{"id":50843012,"url":"https://github.com/matlab/agent-skills-playground","last_synced_at":"2026-06-14T07:35:49.400Z","repository":{"id":325480876,"uuid":"1083220669","full_name":"matlab/agent-skills-playground","owner":"matlab","description":"A sandbox for prototyping and demonstrating Agent Skills for MATLAB and Simulink work. ","archived":false,"fork":false,"pushed_at":"2026-06-05T00:56:22.000Z","size":437,"stargazers_count":125,"open_issues_count":0,"forks_count":31,"subscribers_count":9,"default_branch":"main","last_synced_at":"2026-06-14T07:35:46.231Z","etag":null,"topics":["agent-skill","agent-skills","agentic-ai","agents","claude","claude-api","claude-code","claude-desktop","claude-skills","matlab","matlab-skills","simulink"],"latest_commit_sha":null,"homepage":"https://www.mathworks.com/matlabcentral/discussions/ai","language":"HTML","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/matlab.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-10-25T15:28:46.000Z","updated_at":"2026-06-13T03:40:30.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/matlab/agent-skills-playground","commit_stats":null,"previous_names":["matlab/skills","matlab/agent-skills-playground"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/matlab/agent-skills-playground","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab%2Fagent-skills-playground","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab%2Fagent-skills-playground/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab%2Fagent-skills-playground/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab%2Fagent-skills-playground/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/matlab","download_url":"https://codeload.github.com/matlab/agent-skills-playground/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matlab%2Fagent-skills-playground/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":34313515,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-14T02:00:07.365Z","response_time":62,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["agent-skill","agent-skills","agentic-ai","agents","claude","claude-api","claude-code","claude-desktop","claude-skills","matlab","matlab-skills","simulink"],"created_at":"2026-06-14T07:35:47.087Z","updated_at":"2026-06-14T07:35:49.391Z","avatar_url":"https://github.com/matlab.png","language":"HTML","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Agent Skills Playground\n\nA sandbox for prototyping and demonstrating [Agent Skills](https://agentskills.io) for MATLAB and Simulink work. Skills here are experimental. They may be incomplete, change without notice, or migrate to an official toolkit over time.\n\n\u003e **For official skills, use Agentic Toolkits for MATLAB and Simulink:**\n\u003e\n\u003e - **[MATLAB Agentic Toolkit](https://github.com/matlab/matlab-agentic-toolkit)**: Gives your AI agent the knowledge and context to work efficiently with MATLAB and its toolboxes\n\u003e - **[Simulink Agentic Toolkit](https://github.com/matlab/simulink-agentic-toolkit)**: Give your AI coding agent the ability to read, build, edit, and test Simulink® models using Model-Based Design best practices.\n\n## What this repo is for\n\n- **Prototyping**: trying out new skill ideas.\n- **Demos**: informal examples of what Agent Skills can do with MATLAB and Simulink.\n\n## Demos\n\n| Demo | What it shows |\n|---|---|\n| **[engineering-an-agent-skill](demos/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](https://blogs.mathworks.com/matlab/2026/05/11/how-to-engineer-an-ai-skill-for-matlab/). |\n| **[mbse-with-agentic-ai](demos/mbse-with-agentic-ai/)** | Agent-driven Model-Based Systems Engineering workflow in MATLAB and Simulink (RFLP methodology). Accompanies the [blog post](https://blogs.mathworks.com/simulink/2026/04/26/model-based-systems-engineering-and-agentic-ai/). |\n| **[embedded-ai-deployment](demos/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. |\n| **[lorenz-uihtml-app](demos/lorenz-uihtml-app/)** | An interactive Lorenz attractor, built by an agent using the [`matlab-uihtml-app-builder`](skills/matlab-uihtml-app-builder/) and [`matlab-uihtml-design`](skills/matlab-uihtml-design/) skills. An HTML control panel drives an `ode45` integration, with animated tracing, live speed control, mid-run stop, and PNG export. |\n\n## About Agent Skills\n\nSkills are modular, portable capabilities that work across coding agents:\n\n- **Composable**: skills stack together automatically when needed.\n- **Efficient**: skills only load when relevant to the current task.\n- **Executable**: skills combine instructions with code, not just text.\n\nSee the [Agent Skills specification](https://agentskills.io/specification) for the file format.\n\n## Install a single skill\n\n```bash\ngit clone https://github.com/matlab/agent-skills-playground.git\ncp -r agent-skills-playground/skills/\u003cskill-name\u003e ~/.claude/skills/\n```\n\nFor 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**.\n\nFor other agents, follow the host's instructions for installing user-defined skills.\n\n## Run a demo\n\n```bash\ngit clone https://github.com/matlab/agent-skills-playground.git\ncd agent-skills-playground/demos/\u003cdemo-name\u003e\n```\n\nEach 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.\n\n## Skill development resources\n\n- [Official Skills Documentation](https://code.claude.com/docs/en/skills)\n- [Agent Skills Specification](https://agentskills.io/specification)\n- [Agent Skills Repository](https://github.com/agentskills/agentskills)\n- [Anthropic Skills Repository](https://github.com/anthropics/skills)\n- [Claude Code Plugin Guide](https://code.claude.com/docs/en/plugins)\n\n## Related projects\n\n- [matlab/matlab-agentic-toolkit](https://github.com/matlab/matlab-agentic-toolkit): official MATLAB agent skills and live MATLAB session bridge.\n- [matlab/simulink-agentic-toolkit](https://github.com/matlab/simulink-agentic-toolkit): official Simulink agent skills and Model-Based Design tooling.\n- [matlab/matlab-mcp-core-server](https://github.com/matlab/matlab-mcp-core-server): official MATLAB MCP server for AI applications.\n- [matlab/rules](https://github.com/matlab/rules): MATLAB coding rules for AI coding assistants.\n- [matlab/prompts](https://github.com/matlab/prompts): curated AI prompts for MATLAB development.\n- [matlab/slash-commands](https://github.com/matlab/slash-commands): slash commands for MATLAB development in Claude Code.\n\n## License\n\nLicensed under the MathWorks BSD-3-Clause License. See [LICENSE](LICENSE).\n\nCopyright (c) 2025-2026, The MathWorks, Inc. All rights reserved.\n\n## Community\n\n- **Issues**: [GitHub Issues](https://github.com/matlab/agent-skills-playground/issues)\n- **Discussions**: [MATLAB Central GenAI Discussions](https://www.mathworks.com/matlabcentral/discussions/ai)\n\n---\n\n**Supported coding agents**: Agent Skills work with [Claude Code](https://claude.ai/code), [Claude.ai](https://claude.ai), [Cursor](https://cursor.com), [VS Code](https://code.visualstudio.com), [GitHub Copilot](https://github.com), [Gemini CLI](https://geminicli.com), [OpenAI Codex](https://developers.openai.com/codex), [Amp](https://ampcode.com), [Goose](https://block.github.io/goose), [Roo Code](https://roocode.com), and [many more](https://agentskills.io). Feature availability varies by plan and platform.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatlab%2Fagent-skills-playground","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmatlab%2Fagent-skills-playground","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatlab%2Fagent-skills-playground/lists"}