setup
Initialize project and set up competition environment (all-in-one). Use when starting a new Kaggle/atmaCup competition project or when user invokes /setup.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
菜单
Initialize project and set up competition environment (all-in-one). Use when starting a new Kaggle/atmaCup competition project or when user invokes /setup.
用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Get competition metadata, data files, and rules using Kaggle MCP. Use when looking up competition details, searching competitions, or fetching competition data file info.
Search, download, and manage Kaggle datasets using Kaggle MCP. Use when finding datasets, checking file structures, or downloading data.
Browse and search Kaggle discussion forums using Kaggle MCP. Use when looking for tips, solutions, or community insights about competitions or datasets.
View and analyze competition leaderboard and submissions using Kaggle MCP. Use when checking rankings, scores, or submission history.
Search, view, save, and run Kaggle notebooks using Kaggle MCP. Use when exploring public notebooks, pushing code to Kaggle, or managing notebook sessions.
Submit to a Kaggle competition (code/notebook submission or file upload). Use when submitting predictions or notebooks to a competition.
| name | setup |
| description | Initialize project and set up competition environment (all-in-one). Use when starting a new Kaggle/atmaCup competition project or when user invokes /setup. |
This skill sets up the entire project for a Kaggle/atmaCup competition in one command. It handles dependency installation, directory creation, competition information fetching, and AI context file generation.
/setup or /setup [competition-url-or-name]Execute these 4 steps in order:
Run uv sync to install all Python dependencies defined in pyproject.toml.
uv sync
Create the following directories if they don't exist:
mkdir -p configs data/raw data/processed src/commons src/Solution1 src/Solution2 ai-src notebook logs
If a competition URL or name is provided:
Follow the instructions in references/fetch-kaggle.md.
This will create:
.references/COMPETITION.md.references/DATASET.md.references/METRIC.mdIf no URL/name is provided: Skip this step.
After creating documentation files:
Follow the instructions in references/create-claude-md.md.
This will create/update CLAUDE.md with competition-specific context.
After completing all steps, summarize to the user:
| Step | Status |
|---|---|
| Dependencies installed | ✅ / ❌ |
| Directories created | ✅ / ❌ |
| Competition info fetched | ✅ / ❌ / ⏭️ (skipped if no URL) |
| CLAUDE.md generated | ✅ / ❌ |
Provide guidance based on the result:
/eda on the training dataThis skill includes detailed procedures in references/:
# Full setup with Guru Guru Science competition
/setup https://www.guruguru.science/competitions/31
# Full setup with Kaggle competition
/setup titanic
# Basic setup only (no competition specified)
/setup
uv sync fails, report the error and suggest solutions.