ds-ai-coding-skills

分析を始める前に構造化された分析計画を作成する

現在の変更に対するプルリクエストのサマリーを作成する

SQLクエリの正確性と安全性をレビューする

データセットのEDAを実装・実行する。引数: <dataset_path> <topic>

予測モデリングのワークフローを実装・評価する。引数: <dataset_path> <target> <task>

分析結果を日本語でまとめる

Claude CodeとGitHub Copilotのスキル・指示ファイルの差分を検出し、機械的な部分はスクリプトで、判断が必要な部分はここで同期する

リポジトリの規約が変更されたときにCLAUDE.md・スキル・docs/agentを更新する

Use this when summarizing analysis results, writing reports, documenting experiment outcomes, or presenting model evaluation — including structuring findings in Japanese with conclusions, facts, assumptions, interpretations, and caveats.

Use this when performing DataFrame operations — including loading, filtering, joining, aggregating, transforming, or reshaping tabular data with polars or pandas.

Use this when creating, editing, executing, or reviewing Jupyter notebooks — including cell structure, kernel management, extracting reusable logic to src/, and ensuring notebooks are restartable.

Use this when reading from or writing to local files — including constructing file paths with pathlib, creating directories, choosing output locations, and using path utilities from src/analysis_project/paths.py.

Use this when managing Python dependencies with uv, running tests with pytest, linting with ruff, formatting code, type checking with mypy, or executing notebooks.

Use this when creating, editing, or reviewing Python code — including type hints, docstrings, naming conventions, imports, error handling, and code structure.

Use this when reading, writing, moving, copying, modifying, deleting, or generating data files — including any operation that touches data/raw, data/external, data/interim, data/processed, or outputs directories.

Use this when writing, reviewing, or modifying SQL queries — including SELECT, CTEs, joins, aggregations, window functions, and validating query correctness or performance.

Use this when performing statistical analysis, hypothesis testing, A/B testing, model training, model evaluation, feature engineering, or any machine learning task — including documenting assumptions, leakage risks, and validation strategies.

Use this when creating, modifying, reviewing, or saving charts, figures, plots, or visual summaries — including matplotlib/seaborn code, EDA figures, report figures, dashboards, or any task involving Japanese chart labels, color palettes, or figure styling.

Use this when summarizing analysis results, writing reports, documenting experiment outcomes, or presenting model evaluation — including structuring findings in Japanese with conclusions, facts, assumptions, interpretations, and caveats.

Use this when performing DataFrame operations — including loading, filtering, joining, aggregating, transforming, or reshaping tabular data with polars or pandas.

Use this when creating, editing, executing, or reviewing Jupyter notebooks — including cell structure, kernel management, extracting reusable logic to src/, and ensuring notebooks are restartable.

Use this when reading from or writing to local files — including constructing file paths with pathlib, creating directories, choosing output locations, and using path utilities from src/analysis_project/paths.py.

Use this when managing Python dependencies with uv, running tests with pytest, linting with ruff, formatting code, type checking with mypy, or executing notebooks.

Use this when creating, editing, or reviewing Python code — including type hints, docstrings, naming conventions, imports, error handling, and code structure.

Use this when reading, writing, moving, copying, modifying, deleting, or generating data files — including any operation that touches data/raw, data/external, data/interim, data/processed, or outputs directories.

Use this when writing, reviewing, or modifying SQL queries — including SELECT, CTEs, joins, aggregations, window functions, and validating query correctness or performance.

Use this when performing statistical analysis, hypothesis testing, A/B testing, model training, model evaluation, feature engineering, or any machine learning task — including documenting assumptions, leakage risks, and validation strategies.

Use this when creating, modifying, reviewing, or saving charts, figures, plots, or visual summaries — including matplotlib/seaborn code, EDA figures, report figures, dashboards, or any task involving Japanese chart labels, color palettes, or figure styling.