Simulink Control Motors

OrganizationPopular

matlab

simulink-control-motors

Build motor control solutions using Motor Control Blockset for PMSM, induction motors, BLDC, and SynRM. Implement field oriented control, sensorless FOC, six-step control, speed control, current control, and torque control. Configure SVPWM, flux weakening, MTPA, MTPV, control of non-linear motors, inverter control, and motor parameter estimation. Compose motor drive models, tune gains, and generate embedded code.

Overview

Publisher	matlab
Repository	`simulink-agentic-toolkit`
Skill name	`simulink-control-motors`
Stars	1.2K
Forks	112
Bundled files	64
Links	Skill source Repository

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.
64 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 Simulink Control Motors AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/matlab/simulink-agentic-toolkit/tree/main/skills-catalog/control-systems/simulink-control-motors
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/matlab/simulink-agentic-toolkit/tree/main/skills-catalog/control-systems/simulink-control-motors

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/control-systems/simulink-control-motors .claude/skills/simulink-control-motors

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Simulink Control Motors 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 Simulink Control Motors 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 Simulink Control Motors 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.

Simulink Control Motors — Motor Control Blockset Skill

Build motor control solutions using Motor Control Blockset (MCB): characterize motors, select control algorithms (FOC, DTC, six-step, V/f), compose Simulink models, tune gains, configure sensorless estimation, and generate code for embedded targets.

When to Use

User explicitly requests motor control assistance or asks to load this skill
User works with Motor Control Blockset or motor drive design
Building, tuning, debugging, or designing motor control systems
User mentions PMSM, BLDC, induction motor, SynRM, FOC, sensorless, six-step, SVPWM, flux weakening, MTPA, MTPV

When NOT to Use

General Simulink modeling work that does not involve motor control
Simple factual questions about motors (no model building needed)

Dependencies

Required: Motor Control Blockset, Simulink
Optional: Embedded Coder, Simscape Electrical, Powertrain Blockset

How This Skill Works

Read references/common/COMMON-mcb.md (shared conventions — always load first)
Read references/common/ROUTER-mcb.md for block routing and resolution rules
Identify user intent using the routing table below
Follow the matching section — each section points to detailed reference files
Consult references/configurations/ for non-FOC architectures (DTC, six-step, V/f, BLDC, ACIM)
Use references/common/mcb-examples.md for official MCB example references

Intent Routing

User Intent	Section	Key Reference
New to MCB / learning	Designing	`references/design/beginner-path.md`
What pattern for my application?	Designing	`references/design/application-catalog.md`
Build a new model	Building	`references/wiring/wiring-topologies.md`
Configure block parameters	Configuring	`references/block-config/block-configurations.md`
Compute PI gains / tune	Tuning	`references/common/detailed-workflows.md` § Tuning
Generate LUT / FEA data	Nonlinear Data	`references/common/detailed-workflows.md` § Importing
Add sensorless (SMO, HFI)	Sensorless	`references/common/detailed-workflows.md` § Sensorless
Estimate Rs, Ld, Lq, J	Parameters	`references/common/detailed-workflows.md` § Estimating
Convert plant (MCB→Simscape)	Plant	`references/common/detailed-workflows.md` § Plant
Model errors / doesn't move	Diagnosing	`references/common/detailed-workflows.md` § Diagnosing
End-to-end workflow	—	`references/workflows/` directory

Quick Decision

User describes an application → Designing
User says "build" → Building
User has an error → Diagnosing
User wants to tune gains → Tuning
User has FEA/LUT data → Nonlinear Data
User wants sensorless → Sensorless
User wants Simscape plant → Plant

Designing Motor Control

Recommends control strategies, selects patterns, evaluates feature compatibility.

Load: references/design/beginner-path.md for enquiry protocol and learning paths.

Detect mode (Learn / Select / Validate / Enquiry) — see references/design/beginner-path.md
Search references/design/application-catalog.md by user's keywords → get Pattern + Features
Validate combination against references/design/composition-rules-combining.md
Review architecture details in references/design/architecture-patterns.md

Critical rules:

NEVER recommend Pattern A for speed control (structural instability with MCB discrete plant)
NEVER recommend Sensorless Six-Step + BLDC AVI together
Pattern B is the DEFAULT for standard speed-controlled FOC

Output: basePattern + features + motorType + controlMode → carry to Building section.

