Systematic Feature Engineering & Selection for Production ML
Engineer and select high-impact features for production ML models
What You Can Do
This skill guides you through systematic feature engineering to identify and validate features that drive real model performance. You'll leverage Claude to analyze your data, generate feature hypotheses, validate statistical significance, and quantify business impact—all with workflows designed to catch pitfalls before production deployment.
Features
Analyze distributions, correlations, and multicollinearity to identify candidate features from raw data
Brainstorm domain-specific engineered features using Claude's domain knowledge
Test feature significance, stability, and collinearity across data splits
Quantify expected model lift, ROI, and operational cost-benefit for each feature
Verify data quality, monitoring, and deployment stability before going live
Rank candidates by performance, complexity, and stability trade-offs
Identify multiplicative and non-linear relationships in your feature space
Auto-generate feature definitions, lineage, and monitoring specifications
Example Output
Feature Impact Analysis:
feature_name: customer_lifetime_days
statistical_significance: p-value < 0.001 ✓
business_lift: +3.2% churn reduction
stability_score: 0.92 (consistent across CV folds)
recommendation: INCLUDE in v1.0
Feature Engineering Candidates:
original_feature: purchase_amount
engineered_candidates:
1. log_purchase_amount
→ Gini importance: 12.3%, normal distribution
2. purchase_amount_percentile
→ rank-based, robust to outliers
3. purchase_per_day_ratio
→ rate normalization, business-relevant
ranked_recommendation: log_purchase_amount (best stability)
What's Included
- SKILL.md: Complete feature engineering workflow with decision trees and Claude prompts
- Data exploration template: Statistical analysis checklist with Python code examples
- Feature hypothesis generator: Guided brainstorm template for domain-specific features
- Statistical validation worksheet: Correlation, significance, and stability testing framework
- Business impact scoring matrix: ROI and lift estimation template
- Production readiness checklist: Data quality, monitoring, and deployment readiness assessment
- Feature monitoring specification: Drift detection and SLA monitoring template
- Data catalog documentation guide: Lineage, definitions, and ownership templates
Who It's For
- Data scientists building classification and regression models with limited feature budgets
- ML engineers optimizing model performance and reducing technical debt before production
- Analytics engineers designing feature tables and scalable data pipelines
- Product managers evaluating which ML improvements drive business outcomes
- Data-driven teams standardizing feature engineering practices across projects
Best For
- Reducing feature count without sacrificing model performance or adding complexity
- Discovering new features from existing raw data through systematic analysis
- Validating engineered features are statistically significant and stable across data splits
- Quantifying business impact of model improvements for stakeholder alignment
- Building reproducible workflows that scale as your data and models grow
You might also like
This skill guides you through rigorous experiment design from hypothesis to analysis plan. You'll compute the statistical power needed for your tests, identify confounding variables to control for, design optimal randomization strategies, and generate pre-registered analysis plans that prevent p-hacking and publication bias. Whether you're running a product A/B test or investigating causal effects in observational data, you get structured, validated designs that account for real-world constraints.
by moonwell-fi
You can build production-grade vector search systems that retrieve semantically similar documents in sub-millisecond time using AgentDB's optimized HNSW indexing. The skill enables you to implement RAG pipelines, semantic search engines, and intelligent knowledge bases with configurable embedding dimensions, distance metrics (cosine, Euclidean, dot product), and similarity thresholds—all with built-in quantization and caching for massive performance gains.
by moonwell-fi
This skill transforms high-level feature requests into actionable implementation plans by conducting deep requirement interviews, analyzing existing codebases (or planning greenfield projects), and producing comprehensive handoff documents. It distinguishes between brownfield development (with existing code to integrate) and greenfield projects (starting from scratch), ensuring your technical strategy accounts for your actual constraints and patterns.
by moonwell-fi
Diagnose root causes of model performance failures, select optimal evaluation metrics based on your use case and data characteristics, and design comprehensive evaluation strategies. You'll get systematic workflows for analyzing failure modes, statistical significance testing, threshold optimization, and cross-validation planning—turning vague model problems into actionable fixes.
by moonwell-fi
This skill helps you systematically diagnose failures in distributed ML training and serving infrastructure. You provide system logs, metrics, and error traces, and Claude performs structured root-cause analysis to identify the underlying issue—whether it's resource exhaustion, distributed system deadlock, data pipeline corruption, or model serving misconfiguration. You get a detailed diagnosis with remediation steps ranked by likelihood and implementation effort.
by moonwell-fi
Systematically evaluate your Claude prompts using quantitative scoring frameworks to identify weaknesses in clarity, task alignment, and output quality. You'll receive detailed optimization recommendations with A/B testing guidance to improve prompt effectiveness and consistency across different use cases and input variations.
by moonwell-fi
You can rapidly compile, organize, and format disparate health economic evidence—from clinical trials to cost-effectiveness analyses—into structured, regulatory-compliant dossiers. This skill maps your evidence to specific payer and HTA requirements, automatically generates evidence hierarchies, and produces submission-ready dossier outlines with formatting that meets regulatory standards for NICE, EUnetHTA, and other major bodies.
by moonwell-fi
You can confidently navigate complex statistical analyses by working through structured workflows that match your research question and data type to the right test. The skill guides you through assumption validation, helps you interpret results accurately without common pitfalls, and walks you through regression diagnostics with full transparency about what your findings actually mean.
by moonwell-fi