wzyn20051216/matlab-agent-skills / skills/matlab-orchestrator
matlab-orchestrator
VerifiedMATLAB agentic workflow router. Use this whenever the user asks for MATLAB, Simulink, .m/.mlx/.slx work, toolbox-driven engineering, paper reproduction, simulation, code generation, data analysis, control, robotics, signal/image/AI workflows, or wants an end-to-end automated MATLAB task with validation. For Simulink tasks on this machine, default to a visible workflow: open MATLAB/Simulink windows first so the user can watch modeling, simulation, tuning, and plotting progress.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 13.4 KB |
| assets/routing.json | config | 13.4 KB |
| assets/tasks.json | config | 4.9 KB |
| references/routing-contract.md | markdown | 6.5 KB |
| scripts/mas_pipeline.m | other | 8.0 KB |
| scripts/mas_route.m | other | 15.9 KB |
| scripts/mas_skill_graph.m | other | 15.1 KB |
| tests/test_routing.m | other | 3.5 KB |
| tests/test_routing_contract.m | other | 10.1 KB |
| tests/test_skill_graph.m | other | 5.3 KB |
assets/tasks.json
View on GitHub{
"schema": "mas-task-registry/1",
"description": "Evaluation tasks: natural-language prompt, the skill the task is meant to exercise, the entry point, and the products it needs. The prompt is what goes through mas_route, so skillMatch measures the ROUTER on a realistic sentence rather than on a label. The `split` field separates the DEVELOPMENT set (D1-D8, C1-C3, T1) from the HELD-OUT set (S1, R1, G1): held-out tasks exercise the Phase 4.2 Task 3/4/5 tools and are graded only by the frozen reference, never by their own verdict.",
"tasks": [
{
"id": "D1",
"domain": "scientific computing",
"prompt": "求解线性方程组并对 4/(1+x^2) 做数值积分",
"expectedSkill": "matlab-data-analysis",
"entry": "cd_d1_linalg",
"products": [],
"split": "dev"
},
{
"id": "D2",
"domain": "data analysis",
"prompt": "读取实验数据表,处理缺失值并做指数回归拟合",
"expectedSkill": "matlab-data-analysis",
"entry": "cd_d2_regression",
"products": [],
"split": "dev"
},
{
"id": "D3",
"domain": "signal processing",
"prompt": "设计 4 阶 Butterworth 低通滤波器并检查幅频响应",
"expectedSkill": "matlab-signal-vision-ai",
"entry": "cd_d3_filter",
"products": [
"Signal Processing Toolbox"
],
"split": "dev"
},
{
"id": "D4",
"domain": "image processing",
"prompt": "对图像做阈值分割并统计每个目标的面积和质心",
"expectedSkill": "matlab-signal-vision-ai",
"entry": "cd_d4_segment",
"products": [
"Image Processing Toolbox"
],
"split": "dev"
},
{
"id": "D5",
"domain": "control",
"prompt": "建立二阶系统的状态空间模型并分析阶跃响应指标",
"expectedSkill": "matlab-control-optimization",
"entry": "cd_d5_statespace",
"products": [
"Control System Toolbox"
],
"split": "dev"
},
{
"id": "D6",
"domain": "Simulink",
"prompt": "用 Simulink 搭建一阶系统并仿真验证输出轨迹",
"expectedSkill": "matlab-simulink-modeling",
"entry": "cd_d6_simulink",
"products": [
"Simulink"
],
"split": "dev"
},
{
"id": "D7",
"domain": "power electronics",
"prompt": "分析 Boost 变换器的稳态占空比和电感电流纹波",
"expectedSkill": "matlab-control-optimization",
"entry": "cd_d7_boost",
"products": [],
"split": "dev"
},
{
"id": "D8",
"domain": "robotics",
"prompt": "计算机器人二连杆的正运动学末端位置",
"expectedSkill": "matlab-robotics-autonomy",
"entry": "cd_d8_kinematics",
"products": [],
"split": "dev"
},
{
"id": "C1",
"domain": "control (known stable)",
"prompt": "分析一个已知一阶回路的相位裕度和增益裕度",
"expectedSkill": "matlab-control-optimization",
"entry": "cd_c1_stable",
"products": [
"Control System Toolbox"
],
"split": "dev"
},
{
"id": "C2",
"domain": "control (unstable plant)",
"prompt": "判断一个含右半平面极点的系统是否稳定",
"expectedSkill": "matlab-control-optimization",
"entry": "cd_c2_unstable",
"products": [
"Control System Toolbox"
],
"split": "dev"
},
{
"id": "C3",
"domain": "control (multi-crossing)",
"prompt": "检查一个存在多次 0dB 交越的回路的最坏相位裕度",
"expectedSkill": "matlab-control-optimization",
"entry": "cd_c3_multicross",
"products": [
"Control System Toolbox"
],
"split": "dev"
},
{
"id": "T1",
"domain": "data cleaning",
"prompt": "清洗一份含缺失值、重复值和异常值的实验数据表",
"expectedSkill": "matlab-data-analysis",
"entry": "cd_t1_clean",
"products": [
"Statistics and Machine Learning Toolbox"
],
"split": "dev"
},
{
"id": "S1",
"domain": "signal (held-out)",
"split": "heldout",
"prompt": "仿真 OFDM/QPSK 在 0/4/8 dB 下的误码率并与理论值比较",
"expectedSkill": "matlab-signal-vision-ai",
"entry": "cd_s1_ofdm",
"products": []
},
{
"id": "R1",
"domain": "robotics (held-out)",
"split": "heldout",
"prompt": "对二连杆机械臂做逆运动学,验证 FK(IK(pose)) 能还原位姿",
"expectedSkill": "matlab-robotics-autonomy",
"entry": "cd_r1_ik",
"products": []
},
{
"id": "G1",
"domain": "codegen (held-out)",
"split": "heldout",
"prompt": "把一段求和的 MATLAB 函数生成 C 代码并验证数值与 MATLAB 一致",
"expectedSkill": "matlab-codegen-deploy",
"entry": "cd_g1_codegen",
"products": [
"MATLAB Coder"
]
}
]
}Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |