param087/agent-ml-skills

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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

param087/agent-ml-skills

Skill Claude CodeCodex

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

param087/agent-ml-skills

Skill Claude CodeCodex

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

param087/agent-ml-skills

Skill Claude CodeCodex

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.

param087/agent-ml-skills

Skill Claude CodeCodex

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