Finding Simulink Examples logo

Finding Simulink Examples

OrganizationPopular
matlab
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.

Overview

Publishermatlab
Repositorysimulink-agentic-toolkit
Skill namefinding-simulink-examples
Stars
1.2K
Forks
112
Bundled files
2
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 2 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by matlab on GitHub. Read the source before you install it.

Installation

Install the Finding Simulink Examples AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/matlab/simulink-agentic-toolkit/tree/main/skills-catalog/simulink-environment-fundamentals/finding-simulink-examples
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/matlab/simulink-agentic-toolkit.git /tmp/simulink-agentic-toolkit
mkdir -p .claude/skills
cp -r /tmp/simulink-agentic-toolkit/skills-catalog/simulink-environment-fundamentals/finding-simulink-examples .claude/skills/finding-simulink-examples
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Finding Simulink Examples in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Finding Simulink Examples on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Finding Simulink Examples is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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):

matlab
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.


Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Finding Simulink Examples AI skill do?

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

Why use Finding Simulink Examples on TypingMind?

Because you install it once and use it with any model. Finding Simulink Examples is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Finding Simulink Examples in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/matlab/simulink-agentic-toolkit/tree/main/skills-catalog/simulink-environment-fundamentals/finding-simulink-examples. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Finding Simulink Examples?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Finding Simulink Examples?

As many as you like. As long as a model supports skills, you can use Finding Simulink Examples with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Finding Simulink Examples AI skill free?

It is published on GitHub by matlab. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