by affaan-m
pytorch-patterns helps you write, review, and debug PyTorch code with device-agnostic patterns, reproducible experiments, and explicit tensor handling. Use the pytorch-patterns skill for cleaner training loops, model refactors, and practical PyTorch guidance.
by wshobson
vector-index-tuning helps tune vector search indexes for latency, recall, and memory. Use it to choose index types, adjust HNSW settings, and compare quantization options for RAG workflows.
by huggingface
huggingface-vision-trainer helps you install and use a Hugging Face skill for vision training jobs: object detection, image classification, and SAM/SAM2 segmentation. It covers dataset prep, cloud GPU setup, evaluation, Trackio logging, and pushing results to the Hub. Ideal for backend automation and repeatable training workflows.
by huggingface
huggingface-trackio helps track ML training runs with Trackio. Use this skill to log metrics from Python, add training alerts, and retrieve or analyze runs with the trackio CLI. It supports real-time dashboards, Hugging Face Space sync, and JSON output for automation, making huggingface-trackio useful for experiment tracking and data analysis.
by huggingface
huggingface-llm-trainer helps you train or fine-tune language and vision models on Hugging Face Jobs with TRL or Unsloth. Use this huggingface-llm-trainer skill for SFT, DPO, GRPO, reward modeling, dataset checks, GPU selection, Hub saving, Trackio monitoring, and GGUF export for backend development workflows.
by huggingface
The huggingface-best skill helps you find the best model for a task by checking Hugging Face benchmark leaderboards and filtering by device limits and model size. Use it for model recommendations in coding, reasoning, chat, OCR, RAG, speech, vision, or multimodal work when you need a practical shortlist, not a generic model list.
by huggingface
The hf-cli skill helps you use the Hugging Face Hub CLI (`hf`) for authentication, downloads, uploads, repo and bucket management, dataset and model inspection, and other Hub workflows. It is useful for Backend Development teams that want repeatable, scriptable hf-cli usage and a practical hf-cli guide.
by microsoft
azure-ai-ml-py is the Azure Machine Learning SDK v2 for Python. Use this skill to install azure-ai-ml-py, connect with MLClient, and manage Azure ML workspaces, jobs, models, datasets, compute, and pipelines. It is a strong fit for backend automation and repeatable Azure ML workflows.
by microsoft
azure-mgmt-weightsandbiases-dotnet is the .NET Azure Resource Manager SDK for Weights & Biases on Azure Marketplace. Use this azure-mgmt-weightsandbiases-dotnet skill for backend development to install the preview package, configure Azure Identity, and manage W&B instance provisioning, SSO, and resource lifecycle from C#.
by K-Dense-AI
scvi-tools is a Python framework for probabilistic single-cell analysis. Use this scvi-tools skill for batch correction, latent embeddings, differential expression with uncertainty, transfer learning, and multimodal integration. It is a strong fit for single-cell RNA-seq, ATAC, CITE-seq, multiome, and spatial workflows, especially for advanced Machine Learning use cases.
by K-Dense-AI
modal skill for Backend Development teams using Modal as a cloud runtime for Python. Learn when to use Modal for GPU workloads, autoscaling functions, web APIs, scheduled jobs, and batch pipelines, plus how to choose the right install context, read the repo, and write deployment-ready code with less boilerplate.
by microsoft
azure-ai-textanalytics-py is a skill for Azure AI Text Analytics in Python. It helps with sentiment analysis, entity recognition, key phrase extraction, language detection, PII detection, and healthcare NLP. Use it when you need a fast path to Azure client setup, authentication, and practical text analytics usage for apps, notebooks, or data analysis workflows.
by wshobson
ml-pipeline-workflow is a practical guide to designing end-to-end MLOps pipelines for data prep, training, validation, deployment, and monitoring, with orchestration patterns for repeatable workflow automation.