Building Motor Controller

Constructs complete models using wiring topologies, composition rules, and model_edit.

Step 1: Check for a Dedicated Configuration

BEFORE using generic wiring tables, check references/configurations/ for a matching file:

Architecture	Configuration File
ACIM Indirect RFOC	`references/configurations/acim-indirect-rfoc.md`
ACIM Simscape RFOC	`references/configurations/acim-simscape-rfoc.md`
ACIM V/f Open-Loop	`references/configurations/acim-vf-openloop.md`
BLDC Hall Six-Step	`references/configurations/bldc-hall-sixstep.md`
BLDC Sensorless BEMF	`references/configurations/bldc-sensorless-bemf.md`
DTC (SVPWM)	`references/configurations/dtc-svpwm-pmsm.md`
Nonlinear Gain-Scheduled	`references/configurations/nonlinear-gain-scheduled.md`
Position Cascade FOC	`references/configurations/position-cascade-foc.md`
Overmodulation FOC	`references/configurations/overmodulation-foc.md`
HFI+SMO Hybrid	`references/configurations/hfi-smo-hybrid.md`
Dual Motor Sync	`references/configurations/dual-motor-sync.md`
Wind Turbine PMSG	`references/configurations/wind-turbine-pmsg.md`
ADRC Speed	`references/configurations/adrc-speed.md`
Backstepping Speed	`references/configurations/backstepping-speed.md`
Deadbeat Current	`references/configurations/deadbeat-current.md`
Sliding Mode Speed	`references/configurations/sliding-mode-speed.md`

If a config file exists: follow it directly. Otherwise: proceed to Step 2.

Step 2: Generic FOC Wiring

Pattern	Document
A, A+FF, A+PWM, B, B-Simple, C	`references/wiring/wiring-topologies.md`
D, E, F, G, H	`references/wiring/wiring-topologies-advanced.md`

Step 3: Add Features

Core (FW, SMO, GainSched, FF, Position, I/f): references/wiring/composition-rules.md
Infrastructure (Protection, PWM, Multi-Rate): references/wiring/composition-rules-infrastructure.md
Integration (Logging, Speed Profiles): references/wiring/composition-rules-integration.md

Step 4: Set Structural Config

PI: ControllerParametersSource='internal', ExternalReset='none', InitialConditionSource='internal'
Park: ThetaInput='Electrical position', AngleInput='Radians'
Unit Delay on voltage path to plant

Key rules:

Always check references/configurations/ FIRST
Use wiring-topologies.md block lists verbatim (type strings are validated)
Composition-rules operations are STRUCTURAL (affect port count) — do during wiring
All structural changes go through model_edit

Configuring MCB Blocks

Sets mask parameters for 30+ MCB block types using motor datasheet values.

Reference files:

references/block-config/block-configurations.md — control blocks
references/plants/block-configurations-plants.md — plant/sensor blocks
references/block-config/block-configurations-utility.md — utility blocks
references/block-config/block-configurations-bldc.md — BLDC blocks

Critical configurations (must get right):

Block	Critical Setting	Wrong Default
FOC CC	Port 6 VLimits = `[Vmax;-Vmax;0;0]`	q-axis non-zero → drift
SMO	`PositionUnit='Radians'`	Default 'Degrees' → 57× error
Interior PMSM	`P` = pole pairs (not 2×p)	Double frequency → zero torque
LUT Control Ref	Hidden params: MTPA, FW enable	Defaults leave FW disabled

Key rules:

Mask param names ≠ motor struct fields — always check reference table
Use model_edit configure for setting parameters
Single-precision plant outputs need DTC blocks before double-precision control

Tuning Motor FOC Gains

Computes PI gains, IIR filters, and PU normalization.

Full workflow: references/common/detailed-workflows.md § Tuning Motor FOC Gains

Quick summary: Use mcb.calcFOCGains(pmsm, inverter, Ts, Ts_speed) for all categories except Category A (kt/J > 10,000) which needs manual Ki_speed override. MCB uses Ki×Ts convention — never pass raw Ki.

