Skill UI

This skill provides comprehensive best practices for managing data within AI agent workflows. It covers data classification (PII, PHI), prompt-level controls, secure memory usage, and isolation techniques. It ensures that agents adhere to global regulations like GDPR, CCPA, and HIPAA when handling sensitive or regulated data.

A comprehensive skill for leveraging massive pre-trained transformer models across diverse AI domains, including Natural Language Processing (NLP), Computer Vision (CV), and Audio. Use this skill for advanced tasks such as text generation, classification, question answering, summarization, object detection, and model fine-tuning on proprietary datasets. It provides streamlined pipelines and granular control for deployment.

Amazon Macie is a fully managed AWS service utilizing advanced machine learning and pattern matching to discover, classify, and protect sensitive data (PII, financial records, credentials) stored in Amazon S3. It provides deep visibility into your cloud data, enabling comprehensive Data Loss Prevention (DLP) and compliance auditing by identifying specific sensitive data types through automated and targeted discovery jobs.

This skill guides users on setting up and running LLM-as-judge evaluations using Arize. It covers defining evaluators (including prompts, classification choices, and models) and executing tasks against real data spans or experiments. It supports key metrics like hallucination, faithfulness, and correctness, and facilitates continuous monitoring for comprehensive LLM performance analysis.

PyTorch Geometric is a standard library for Graph Neural Networks built on PyTorch. It supports node, link, and graph classification, message passing algorithms like GCN and GAT, heterogeneous graphs, and neighbor sampling. Ideal for building scalable GNN models with custom datasets and transforms.

Scikit-learn is the industry-standard Python library for classical machine learning. It provides comprehensive tools for supervised and unsupervised learning tasks, including classification, regression, clustering, and dimensionality reduction. Use it to build robust, production-ready ML pipelines, perform rigorous model evaluation, and preprocess complex datasets for various data science applications.

Train object detection, image classification, and SAM/SAM2 segmentation models locally or on Hugging Face Jobs with dataset validation and Hub saving.