freemcplab / Directorio / Playground / Kaggle Skill

● Comunidad shepsci ⚡ Instantáneo

Kaggle Skill

Name: Kaggle Skill (Claude Skill)
Author: shepsci

Complete Kaggle integration — competition reports, dataset/model downloads, notebook execution.

A skill that wires Kaggle into Claude Code: list competitions, download datasets/models, submit predictions, fetch notebook executions, track badges. Works across Claude Code, Cursor, Codex, Gemini CLI through skills.sh.

▶ Ver demo 📦 Instalar 💡 Casos de uso

Por qué usarlo

Características clave

Competition browsing + submission
Dataset and model download with versioning
Notebook execution status + outputs
Badge progress tracking
Multi-agent compatibility via skills.sh standard

Demo en vivo

Cómo se ve en la práctica

kaggle-skill.replay ▶ listo

0/0

Instalar

Elige tu cliente

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

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

Abre Claude Desktop → Settings → Developer → Edit Config. Reinicia después de guardar.

~/.cursor/mcp.json · .cursor/mcp.json

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

Cursor usa el mismo esquema mcpServers que Claude Desktop. La configuración del proyecto prevalece sobre la global.

VS Code → Cline → MCP Servers → Edit

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

Haz clic en el icono MCP Servers de la barra lateral de Cline y luego en "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

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

Mismo formato que Claude Desktop. Reinicia Windsurf para aplicar.

~/.continue/config.json

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

Continue usa un array de objetos de servidor en lugar de un mapa.

~/.config/zed/settings.json

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

Añádelo a context_servers. Zed recarga en caliente al guardar.

claude mcp add kaggle-skill -- git clone https://github.com/shepsci/kaggle-skill ~/.claude/skills/kaggle-skill

Un solo comando. Verifica con claude mcp list. Quita con claude mcp remove.

Casos de uso

Usos del mundo real: Kaggle Skill

Pull a competition dataset, train a baseline, submit predictions

👤 Kagglers iterating fast ⏱ ~15 min intermediate

Cuándo usarlo: You want to get a first submission on the leaderboard quickly.

Requisitos previos

Server/skill installed and authenticated — See repo README

Flujo

Pull data

Use the Kaggle skill to download the latest version of competition 'titanic' to ./data.✓ Copiado

→ Dataset downloaded; files listed
Submit

After my notebook runs, submit submission.csv with message 'baseline LR'.✓ Copiado

→ Submission id + public score when scored

Resultado: A real submission on the leaderboard with one chat.

Errores comunes

Daily submission limits per competition — usually 5–10. The skill warns when you're close. — Daily submission limits per competition — usually 5–10. The skill warns when you're close.

Combinar con: filesystem

Combinaciones

Combínalo con otros MCPs para multiplicar por 10

kaggle-skill + filesystem

Pair with filesystem

Use this skill together with filesystem.✓ Copiado

Herramientas

Lo que expone este MCP

Herramienta	Entradas	Cuándo llamar	Coste
list_competitions	category, status	Find active competitions	1 API call
download_dataset	ref, version	Pull a dataset locally	Disk I/O
submit	competition, file, message	Submit predictions	1 API call

Coste y límites

Lo que cuesta ejecutarlo

Cuota de API: Kaggle rate limits apply
Tokens por llamada: Varies
Monetario: Free for public competitions
Consejo: Cache downloads.

Seguridad

Permisos, secretos, alcance

Almacenamiento de credenciales: ~/.kaggle/kaggle.json with chmod 600

Salida de datos: kaggle.com

Resolución de problemas

Errores comunes y soluciones

403 Forbidden on download

Accept the competition's rules on Kaggle first via the web UI. The CLI cannot accept rules.

Verificar: Visit competition page

kaggle.json missing

Place your API token at ~/.kaggle/kaggle.json with chmod 600.

Verificar: kaggle competitions list

Alternativas

Kaggle Skill vs otros

Alternativa	Cuándo usarla	Contrapartida
Kaggle CLI directly	You want raw CLI	No agent integration

Más

Recursos

📖 Lee el README oficial en GitHub

🐙 Ver issues abiertas

🔍 Ver todos los 400+ servidores MCP y Skills