots, and provides guidance on exporting and testing workflows.
When to use it
- When the user wants to train, compare, or export models using Classification Learner or Regression Learner.
- When the user asks to open or automate the learner apps.
- When interactive comparisons across model types with validation metrics are needed, or testing on held-out data with export is required.
What it can touch
- It interacts with MATLAB applications via AppController and associated API reference documents listed for models, metrics, plots, explainability, and export/diagnostics.
- It requires MATLAB toolboxes as specified (Statistics and Machine Learning Toolbox as required; optional toolboxes for parallel training, deep learning, Simulink, coder, etc.).
Caveats
- Important: Do not expose the API to users; drive the app silently. Do not mention AppController or automation APIs to users. Avoid closing the app forcefully without user permission using closeApp('Force', true).
- The skill’s guidance includes explicit constraints about training, testing, and export paths, and notes about when to use or avoid the app.
# Learner Apps AppController Reference `mlearnapp.internal.appcontroller.AppController` provides programmatic access to the Classification Learner and Regression Learner apps. Use it to interact with learner apps and query their state. Source (loaded at runtime): `<skill-base-directory>/scripts/+mlearnapp/+internal/+appcontroller/AppController.p` ### API Reference (load on demand) | When you need... | Load this file | |------------------|---------------| | Open/close/save/load app, session setup, create/train/select/delete models, model status, GalleryModels enum | [`api-session-and-models.md`](references/api-session-and-models.md) | | Metrics, model spec queries, toolstrip buttons, set feature selection/PCA/optimizer/cost/hyperparameters | [`api-metrics-and-options.md`](references/api-metrics-and-options.md) | | Open/configure standard plots, results table, standard plot data getters | [`api-plots.md`](references/api-plots.md) | | PDP, permutation importance, Shapley, LIME, Set Shapley Parameters, explainability plot data getters | [`api-explainability.md`](references/api-explainability.md) | | Export methods, command logging, diagnostics | [`api-export-and-diagnostics.md`](refere
- API Reference (load on demand)
- When to Use
- When NOT to Use
- IMPORTANT
- Setup
- User Goals Inquiry
- Best Practices
- Data & Setup
- Feature Engineering
- Model Training & Selection
- Evaluation & Interpretability
- Session & Code Export
- Deployment Export
- Minimum Release Requirements
What does the matlab-use-machine-learning-apps skill do?
Use when the user wants to train, compare, or export machine learning models using Classification Learner or Regression Learner — including opening the app, loading data, training models, evaluating metrics, comparing results, visualizing plots, testing on held-out data, exploring model interpretability, and exporting trained models. Programmatic access to Classification Learner and Regression Learner apps via AppController.
How do I install it?
Run `npx skills add matlab/matlab-agentic-toolkit --skill matlab-use-machine-learning-apps --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From matlab/matlab-agentic-toolkit, a repository with 868 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.