Agent Skills Playground
May 28, 2026 · View on GitHub
A sandbox for prototyping and demonstrating Agent Skills for MATLAB and Simulink work. Skills here are experimental. They may be incomplete, change without notice, or migrate to an official toolkit over time.
For official skills, use Agentic Toolkits for MATLAB and Simulink:
- MATLAB Agentic Toolkit: Gives your AI agent the knowledge and context to work efficiently with MATLAB and its toolboxes
- Simulink Agentic Toolkit: Give your AI coding agent the ability to read, build, edit, and test Simulink® models using Model-Based Design best practices.
What this repo is for
- Prototyping: trying out new skill ideas.
- Demos: informal examples of what Agent Skills can do with MATLAB and Simulink.
Demos
| Demo | What it shows |
|---|---|
| engineering-an-agent-skill | A test-first process for authoring your own Agent Skills, with a meta-skill that walks an agent through the five stages. Accompanies the blog post. |
| mbse-with-agentic-ai | Agent-driven Model-Based Systems Engineering workflow in MATLAB and Simulink (RFLP methodology). Accompanies the blog post. |
| embedded-ai-deployment | Agent-driven deployment of AI models to embedded hardware with MATLAB, Simulink, and Embedded Coder. Routes between native models compressed for lean targets (Cortex-M, DSP) and direct C/C++ generation from PyTorch and LiteRT models for high-performance hardware. Requires MATLAB R2026a. |
| lorenz-uihtml-app | An interactive Lorenz attractor, built by an agent using the matlab-uihtml-app-builder and matlab-uihtml-design skills. An HTML control panel drives an ode45 integration, with animated tracing, live speed control, mid-run stop, and PNG export. |
About Agent Skills
Skills are modular, portable capabilities that work across coding agents:
- Composable: skills stack together automatically when needed.
- Efficient: skills only load when relevant to the current task.
- Executable: skills combine instructions with code, not just text.
See the Agent Skills specification for the file format.
Install a single skill
git clone https://github.com/matlab/agent-skills-playground.git
cp -r agent-skills-playground/skills/<skill-name> ~/.claude/skills/
For Claude.ai (web) and Claude Desktop, zip a skill's directory (with SKILL.md at the root) and upload it via Settings, then Capabilities, then Upload Skill.
For other agents, follow the host's instructions for installing user-defined skills.
Run a demo
git clone https://github.com/matlab/agent-skills-playground.git
cd agent-skills-playground/demos/<demo-name>
Each demo folder is self-contained: it bundles its own skills under skills/, a tutorial README, and any supporting files. Open the folder in your agent (for Claude Code, run claude from inside the folder) and follow the demo's README.
Skill development resources
- Official Skills Documentation
- Agent Skills Specification
- Agent Skills Repository
- Anthropic Skills Repository
- Claude Code Plugin Guide
Related projects
- matlab/matlab-agentic-toolkit: official MATLAB agent skills and live MATLAB session bridge.
- matlab/simulink-agentic-toolkit: official Simulink agent skills and Model-Based Design tooling.
- matlab/matlab-mcp-core-server: official MATLAB MCP server for AI applications.
- matlab/rules: MATLAB coding rules for AI coding assistants.
- matlab/prompts: curated AI prompts for MATLAB development.
- matlab/slash-commands: slash commands for MATLAB development in Claude Code.
License
Licensed under the MathWorks BSD-3-Clause License. See LICENSE.
Copyright (c) 2025-2026, The MathWorks, Inc. All rights reserved.
Community
- Issues: GitHub Issues
- Discussions: MATLAB Central GenAI Discussions
Supported coding agents: Agent Skills work with Claude Code, Claude.ai, Cursor, VS Code, GitHub Copilot, Gemini CLI, OpenAI Codex, Amp, Goose, Roo Code, and many more. Feature availability varies by plan and platform.