agent-ml-skills

Use when preparing raw data for modeling — handling missing values, duplicates, inconsistent types, outliers, and bad categorical values. Emphasizes fitting all imputation on train-only to avoid leakage.

Use when running ML experiments that need to be compared, reproduced, or shared. Covers MLflow/Weights & Biases logging, what to track, run organization, and model registry basics.

Use when starting on a new dataset, before modeling, or when asked to "explore", "profile", "understand", or "summarize" data. Covers structured EDA, distributions, correlations, target leakage checks, and visualization.

Use when creating, encoding, scaling, or selecting features for ML models. Covers categorical encoding, numeric transforms, datetime/text/aggregation features, and leakage-safe target encoding.

Use when optimizing model hyperparameters. Covers search strategy (random vs Bayesian/Optuna), leakage-safe tuning inside CV, search-space design, early stopping, and budget management.

Use when the target is rare (fraud, churn, disease, anomalies). Covers correct metrics, resampling (SMOTE/undersampling), class weights, threshold tuning, and avoiding the accuracy trap and resampling leakage.

Use when fine-tuning a large language model. Covers choosing full vs LoRA/QLoRA, dataset formatting, the transformers/PEFT/TRL stack, key hyperparameters, and evaluating fine-tunes without overfitting.

Use when a model won't learn, loss is NaN, metrics look too good/bad, or training is unstable. Provides a systematic decision tree for diagnosing data, optimization, and generalization failures.

Use when choosing metrics, validating models, or interpreting results. Covers metric selection by problem type, cross-validation strategy, calibration, confusion-matrix analysis, and avoiding misleading scores.

Use when deploying a trained model behind an API. Covers FastAPI inference services, loading artifacts safely, request validation, batching, ONNX/quantization for speed, health checks, and monitoring.

Use when writing or reviewing pandas code. Covers idiomatic, vectorized, memory-efficient patterns; avoiding SettingWithCopyWarning, chained indexing, and slow apply loops.

Use when writing or reviewing a PyTorch training loop. Covers correct train/eval modes, gradient handling, mixed precision, checkpointing, reproducibility, and device management.

Use when building retrieval-augmented generation. Covers chunking strategy, embedding choice, vector stores, hybrid + reranking retrieval, prompt assembly, and evaluating retrieval and answer quality.

Use when an ML result must be reproducible — fixing seeds, pinning environments, versioning data, and structuring projects so runs can be exactly recreated. Covers determinism gotchas across NumPy, PyTorch, and CUDA.

Use when building scikit-learn models that must not leak preprocessing. Covers Pipeline, ColumnTransformer, custom transformers, and combining preprocessing with cross-validation correctly.