freemcplab / 디렉터리 / 플레이그라운드 / Kaggle Skill

● 커뮤니티 shepsci ⚡ 바로 사용

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.

▶ 데모 보기 📦 설치 💡 사용 사례

왜 쓰나요

핵심 기능

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

라이브 데모

실제 사용 모습

kaggle-skill.replay ▶ 준비됨

0/0

설치

클라이언트 선택

~/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
    }
  }
}

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

~/.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
    }
  }
}

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

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
    }
  }
}

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

~/.codeium/windsurf/mcp_config.json

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

Claude Desktop과 같은 형식. Windsurf 재시작 후 적용.

~/.continue/config.json

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

Continue는 맵이 아닌 서버 오브젝트 배열 사용.

~/.config/zed/settings.json

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

context_servers에 추가. 저장 시 Zed가 핫 리로드.

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

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

사용 사례

실전 활용법: Kaggle Skill

Pull a competition dataset, train a baseline, submit predictions

👤 Kagglers iterating fast ⏱ ~15 min intermediate

언제 쓸까: You want to get a first submission on the leaderboard quickly.

사전 조건

Server/skill installed and authenticated — See repo README

흐름

Pull data

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

→ Dataset downloaded; files listed
Submit

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

→ Submission id + public score when scored

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

함정

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.

함께 쓰기: filesystem

조합

다른 MCP와 조합해 10배 효율

kaggle-skill + filesystem

Pair with filesystem

Use this skill together with filesystem.✓ 복사됨

도구

이 MCP가 노출하는 것

도구	입력	언제 호출	비용
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

비용 및 제한

운영 비용

API 쿼터: Kaggle rate limits apply
호출당 토큰: Varies
금액: Free for public competitions
팁: Cache downloads.

보안

권한, 시크릿, 파급범위

자격 증명 저장: ~/.kaggle/kaggle.json with chmod 600

데이터 외부 송신: kaggle.com

문제 해결

자주 발생하는 오류와 해결

403 Forbidden on download

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

확인: Visit competition page

kaggle.json missing

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

확인: kaggle competitions list

대안

Kaggle Skill 다른 것과 비교

대안	언제 쓰나	단점/장점
Kaggle CLI directly	You want raw CLI	No agent integration