跳至正文
OpenAgentSkill
浏览已开放 · 目录记录日期 2026-11-21 · 自动更新和账户服务暂时关闭。
AI 与知识库

simulink-create-course-activity

Create MATLAB Course Designer Simulink Exercise learning activities with starter and solution Simulink model files. Use when the user asks to create a Simulink activity, Simulink Exercise, starter model, solution model, model-based learning activity, or Course Designer-ready Simulink artifact. Uses MATLAB MCP Server tool calls and Simulink Agentic Toolkit guidance to create, inspect, edit, simulate, and validate model files.

matlab · 已有 AI 审核记录

安装与使用

运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。

npx skills add matlab/agent-skills-playground --skill simulink-create-course-activity

技能说明


name: simulink-create-course-activity description: Create MATLAB Course Designer Simulink Exercise learning activities with starter and solution Simulink model files. Use when the user asks to create a Simulink activity, Simulink Exercise, starter model, solution model, model-based learning activity, or Course Designer-ready Simulink artifact. Uses MATLAB MCP Server tool calls and Simulink Agentic Toolkit guidance to create, inspect, edit, simulate, and validate model files. license: MathWorks BSD-3-Clause (see LICENSE) metadata: author: MathWorks version: "1.0"

Simulink Course Activity Generator

Create MATLAB Course Designer-ready Simulink Exercise learning activities. The skill must produce actual starter and solution model files, not only instructions. Use MATLAB MCP Server tool calls, following Simulink Agentic Toolkit guidance, to create, edit, inspect, and validate the models. The resulting activity folder should be ready for Course Designer web application import workflows, with course-designer-activity.json as the import-oriented metadata sidecar.

Input

The user may have provided a module objective or activity idea in their request. If it is missing or too vague, collect the missing activity inputs in Step 1.

Reference Files

Read these references from the references/ directory as needed:

  • references/model-generation-workflow.md — starter/solution model workflow
  • references/course-designer-artifacts.md — output folder and metadata rules
  • references/validation-rules.md — validation and review gates

Read references/model-generation-workflow.md and references/course-designer-artifacts.md before creating model files.

Required Tooling

Use Simulink Agentic Toolkit guidance for model construction and inspection. When editing models, follow the building-simulink-models workflow:

  1. Use model_read or model_overview before edits when a model exists.
  2. Use model_edit for structural edits and parameter configuration. Treat a status: partial result as a failure until every reported parameter rejection is resolved and the intended values are confirmed with model_query_params; a partial edit can leave a block at a silently wrong default that model_read and model_check do not surface.
  3. Use model_read, model_overview, and model_query_params to verify.
  4. Use MATLAB MCP calls such as evaluate_matlab_code, run_matlab_file, check_matlab_code, and detect_matlab_toolboxes for model setup scripts, toolbox checks, simulation smoke tests, and file existence checks.
  5. Use model_test for behavioral tests when a Gherkin validation spec is created, the testing workflow is available, and the model exposes at least one Inport; otherwise use the matlab.unittest fallback in references/validation-rules.md.

The building-simulink-models workflow starts with custom-library gates. For course activities built from base MATLAB and Simulink blocks, answer the custom-library question with "none" and keep the resulting .satk/ configuration in the course output folder, not in this skill package.

Do not rely on prose-only model descriptions for final artifacts.

Pipeline Overview

Step 1: Collect activity inputs and Course Designer placement
Step 2: Confirm products, toolboxes, and output folder
Step 3: Create the solution model with MCP tool calls
Step 4: Create the starter model from the solution model
Step 5: Validate solution and starter models
Step 6: Write Course Designer-ready activity metadata and review notes

Step 1: Activity Inputs

Collect only missing information:

  • Course title or course identifier
  • Module title and module order
  • Learning activity title and activity order
  • Module objective and observable learner outcome
  • Simulink concept: modeling, simulation, controls, physical modeling, verification, code generation, or another domain
  • Learner task and expected model behavior
  • Required MATLAB, Simulink, and toolbox products
  • Starter model scope: what should be missing, incomplete, or configurable
  • Solution model scope: complete expected behavior
  • Validation requirements: simulation output, signal behavior, parameter values, model structure, or manual rubric
  • Output directory

Default to a Course Designer learning activity type of Simulink Exercise.

Step 2: Product and Output Checks

Use detect_matlab_toolboxes when available to confirm MATLAB, Simulink, and required toolbox access. If a needed toolbox is missing, stop before creating a misleading model and report the blocked requirement.

Create or use this output folder:

simulink-activities/module-NN-activity-MM-[slug]/

All generated file names must be stable, lowercase, and Course Designer import friendly.

Step 3: Create Solution Model

Use references/model-generation-workflow.md.

Create the complete solution model first. The solution model is the instructor reference and the source used to derive the starter model.

Required actions:

  1. Create or open the model using MATLAB MCP calls.
  2. Use model_edit for blocks, connections, parameters, model configuration, and subsystem structure.
  3. Use model_read or model_overview to verify topology.
  4. Save the model as:
[activity-slug]_solution.slx

Step 4: Create Starter Model

Create the starter model from the validated solution model. Remove, mask, disable, parameterize, or replace only the parts learners are expected to complete.

Required actions:

  1. Copy or save the solution model as:
[activity-slug]_starter.slx
  1. Use model_edit to create the intended learner gaps.
  2. Use model_read or model_overview to confirm the starter model still opens and contains the expected scaffold.
  3. Do not leave broken model references, missing files, or unresolved variables unless they are explicitly part of the learner task.

Step 5: Validate Models

Use references/validation-rules.md.

At mi

阅读完整来源 ↗