Skip to content
cccskills
FreePublished on GitHub

finding-simulink-examples

Find, show, open, or identify shipped MathWorks example models that demonstrate a concept, block, or application domain, and return the command to open them.

The English summary is being prepared. Showing the original description.

See how to install

Files included (3)

  • SKILL.md4.4 KB
  • manifest.yaml672 B
  • scripts/invokeModelFinder.p5.1 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Finding Simulink Examples

Use this skill to find examples and models in the MathWorks Examples database.

Use the invokeModelFinder helper script to search the database of shipped MathWorks example models, then report matching examples.

invokeModelFinder searches a database of every example MathWorks ships across all products. It is a database search, not a scan of the local disk: a hit means the example exists in the MathWorks database and comes with the command to open it, regardless of what is currently open or saved locally. Opening a match requires the owning product to be installed; the returned open_command (e.g. openExample(...)) handles that.

invokeModelFinder is a helper script that ships with this skill in its scripts/ folder. It exists because the customer-facing modelfinder function is interactive — it opens a Selection: menu in the terminal and blocks, so it cannot be driven programmatically. invokeModelFinder is a thin, non-interactive wrapper that returns results directly. Call it with evaluate_matlab_code, setting project_path to the skill's scripts/ folder so MATLAB can resolve the function (never use addpath):

invokeModelFinder('<query>', '<filters_json>', '<max_results>', '<view>')
  • query — free-text search. Examples: 'motor control', 'PID', 'battery'; '*' lists everything.
  • filters_json — JSON object of optional filters. Fields: match, product, location, block, reference. Use '{}' for no filters. Example: '{"product": "Simscape Electrical", "block": "PID Controller"}'.
  • max_results — max results to return, as a string. Default '20', clamped to 100.
  • view — result layout. 'Categorized' (default) groups examples with their supporting models and surfaces the example-level openExample(...) command — best when the user wants an example to open. 'Models' lists the underlying model files individually — use it when the user wants a specific model file rather than the example that contains it. Omit it to get 'Categorized'.

It returns a YAML string with each match's name, open_command, and description. Use the open_command to open a result for inspection.

Treat the search behavior as a black box: don't assume how it ranks or combines terms.

Refining your search. If a query returns too many or off-target matches, narrow it rather than scanning a long list — re-run with a more specific query, or add filters_json fields to scope the results (product to a single product, block to a specific block, reference to models that reference a given model). Conversely, if a query returns nothing, loosen it: drop filters or use fewer, more general terms.

Older releases: the filters and view options were added in R2025a. Before R2025a the helper ignores both and runs a plain keyword search — still pass all four arguments; the helper degrades gracefully on its own.

When to Use

  • The user asks you to find, show, or open a shipped example model
  • The user wants you to point them at an example that demonstrates a concept or domain
  • You need to identify which shipped example matches a description before doing anything with it

This skill searches shipped MathWorks examples, not the user's own project models. It does not find, list, or open models in the user's working directory or open project.

Using the Result

  • Present the matches as a table with three columns:
    • Name — the example/model name.
    • Open command — the returned open_command, verbatim, so the user can run it as-is.
    • Description — a short, concise summary (roughly one sentence) of what the example does; trim the returned description down rather than pasting it in full.
  • Offer to open a match with its open_command if the user wants to view it.
  • Treat every match as read-only. Inspect it, but never edit, delete, or save_system onto a shipped example. If the user wants to change one, save it under a new filename first and work on the copy.

Copyright 2026 The MathWorks, Inc.


Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

Author or upgrade Model Advisor checks for Simulink and System Composer models. Covers the full lifecycle: guideline authoring, check specification, Model Advisor check implementation, and qualification testing. Use when creating new checks (edit-time, standard batch, config-parameter, auto-fix), converting legacy StyleOne/StyleTwo/StyleThree checks to modern DetailStyle, creating a guideline for modeling, enforcing a modeling rule, or testing/qualifying a check. Triggers on any modeling constraint (e.g., "blocks shall...", "signals must match...", "parameters shall be set to...").

The English summary is being prepared. Showing the original description.

matlab/simulink-agentic-toolkit1.2KUpdated Oct 15, 2026

Synthesize new waveforms from scratch for Simulink inports using createInputDataset. Use ONLY when the user asks to generate, create, or synthesize signals (step, ramp, sine, chirp, pulse, noise) to populate a Dataset for External Inputs or Signal Editor. Covers timeseries and timetable formats with correct data type, interpolation, units, and dimensions. Also covers function-call and trigger inport timing setup. Do NOT use when the user wants to load, import, or read existing data from files (MAT, CSV, spreadsheet) — even if that data will be used as model input. Do NOT use for running simulations or plotting outputs.

The English summary is being prepared. Showing the original description.

matlab/simulink-agentic-toolkit1.2KUpdated Oct 15, 2026

Common steps for building multi-layer system architecture models using System Composer. Use when implementing architecture models or when interacting with interface dictionaries, allocation sets, stereotypes, and requirements for architecture components.

The English summary is being prepared. Showing the original description.

matlab/simulink-agentic-toolkit1.2KUpdated Oct 15, 2026

Builds and edits Simulink, System Composer, Stateflow, and Simscape models. Use when modifying model structure, parameters, ports, connections, or Stateflow chart internals.

The English summary is being prepared. Showing the original description.

matlab/simulink-agentic-toolkit1.2KUpdated Oct 15, 2026

Use this skill when the user asks to check Simulink model compliance against a standard (MISRA, MAB, JMAAB, ISO, DO, IEC, EN, CERT C/CWE, AUTOSAR, Simulink Code Inspector (SLCI)), wants to run Model Advisor checks, or needs a compliance report with fix suggestions. For JMAAB/MAB, supplement deterministic checks with agentic review of uncheckable guidelines.

The English summary is being prepared. Showing the original description.

matlab/simulink-agentic-toolkit1.2KUpdated Oct 15, 2026

Guide users through creating and managing .satk/block-policy.json for controlling which blocks the agent can use, which are excluded, and which block parameters the agent should not modify. Use when setting up block usage policy for a project.

The English summary is being prepared. Showing the original description.

matlab/simulink-agentic-toolkit1.2KUpdated Oct 15, 2026

See all skills by matlab

Report a problem with this skill