Reference files: references/tuning/parameter-computation.md, references/shared/gain-formulas.md

Importing Nonlinear Motor Data

Generates and validates LUTs from FEA/measurement data.

Full workflow: references/common/detailed-workflows.md § Importing Nonlinear Motor Data

Quick summary: Use mcb.generateMotorLUT(pmsm, inverter, purpose) with correct purpose string. Validate trefVec symmetry and FluxDTable first row = 0.

Reference files: references/nonlinear-data/pmsmlut-structure.md

Building Motor Plant

Converts between MCB ideal plants, Simscape, and FEM-parameterized models.

Full workflow: references/common/detailed-workflows.md § Building Motor Plant

Quick summary: Solver must change to ode14x for Simscape. Add angle adapter Gain(1/(2*pi)). Gains need re-tuning after plant swap.

Reference files: references/plants/plant-model-converters.md, references/plants/block-configurations-plants.md

Estimating Motor Parameters

Commissioning workflows for Rs, Ld, Lq, FluxPM, J, B.

Full workflow: references/common/detailed-workflows.md § Estimating Motor Parameters

Quick summary: Estimate in order: Rs → Ld/Lq → FluxPM → J/B. Motor must be stationary for Rs and Ld/Lq. Feed results into mcb.calcFOCGains.

Reference files: references/estimation/estimation-procedures.md, references/estimation/estimation-to-tuning.md

Estimating Sensorless Motor Position

Configures I/F startup, SMO, HFI, EEMF observers, and handoff logic.

Full workflow: references/common/detailed-workflows.md § Estimating Sensorless Motor Position

Quick summary: SPM → SMO + I/F. IPM → HFI + SMO hybrid. ACIM → Flux Observer + I/F. Always set SMO PositionUnit='Radians'.

Reference files: references/sensorless/sensorless-blocks.md, references/sensorless/hfi-scheduler.md

Diagnosing Motor Control

Diagnoses errors, oscillations, zero-torque using structured checklists.

Full workflow: references/common/detailed-workflows.md § Diagnosing Motor Control

Quick summary: Identify symptom → run matching checklist → apply fix from auto-fix-recipes → validate. Never rebuild from scratch.

Reference files: references/diagnostics/auto_fix/ERROR_PATTERNS.md, references/diagnostics/auto_fix/auto-fix-recipes.md, references/diagnostics/model-sanity-check.md

Bundled files

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

and 4 more files.

Frequently asked questions

What does the Simulink Control Motors AI skill do?

Why use Simulink Control Motors on TypingMind?

Because you install it once and use it with any model. Simulink Control Motors 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 Simulink Control Motors in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/matlab/simulink-agentic-toolkit/tree/main/skills-catalog/control-systems/simulink-control-motors. 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 Simulink Control Motors?

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 Simulink Control Motors?

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

Is the Simulink Control Motors 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

Graincrawl

openclaw

OrganizationPopular

Granola archive: search, sync freshness, notes, transcripts, panels, SQL counts, and Graincrawl repo work.

Openclaw Changelog Update

openclaw

OrganizationPopular

Regenerate OpenClaw release changelog sections from git history before beta, stable, or extended-stable releases.

Openclaw Ci Limits

Manage OpenClaw GitHub Actions and Blacksmith CI capacity, runner-registration budgets, fanout caps, main-push single-flight, shard sizing, hosted-runner offload, queue health, and safe…

Openclaw Debugging

Debug OpenClaw model, provider, tool-surface, code-mode, streaming, and live/Crabbox behavior by choosing the right logs, probes, and proof path before changing code, including fetching stored…

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Simulink Control Motors — Motor Control Blockset Skill

When to Use

When NOT to Use

Dependencies

How This Skill Works

Intent Routing

Quick Decision

Designing Motor Control

Building Motor Controller

Step 1: Check for a Dedicated Configuration

Step 2: Generic FOC Wiring

Step 3: Add Features

Step 4: Set Structural Config

Configuring MCB Blocks

Tuning Motor FOC Gains

Importing Nonlinear Motor Data

Building Motor Plant

Estimating Motor Parameters

Estimating Sensorless Motor Position

Diagnosing Motor Control

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now