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.
EnglishAudit ML experiment tracking infrastructure for reproducibility gaps, parameter logging completeness, metric capture, artifact management, and pipeline orchestration. Covers MLflow, Weights and Biases, DVC, Sacred, Neptune, Hydra configs, model registries, and produces a reproducibility scorecard (0-30) with actionable fixes for data science teams.
EnglishUse when optimizing model hyperparameters. Covers search strategy (random vs Bayesian/Optuna), leakage-safe tuning inside CV, search-space design, early stopping, and budget management.
EnglishUse 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.
EnglishUse 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.
EnglishUse 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.
EnglishUse when writing or reviewing pandas code. Covers idiomatic, vectorized, memory-efficient patterns; avoiding SettingWithCopyWarning, chained indexing, and slow apply loops.
EnglishUse when writing or reviewing a PyTorch training loop. Covers correct train/eval modes, gradient handling, mixed precision, checkpointing, reproducibility, and device management.
EnglishDetails on the Retrieval Augmented Generation pipeline, Ingestion, and Vector Search.
EnglishUse 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.
EnglishUse when building scikit-learn models that must not leak preprocessing. Covers Pipeline, ColumnTransformer, custom transformers, and combining preprocessing with cross-validation correctly.
English
AGENT SKILLS ATLASIncludes Data Cleaning, Experiment Tracking, Hyperparameter Tuning, and other workflows.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLISupported by the Atlas install prompt. Skill-specific requirements vary.
Pack stats
What’s included
Data Cleaning
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.
Experiment Tracking
Audit ML experiment tracking infrastructure for reproducibility gaps, parameter logging completeness, metric capture, artifact management, and pipeline orchestration. Covers MLflow, Weights and Biases, DVC, Sacred, Neptune, Hydra configs, model registries, and produces a reproducibility scorecard (0-30) with actionable fixes for data science teams.
Hyperparameter Tuning
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.
Imbalanced Data
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.
LLM Finetuning
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization
Ml Debugging
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.
Model Serving
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.
Pandas Patterns
Use when writing or reviewing pandas code. Covers idiomatic, vectorized, memory-efficient patterns; avoiding SettingWithCopyWarning, chained indexing, and slow apply loops.
PyTorch Training Loop
Use when writing or reviewing a PyTorch training loop. Covers correct train/eval modes, gradient handling, mixed precision, checkpointing, reproducibility, and device management.
RAG Pipeline
Details on the Retrieval Augmented Generation pipeline, Ingestion, and Vector Search.
Reproducible Ml
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.
Sklearn Pipelines
Use when building scikit-learn models that must not leak preprocessing. Covers Pipeline, ColumnTransformer, custom transformers, and combining preprocessing with cross-validation correctly.
Quick start
- Choose your skills. Select individual skills above, or choose the entire pack.
- Copy the install prompt. Use Copy install prompt above the list.
- Send it to your agent. Paste into your coding agent’s chat. Your agent reviews the source and guides the setup.
Try it with your agent
After installation, start with a request like:
Use the Data Cleaning skill to help with my task.
Ask me for the context you need before getting started.Requirements & license
- A coding agent that can access your project files and install skills.
- Your agent checks each skill’s instructions, dependencies, and permissions during setup.
- Reported license for the skills shown: MIT. The author’s terms apply.