Skill UI

Apply Michael T. Nygard-inspired production reliability rules when designing failure handling, timeouts, retries, circuit breakers, observability, or deployment behavior.

Instrument AI agents with OpenTelemetry tracing, Prometheus metrics, token and cost tracking, latency monitoring, and structured logs for reliability and debugging.

This comprehensive workflow bundle covers the full lifecycle of AI and machine learning development. It includes LLM application design, RAG implementation, AI agent architecture, ML pipeline development, observability, and security. Suitable for building production-ready AI systems.

This skill specializes in creating realistic mock services for development, testing, and demonstration purposes. It simulates real API behavior to enable parallel development and facilitate thorough testing. Use it for building mock APIs for frontend or integration testing, simulating partner APIs, creating demo environments, and validating API contracts before backend completion. Avoid using for production systems or security testing.

Optimize end-to-end application performance through comprehensive profiling, observability, and tuning across backend, frontend, and infrastructure layers. Use this skill for coordinating performance improvements, establishing baselines, designing load tests, and ensuring scalability. It covers database optimization, API tuning, and distributed system enhancements to address real bottlenecks.

Design, test, and deploy an automated triage workflow for Monte Carlo data-observability alerts: fetch alerts, score incident likelihood and impact, run deep troubleshooting, and classify findings via MCP tools.

Comprehensive expert for deploying and managing AI agents at scale using AWS Bedrock AgentCore. Covers all nine core services including Gateway, Runtime, Memory, Identity, Code Interpreter, Browser, Observability, Agent Registry, and Evaluations. Use for agent deployment, MCP integration, credential management, and cross-service workflows with AWS CLI.

This skill provides expert guidance for AWS cost optimization, monitoring, and operational excellence. It helps analyze AWS bills, estimate costs before deployment, set up CloudWatch alarms, query logs, and audit CloudTrail activity. Users can optimize spending, monitor infrastructure performance, and assess security posture using integrated MCP servers for pricing, cost explorer, and observability.

Provides a .NET Azure Resource Manager SDK for creating, reading, updating, and deleting Arize AI Observability and Evaluation organizations on Azure, including Marketplace and SSO configuration.

Deploy and manage Weights & Biases ML experiment tracking instances on Azure Marketplace using the .NET Resource Manager SDK, including SSO and observability configuration.

This Python SDK enables developers to send custom logs to Azure Monitor Log Analytics workspaces using the Logs Ingestion API. It supports authentication via DefaultAzureCredential, handles async/sync uploads, manages batching, and includes error handling for partial failures. Ideal for cloud observability and log management workflows.

Auto-instrument Node.js and TypeScript applications with Azure Monitor OpenTelemetry, enabling distributed tracing, custom metrics, and log collection for cloud observability.