/ Verzeichnis / Playground / OpenAI Skills Catalog
● Offiziell openai ⚡ Sofort

OpenAI Skills Catalog

von openai · openai/skills

Skills Catalog for Codex — OpenAI's curated and official skills for coding agents.

OpenAI Skills Catalog is a skill that skills catalog for codex — openai's curated and official skills for coding agents Use it from Claude Code, Cursor, Codex, or any MCP-compatible / skills-compatible agent.

Warum nutzen

Hauptfunktionen

Live-Demo

In der Praxis

openai-skills-catalog.replay ▶ bereit
0/0

Installieren

Wählen Sie Ihren Client

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "openai-skills-catalog": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/openai/skills",
        "~/.claude/skills/openai"
      ],
      "_inferred": true
    }
  }
}

Öffne Claude Desktop → Settings → Developer → Edit Config. Nach dem Speichern neu starten.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "openai-skills-catalog": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/openai/skills",
        "~/.claude/skills/openai"
      ],
      "_inferred": true
    }
  }
}

Cursor nutzt das gleiche mcpServers-Schema wie Claude Desktop. Projektkonfiguration schlägt die globale.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "openai-skills-catalog": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/openai/skills",
        "~/.claude/skills/openai"
      ],
      "_inferred": true
    }
  }
}

Klicken Sie auf das MCP-Servers-Symbol in der Cline-Seitenleiste, dann "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "openai-skills-catalog": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/openai/skills",
        "~/.claude/skills/openai"
      ],
      "_inferred": true
    }
  }
}

Gleiche Struktur wie Claude Desktop. Windsurf neu starten zum Übernehmen.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "openai-skills-catalog",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/openai/skills",
        "~/.claude/skills/openai"
      ]
    }
  ]
}

Continue nutzt ein Array von Serverobjekten statt einer Map.

~/.config/zed/settings.json
{
  "context_servers": {
    "openai-skills-catalog": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/openai/skills",
          "~/.claude/skills/openai"
        ]
      }
    }
  }
}

In context_servers hinzufügen. Zed lädt beim Speichern neu.

claude mcp add openai-skills-catalog -- git clone https://github.com/openai/skills ~/.claude/skills/openai

Einzeiler. Prüfen mit claude mcp list. Entfernen mit claude mcp remove.

Anwendungsfälle

Praxisnahe Nutzung: OpenAI Skills Catalog

Use OpenAI Skills Catalog for its core workflow

👤 Engineers and power users ⏱ ~15 min intermediate

Wann einsetzen: You want skill integration for skill work without writing glue code.

Voraussetzungen
  • Repo installed / cloned — See repo README
Ablauf
  1. Install
    Set up the OpenAI Skills Catalog skill.✓ Kopiert
    → skill listed in your agent config
  2. Invoke
    Use OpenAI Skills Catalog to run a representative task in skill.✓ Kopiert
    → Tool call succeeds; result returned

Ergebnis: Real skill work completed via OpenAI Skills Catalog with one chat.

Fallstricke
  • Auth/credential setup is the most common blocker. — Follow the repo README for env vars and tokens.
Kombinieren mit: filesystem

Kombinationen

Mit anderen MCPs für 10-fache Wirkung

openai-skills-catalog + filesystem

Pair with filesystem for skill workflows that need local file IO.

Use OpenAI Skills Catalog together with filesystem.✓ Kopiert

Werkzeuge

Was dieses MCP bereitstellt

WerkzeugEingabenWann aufrufenKosten
primary_call task-specific For the main use case Varies

Kosten & Limits

Was der Betrieb kostet

API-Kontingent
Provider rate limits apply
Tokens pro Aufruf
Varies
Kosten in €
Free / pay provider directly
Tipp
Cache results; batch calls.

Sicherheit

Rechte, Secrets, Reichweite

Credential-Speicherung: Use environment variables or your OS keychain.
Datenabfluss: Depends on integration

Fehlerbehebung

Häufige Fehler und Lösungen

Confirm install and restart your agent.

Mehr

Ressourcen

📖 Offizielle README auf GitHub lesen

🐙 Offene Issues ansehen

🔍 Alle 400+ MCP-Server und Skills durchsuchen