skills MCP — 使用場景, 安裝 & 即時演示

Name: skills MCP Server
Author: matlab

為什麼要用

核心特性

Official: maintained by MathWorks
Covers core MATLAB language plus common toolboxes
Encodes MATLAB Projects and unit-test conventions
Performance guidance: vectorization, preallocation, profiling
Works with Claude Code and other skill-compatible agents

即時演示

實際使用效果

skills-skill-4.replay ▶ 就緒

0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "skills-skill-4": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/matlab/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "skills-skill-4": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/matlab/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "skills-skill-4": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/matlab/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

點擊 Cline 側欄中的 MCP Servers 圖示，然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "skills-skill-4": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/matlab/skills",
        "~/.claude/skills/skills"
      ],
      "_inferred": true
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "skills-skill-4",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/matlab/skills",
        "~/.claude/skills/skills"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列，而非映射。

~/.config/zed/settings.json

{
  "context_servers": {
    "skills-skill-4": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/matlab/skills",
          "~/.claude/skills/skills"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add skills-skill-4 -- git clone https://github.com/matlab/skills ~/.claude/skills/skills

一行命令搞定。用 claude mcp list 驗證，claude mcp remove 移除。

使用場景

實戰用法： skills

How to get Claude to write idiomatic MATLAB, not MATLAB-flavored Python

👤 MATLAB developers who noticed Claude defaulting to loops everywhere ⏱ ~25 min intermediate

何時使用： Any MATLAB authoring task — from scripts to toolboxes.

前置條件

MATLAB R2023b+ recommended — mathworks.com/products/matlab.html
Skill cloned — git clone https://github.com/matlab/skills ~/.claude/skills/skills

步驟

Describe the task

Write a function that computes the moving-window correlation of two time series — MATLAB, idiomatic.✓ 已複製

→ Vectorized implementation, correct function signature, docstring
Ask for tests

Add MATLAB unit tests using matlab.unittest.✓ 已複製

→ Tests in a separate file following MATLAB Test conventions
Profile

If this is called in a tight loop, how would you profile and speed it up?✓ 已複製

→ tic/toc or profile() suggestions, preallocation hints

結果： Idiomatic, fast, tested MATLAB code.

注意事項

Claude reaches for Python-style loops — Explicitly ask for vectorized form; reference MATLAB docs style

搭配使用： filesystem

Port a Python/NumPy script to MATLAB correctly

👤 Engineers moving research code into a MATLAB pipeline ⏱ ~30 min intermediate

何時使用： You have a NumPy prototype and need a clean MATLAB equivalent.

步驟

Share the Python

Port this NumPy script to MATLAB. Preserve numerical behavior — flag where semantics differ.✓ 已複製

→ Translated code + explicit notes on 1-indexing, broadcasting, default dtypes
Verify with a test

Write a side-by-side test that shows both produce the same outputs on known inputs.✓ 已複製

→ A small cross-check script

結果： MATLAB port with documented semantic differences.

注意事項

Off-by-one from zero- vs one-indexing — Claude should call these out; if not, re-ask

組合

與其他 MCP 搭配，撬動十倍槓桿

skills-skill-4 + filesystem

Work across a MATLAB Projects folder structure

Read +mytools/, add a new function, and update the tests package.✓ 已複製

skills-skill-4 + github

Open PRs for MATLAB codebases with proper test coverage

Open a PR that adds the new function + tests.✓ 已複製

工具

此 MCP 暴露的能力

工具	輸入參數	何時呼叫
matlab-authoring	task description	Any MATLAB task
matlab-testing	function under test	After authoring
perf-guidance	slow code + context	When something is too slow

成本與限制

運行它的成本

API 配額: none
每次呼叫 Token 數: ~3–10k per task
費用: free; MATLAB license sold separately
提示: Constrain to a specific toolbox when asking — reduces context

安全

權限、密鑰、影響範圍

憑證儲存： none

資料出站： none

故障排查

常見錯誤與修復

Generated code uses a toolbox you don't have licensed

Tell Claude which toolboxes are available.

驗證： ver in MATLAB

Script errors in older MATLAB

Specify your MATLAB release; skill adapts suggestions.

驗證： version in MATLAB

替代方案

skills 對比其他方案

替代方案	何時用它替代	權衡
jupyter	You're really doing Python science and only occasionally MATLAB	Different ecosystem

skills

為什麼要用

核心特性

即時演示

實際使用效果

安裝

選擇你的客戶端

使用場景

實戰用法： skills

How to get Claude to write idiomatic MATLAB, not MATLAB-flavored Python

前置條件

步驟

注意事項

Port a Python/NumPy script to MATLAB correctly

步驟

注意事項

組合

與其他 MCP 搭配，撬動十倍槓桿

工具

此 MCP 暴露的能力

成本與限制

運行它的成本

安全

權限、密鑰、影響範圍

故障排查

常見錯誤與修復

替代方案

skills 對比其他方案

更多

資源