feature-engineering
モデルの性能を向上させるために、既存のデータから新しい特徴量を作成する。
Best use case
feature-engineering is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
モデルの性能を向上させるために、既存のデータから新しい特徴量を作成する。
Teams using feature-engineering should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/feature-engineering/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How feature-engineering Compares
| Feature / Agent | feature-engineering | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
モデルの性能を向上させるために、既存のデータから新しい特徴量を作成する。
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Feature Engineering ## 概要 モデルの性能を向上させるために、既存のデータから新しい特徴量を作成する。 ## 手順 1. **ドメイン知識の適用**: ビジネスロジックに基づいた特徴量作成。 2. **変換**: 対数変換、Box-Cox変換、標準化/正規化。 3. **エンコーディング**: One-Hot Encoding, Label Encoding, Target Encoding. 4. **相互作用**: 変数間の掛け合わせ、割り算。 5. **集約**: グループごとの統計量（平均、最大、最小、分散など）の算出。 6. **時系列特徴量**: ラグ特徴量、移動平均など（時系列データの場合）。 ## 使用ツール・ライブラリ - pandas, numpy, scikit-learn ## 成果物の保存場所 - 特徴エンジニアリング、学習、検証用ノートブック: `project/src/03_main.ipynb` - 特徴量エンジニアリング用コード: `project/src/modules/feature_engineering.py` - 特徴量生成後のデータセット: `project/data/[元データ名]-feature_engineered.csv` - 実験結果ログ: `project/reports/experiment/[番号]-[アプローチの概要].md`
Related Skills
software-engineering-lead
Expert software engineering lead who translates product requirements into comprehensive engineering plans using GitHub Projects. Reviews PRDs and user stories, identifies gaps and conflicts, pushes back constructively on poor requirements, applies software engineering best practices, creates detailed technical plans with tasks and milestones, and ensures production-ready architecture. Use when translating product specs into actionable development plans, validating requirements, or designing system architecture.
prioritize-python-3-10-features
Prioritizes the use of new features available in Python 3.12 and later versions.
plan-feature
Plan a new feature from concept to approved implementation plan. Activates Product Council for strategic evaluation, then Feature Council for technical planning. Produces a documented decision and scoped task breakdown. Use when starting any new feature work.
new-feature
Use when starting new feature development - sets up Agent Teams, gathers requirements, creates plan, implements with parallel agents, runs code review/QA/security checks, and commits with conventional commits
Implementing Features
Execute specification-driven implementation with automatic quality gates, multi-agent orchestration, and progress tracking. Use when building features from specs, fixing bugs with test coverage, or refactoring with validation.
genomic-feature-annotation
This skill is used to perform genomic feature annotation and visualization for any file containing genomic region information using Homer (Hypergeometric Optimization of Motif EnRichment). It annotates regions such as promoters, exons, introns, intergenic regions, and TSS proximity, and generates visual summaries of feature distributions. ChIPseeker mode is also supported according to requirements.
full-stack-orchestration-full-stack-feature
Use when working with full stack orchestration full stack feature
feature-status
Count features marked as @failing and write to status JSON file. Used to determine when the autonomous coding loop should end.
feature-investigation
[Investigation] Use when the user asks to investigate, explore, understand, explain, or analyze how an existing feature or logic works. Triggers on keywords like "how does", "explain", "what is the logic", "investigate", "understand", "where is", "trace", "walk through", "show me how".
feature-implementation
[Implementation] Use when the user asks to implement a new feature, enhancement, add functionality, build something new, or create new capabilities. Triggers on keywords like "implement", "add feature", "build", "create new", "develop", "enhancement".
feature-dev-workflow
Complete end-to-end feature development workflow from issue tracking through PR delivery. Use for implementing features, building new functionality, and adding capabilities. Includes requirements discovery, architecture planning, implementation, testing, code review, design audit, and comprehensive validation.
feature-design-assistant
Turn ideas into fully formed designs and specs through natural collaborative dialogue. Use when planning new features, designing architecture, or making significant changes to the codebase.