Skill UI

Automates creation of A/B test configurations for ML deployment, guiding users through best practices, code samples, and validation steps so production models are served with monitoring and rollout control.

A comprehensive framework for rigorously testing and benchmarking LLM agents. It moves beyond simple pass/fail checks to assess complex behaviors, reliability metrics, and capability consistency across multiple runs. Ideal for production monitoring and identifying subtle failure modes in advanced AI agents.

This is the .NET SDK for managing Arize AI Observability and Evaluation resources within Azure Resource Manager (ARM). It provides programmatic access to create, read, update, and delete AI organization resources. It is essential for MLOps professionals and developers who need to monitor, track, and evaluate the performance of AI models deployed on Azure.

This SDK provides a dedicated Python interface for securely sending custom logs to Azure Monitor Log Analytics workspace. It utilizes the Logs Ingestion API, supporting features like batch compression, advanced error handling, asynchronous uploads, and compatibility with various authentication models, including sovereign clouds.

Provides automated guidance for setting up canary deployments in ML production environments, covering model serving, MLOps pipelines, monitoring, and configuration validation.

Comprehensive guide for configuring Bring Your Own Key (BYOK) for major AI providers, including OpenAI, Anthropic, Google Gemini, Azure, and custom endpoints. This allows users to bypass default quotas, manage costs directly with the source provider, and utilize a wide range of specialized models within the Cursor IDE. It covers setup steps, security best practices, and cost monitoring strategies.

This comprehensive dashboard tracks and analyzes usage metrics for AI coding assistants (Cursor) in enterprise environments. It monitors total requests, model consumption, user adoption rates, and associated costs. Managers can use it to optimize resource quotas, control AI spending, and calculate the Return on Investment (ROI) to justify AI tool adoption.

An expert in designing, implementing, and optimizing scalable, reliable, and cost-effective data pipelines for both batch and streaming data. Covers advanced topics including ETL/ELT patterns, Kappa/Lambda architectures, workflow orchestration (Airflow/Prefect), transformation using dbt/Spark, and managing modern storage formats like Delta Lake and Iceberg. Focuses heavily on data quality, monitoring, and cost optimization strategies.

Deploying Machine Learning Models automates serving trained models to production by analyzing requirements, generating API and infrastructure code, and orchestrating deployment workflows with validation, error handling, and monitoring baked in.

This skill provides comprehensive APIs and patterns for managing AI models, tracking usage, and handling pricing structures within a platform environment. It is essential for developers needing to integrate robust model lifecycle management, usage monitoring, and billing logic into their applications.

Firecrawl provides a comprehensive API for web data harvesting. It enables users to perform single-page scraping, multi-page crawling, site mapping (URL discovery), and advanced structured data extraction using Large Language Models (LLMs). Ideal for integrating data pipelines, building web monitoring tools, or conducting market research.

Generates complete, production-ready Google Cloud Platform (GCP) code examples and infrastructure templates. It spans various modern AI patterns, including ADK agents, Genkit RAG flows, and multimodal analysis using Vertex AI and Gemini. The output includes runnable code, deployment configuration (Terraform/IaC), security best practices (IAM, VPC-SC), and monitoring setup, ensuring enterprise-grade reliability and cost optimization.