skills MCP — 사용 사례, 설치 & 라이브 데모

Name: skills MCP Server
Author: matlab

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

skills-skill-4.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/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
    }
  }
}

Claude Desktop → Settings → Developer → Edit Config 열기. 저장 후 앱 재시작.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor는 Claude Desktop과 동일한 mcpServers 스키마 사용. 프로젝트 설정이 전역보다 우선.

VS Code → Cline → MCP Servers → Edit

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

Cline 사이드바의 MCP Servers 아이콘 클릭 후 "Edit Configuration" 선택.

~/.codeium/windsurf/mcp_config.json

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

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

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

context_servers에 추가. 저장 시 Zed가 핫 리로드.

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

한 줄 명령. claude mcp list로 확인, claude mcp remove로 제거.

사용 사례

실전 활용법: 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

언제 쓸까: Any MATLAB authoring task — from scripts to toolboxes.

사전 조건

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

흐름

Describe the task

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

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

Add MATLAB unit tests using matlab.unittest.✓ 복사됨

→ 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?✓ 복사됨

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

결과: Idiomatic, fast, tested MATLAB code.

함정

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

함께 쓰기: filesystem

Port a Python/NumPy script to MATLAB correctly

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

언제 쓸까: You have a NumPy prototype and need a clean MATLAB equivalent.

흐름

Share the Python

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

→ 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.✓ 복사됨

→ A small cross-check script

결과: MATLAB port with documented semantic differences.

함정

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

조합

다른 MCP와 조합해 10배 효율

skills-skill-4 + filesystem

Work across a MATLAB Projects folder structure

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

skills-skill-4 + github

Open PRs for MATLAB codebases with proper test coverage

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

도구

이 MCP가 노출하는 것

도구	입력	언제 호출
matlab-authoring	task description	Any MATLAB task
matlab-testing	function under test	After authoring
perf-guidance	slow code + context	When something is too slow

비용 및 제한

운영 비용

API 쿼터: none
호출당 토큰: ~3–10k per task
금액: free; MATLAB license sold separately
팁: Constrain to a specific toolbox when asking — reduces context

보안

권한, 시크릿, 파급범위

자격 증명 저장: none

데이터 외부 송신: none

문제 해결

자주 발생하는 오류와 해결

Generated code uses a toolbox you don't have licensed

Tell Claude which toolboxes are available.

확인: ver in MATLAB

Script errors in older MATLAB

Specify your MATLAB release; skill adapts suggestions.

확인: version in MATLAB

대안

skills 다른 것과 비교

대안	언제 쓰나	단점/장점
jupyter	You're really doing Python science and only occasionally MATLAB	Different ecosystem

skills