ds-ai-coding-skills

In the author's own words, from each skill's SKILL.md.

• analysis-reporting

  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.

  .claude/skills/analysis-reporting/SKILL.md on GitHub (opens in a new tab)

• causal-inference-diagnostics

  因果推論・効果検証（A/B テスト / ABテスト / オンライン実験 / リフト / SRM / CUPED、観察データの処置効果 / ATE / ATT / CATE / 傾向スコア / propensity score / IPW / 二重頑健 / DML / causal forest、準実験 / 差の差 / DiD / イベントスタディ / 操作変数 / IV / 2SLS / 回帰不連続 / RDD / 合成コントロール）を実行したら必ずセットで出す図と値のルーター。 proportions_ztest, chisquare, statsmodels.stats.power, dowhy, econml, causalml, doubleml, propensity, LinearDML, IV2SLS, rdrobust, rddensity, pysyncon, trea…

  .claude/skills/causal-inference-diagnostics/SKILL.md on GitHub (opens in a new tab)

• dataframe-polars

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

  .claude/skills/dataframe-polars/SKILL.md on GitHub (opens in a new tab)

• notebook-workflow

  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.

  .claude/skills/notebook-workflow/SKILL.md on GitHub (opens in a new tab)

• path-and-io

  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.

  .claude/skills/path-and-io/SKILL.md on GitHub (opens in a new tab)

• plan-analysis

  分析を始める前に構造化された分析計画を作成する

  .claude/skills/plan-analysis/SKILL.md on GitHub (opens in a new tab)

• predictive-modeling-diagnostics

  予測モデリング（教師あり機械学習 / 予測モデル / 精度評価 / 交差検証 / リーク、決定木 / ランダムフォレスト / GBDT / LightGBM / XGBoost / CatBoost、モデル解釈 / 特徴量重要度 / SHAP / PDP / ICE、時系列 / 季節性 / ARIMA / SARIMA / Prophet / VAR / 変化点 / 時系列予測）を実行したら必ずセットで出す図と値のルーター。train_test_split, cross_val_score, GridSearchCV, Pipeline, TimeSeriesSplit, DecisionTree, RandomForest, lgb., xgb., CatBoost, dtreeviz, shap., permutation_importance, PartialDependenceD…

  .claude/skills/predictive-modeling-diagnostics/SKILL.md on GitHub (opens in a new tab)

• prepare-pr

  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

  .claude/skills/prepare-pr/SKILL.md on GitHub (opens in a new tab)

• python-project-ops

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

  .claude/skills/python-project-ops/SKILL.md on GitHub (opens in a new tab)

• python-style

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

  .claude/skills/python-style/SKILL.md on GitHub (opens in a new tab)

• review-sql

  SQLクエリの正確性と安全性をレビューする

  .claude/skills/review-sql/SKILL.md on GitHub (opens in a new tab)

• run-eda

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

  .claude/skills/run-eda/SKILL.md on GitHub (opens in a new tab)

• run-modeling

  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>

  .claude/skills/run-modeling/SKILL.md on GitHub (opens in a new tab)

• safe-data-handling

  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.

  .claude/skills/safe-data-handling/SKILL.md on GitHub (opens in a new tab)

• simulation-optimization-diagnostics

  シミュレーションと数理最適化（モンテカルロ / Monte Carlo / 離散事象シミュレーション / DES / 待ち行列 / リスク分析 / シナリオ分析、線形計画 / LP / 整数計画 / MIP / スケジューリング / 配送計画 / VRP / 割当 / メタヒューリスティクス）を 実行したら必ずセットで出す図と値のルーター。SeedSequence.spawn, scipy.stats の rvs, simpy, SALib, pulp, LpProblem, mip.Model, ortools, pywraplp, cp_model, pyomo, cvxpy, linprog, milp がコードに現れたとき、または ユーザーが「シミュレーションして」「モンテカルロで見積もって」「待ち時間をシミュレートして」「最適化して」 「最適な割当を求めて」「スケジュールを組ん…

  .claude/skills/simulation-optimization-diagnostics/SKILL.md on GitHub (opens in a new tab)

• sql-analysis

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

  .claude/skills/sql-analysis/SKILL.md on GitHub (opens in a new tab)

• statistical-inference-diagnostics

  統計的推論（線形回帰 / 重回帰 / OLS / Lasso / Ridge / 分位点回帰、ロジスティック回帰 / ポアソン / GLM / オッズ比、 混合効果 / マルチレベル / パネル固定効果、仮説検定 / t 検定 / χ² / ANOVA / 有意差、生存時間分析 / Kaplan-Meier / Cox、 ベイズ推定 / MCMC / Stan）を実行したら必ずセットで出す図と値のルーター。sm.OLS, smf.ols, LinearRegression, LassoCV, QuantReg, sm.Logit, sm.GLM, LogisticRegression, mixedlm, PanelOLS, ttest_ind, mannwhitneyu, chi2_contingency, pingouin, lifelines, CoxPHFitter, cmdsta…

  .claude/skills/statistical-inference-diagnostics/SKILL.md on GitHub (opens in a new tab)

• statistical-ml-review

  Use this when reviewing statistical analysis, experiments, model evaluation, or ML work done by someone else (a notebook, PR, or report) — checking that the required context is stated and that every method applied comes with the figures and values required by the matching *-diagnostics skill. When running an analysis yourself, apply the matching *-diagnostics skill directly.

  .claude/skills/statistical-ml-review/SKILL.md on GitHub (opens in a new tab)

• summarize-analysis

  分析結果を日本語でまとめる

  .claude/skills/summarize-analysis/SKILL.md on GitHub (opens in a new tab)

• sync-agent-docs

  Claude Code・GitHub Copilot・Codex のルーター文書とタスクスキルの差分を検出し、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

  .claude/skills/sync-agent-docs/SKILL.md on GitHub (opens in a new tab)

• unsupervised-eda-diagnostics

  教師なし分析と EDA 前処理（欠測 / 欠損 / NaN / 補完 / imputation / 外れ値処理、クラスタリング / セグメンテーション / k-means / 階層クラスタリング / GMM / DBSCAN、次元削減 / PCA / 主成分分析 / 因子分析 / UMAP / t-SNE、異常検知 / anomaly detection / 不正検知）を実行したら必ずセットで出す図と値のルーター。fillna, dropna, fill_null, SimpleImputer, IterativeImputer, missingno, KMeans, AgglomerativeClustering, DBSCAN, GaussianMixture, silhouette_score, dendrogram, PCA, FactorAnalysis, calculate_…

  .claude/skills/unsupervised-eda-diagnostics/SKILL.md on GitHub (opens in a new tab)

• update-agent-docs

  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

  .claude/skills/update-agent-docs/SKILL.md on GitHub (opens in a new tab)

• visualization

  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.

  .claude/skills/visualization/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• agent-skillsby addyosmani Production-grade engineering skills for AI coding agents. 107k stars · 25 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 136k stars · 7 skills
• taste-skillby Leonxlnx Agent skills that give coding agents taste: art direction, reference images and a browser check instead of generic AI pages 97.3k stars · 13 skills
• Understand-Anythingby Egonex-AI Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about… 86.5k stars · 9 skills
• archifyby tt-a1i Turn any idea, plan, or codebase into a beautiful interactive diagram. An agent skill for Claude Code, Codex, and more. 84.1k stars · 2 skills