Machine Learning skills for Claude Code and Codex
Skills for classic and deep machine learning: scikit-learn, PyTorch Lightning, Transformers, PyTorch Geometric, SHAP explanations, UMAP, reinforcement learning with Stable Baselines3 and PufferLib, TimesFM forecasting, AutoML, experiment tracking with Trackio and SwanLab, ML pipelines and Kaggle. They give an agent the library conventions and evaluation habits that keep models honest.
Highest-scoring machine learning skills in the October 22, 2026 snapshot: kaggle from shepsci/kaggle-skill (90/100), data-scientist from tronghieu/agent-skills (86/100) and huggingface-trackio from huggingface/skills (83/100). Scores come from the Suede Skill Check.
- 29 listed skills
- 8 repositories
- 6 with full pages
7 from official publishers. 12 bundle scripts. 5 connect to an outside service. Listed in AI Agents and LLM Engineering (20), Science and Research (5), Data, Analytics and Databases (4).
All 29 machine learning skills
No matching skills. Try fewer words or clear your search.
| Skill | Repository | What it does |
|---|---|---|
| data-scientist 86/100 · B | tronghieu/agent-skills | Turns business questions into data analysis, validated models, and decision-ready reports, including dataset profiling, A/B test checks, and predictive modeling. |
| huggingface-trackio 83/100 · B | huggingface/skills | Tracks and visualizes ML training experiments with Trackio, including metric logging, training alerts with webhooks, real-time dashboards, and metric retrieval through the CLI. |
| kaggle 90/100 · A | shepsci/kaggle-skill | Handles Kaggle tasks when explicitly requested, covering competitions, datasets, models, notebooks, forums, benchmarks, hackathons, badges, and account setup. |
| ml-training-recipes 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Provides PyTorch training recipes for LLMs, vision, diffusion, and genomics, covering training loops, optimizers, learning rate schedules, mixed precision, debugging, and GPU throughput. |
| sentence-transformers 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Generates sentence, text, and image embeddings with 5000+ pre-trained models for semantic similarity, clustering, retrieval, RAG, and semantic search. |
| train-sentence-transformers 83/100 · B | huggingface/skills | Trains and fine-tunes sentence-transformers models, including bi-encoders, cross-encoders, sparse encoders, and multi-vector encoders, with guidance on loss selection, hard-negative mining, evaluators, and Hub publishing. |
| aeon 87/100 · B | K-Dense-AI/claude-scientific-skills | This skill should be used for time series machine learning tasks including classification, regression, clustering, forecasting, anomaly detection… |
| bigquery-ai-ml 79/100 · C | google/skills | Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that… |
| deepchem 81/100 · B | K-Dense-AI/claude-scientific-skills | Builds molecular property prediction and MoleculeNet workflows with DeepChem, including SMILES featurization, scaffold or grouped holdouts, masked… |
| experiment-tracking-swanlab 69/100 · D | Orchestra-Research/AI-Research-SKILLs | Provides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight… |
| ml-pipeline 82/100 · B | jeffallan/claude-skills | Designs and implements production-grade ML pipeline infrastructure: configures experiment tracking with MLflow or Weights & Biases, creates Kubeflow… |
| nvflare-convert-lightning 83/100 · B | NVIDIA/skills | Convert existing PyTorch Lightning training code into an NVFLARE federated job using the Lightning Client API patch, local validation, and job… |
| nvflare-convert-pytorch 85/100 · B | NVIDIA/skills | Convert existing plain or manual PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job… |
| pufferlib 81/100 · B | K-Dense-AI/claude-scientific-skills | Version-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint… |
| pyhealth 85/100 · B | K-Dense-AI/claude-scientific-skills | Builds and validates PyHealth clinical machine-learning pipelines for EHR, signals, imaging, and medical codes. Use for PyHealth dataset loading… |
| pytorch-fsdp2 77/100 · C | Orchestra-Research/AI-Research-SKILLs | Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use… |
| pytorch-lightning 81/100 · B | K-Dense-AI/claude-scientific-skills | Deep learning framework (PyTorch Lightning / lightning package). Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU… |
| pytorch-lightning 77/100 · C | Orchestra-Research/AI-Research-SKILLs | High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate… |
| scanpy 79/100 · C | K-Dense-AI/claude-scientific-skills | Performs Scanpy single-cell RNA-seq QC, normalization, HVG selection, PCA/UMAP/t-SNE, clustering, exploratory marker ranking, pseudobulk… |
| scikit-learn 89/100 · B | K-Dense-AI/claude-scientific-skills | Supports machine learning in Python with scikit-learn. Applies when working with supervised learning (classification, regression), unsupervised… |
| shap 89/100 · B | K-Dense-AI/claude-scientific-skills | Explain and audit machine-learning predictions with SHAP. Use for selecting SHAP explainers and maskers, computing and validating feature… |
| stable-baselines3 81/100 · B | K-Dense-AI/claude-scientific-skills | Trains and evaluates single-agent reinforcement learning with Stable Baselines3 (PPO, SAC, DQN, TD3, DDPG, A2C), Gymnasium custom environments… |
| tao-run-automl 90/100 · A | NVIDIA/skills | Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian… |
| tao-run-automl-deft-pipeline 84/100 · B | NVIDIA/skills | Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train… |
| timesfm-forecasting 81/100 · B | K-Dense-AI/claude-scientific-skills | Performs zero-shot time-series forecasting with Google's TimesFM, including regular-grid CSV preparation, quantile forecasts, XReg covariates, and… |
| torch-geometric 89/100 · B | K-Dense-AI/claude-scientific-skills | Supports PyTorch Geometric (PyG) graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous… |
| torchdrug 87/100 · B | K-Dense-AI/claude-scientific-skills | Builds and troubleshoots TorchDrug 0.2.1 workflows for molecular graphs, property prediction, self-supervised pretraining, molecule generation… |
| transformers 87/100 · B | K-Dense-AI/claude-scientific-skills | Hugging Face Transformers for loading Hub models, running pipeline inference, text generation, and Trainer fine-tuning on NLP, vision, audio, and… |
| umap-learn 77/100 · C | K-Dense-AI/claude-scientific-skills | Applies UMAP-learn to nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP… |
How to choose machine learning skills
Pick by model family. scikit-learn suits tabular data, Lightning and Transformers suit deep learning, torch-geometric suits graphs, and the RL skills suit agents in simulated environments.
Track experiments from the first run. huggingface-trackio, experiment-tracking-swanlab and ml-pipeline record parameters and metrics so results stay comparable.
Most skills run Python and some expect GPUs; the scripts list and SKILL.md say which. Explainability skills such as SHAP are worth adding before a model's predictions reach users.
Related topics
Fine-Tuning and Model Training 127Data Analysis 27Bioinformatics and Genomics 59Chemistry and Drug Discovery 28RAG and Retrieval 32Statistics 12Data Visualization and Charts 15Notebooks 3
Find your next useful skill
Explore Rising Skills with quality scores and source reports, or search from inside your agent.
Get Rising Skills by email · Read Rising Skills · Install the finder · State of Agent Skills