skills MCP — Cas d'usage, Installer & Démo en direct

Name: skills MCP Server
Author: matlab

Pourquoi l'utiliser

Fonctionnalités clés

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

Démo en direct

Aperçu en pratique

skills-skill-4.replay ▶ prêt

0/0

Installer

Choisissez votre client

~/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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.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 utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit

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

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "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
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json

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

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json

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

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : 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

Quand l'utiliser : Any MATLAB authoring task — from scripts to toolboxes.

Prérequis

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

Déroulement

Describe the task

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

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

Add MATLAB unit tests using matlab.unittest.✓ Copié

→ 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?✓ Copié

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

Résultat : Idiomatic, fast, tested MATLAB code.

Pièges

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

Combiner avec : filesystem

Port a Python/NumPy script to MATLAB correctly

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

Quand l'utiliser : You have a NumPy prototype and need a clean MATLAB equivalent.

Déroulement

Share the Python

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

→ 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.✓ Copié

→ A small cross-check script

Résultat : MATLAB port with documented semantic differences.

Pièges

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

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

skills-skill-4 + filesystem

Work across a MATLAB Projects folder structure

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

skills-skill-4 + github

Open PRs for MATLAB codebases with proper test coverage

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

Outils

Ce que ce MCP expose

Outil	Entrées	Quand appeler
matlab-authoring	task description	Any MATLAB task
matlab-testing	function under test	After authoring
perf-guidance	slow code + context	When something is too slow

Coût et limites

Coût d'exécution

Quota d'API: none
Tokens par appel: ~3–10k per task
Monétaire: free; MATLAB license sold separately
Astuce: Constrain to a specific toolbox when asking — reduces context

Sécurité

Permissions, secrets, portée

Stockage des identifiants : none

Sortie de données : none

Dépannage

Erreurs courantes et correctifs

Generated code uses a toolbox you don't have licensed

Tell Claude which toolboxes are available.

Vérifier : ver in MATLAB

Script errors in older MATLAB

Specify your MATLAB release; skill adapts suggestions.

Vérifier : version in MATLAB

Alternatives

skills vs autres

Alternative	Quand l'utiliser	Compromis
jupyter	You're really doing Python science and only occasionally MATLAB	Different ecosystem

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills