Skill UI

Utilizes the Azure AI Projects SDK's ImageBasedHostedAgentDefinition to build robust, container-based AI agents deployed in Azure AI Foundry. This workflow is essential for creating production-grade agents that require custom logic, precise resource allocation (CPU/Memory), and integration of advanced tools like code interpreters.

Helps analyze current CPU, memory, storage, and network utilization to forecast future infrastructure needs, identify bottlenecks, and recommend scaling tactics with cost context for proactive capacity management.

Helps analyze current CPU, memory, storage, and network utilization to forecast future infrastructure needs, identify bottlenecks, and recommend scaling tactics with cost context for proactive capacity management.

This comprehensive skill guides the systematic optimization of end-to-end application performance across the entire stack. It covers establishing performance baselines through deep profiling (CPU, Memory, I/O), assessing observability gaps, optimizing databases, tuning backend services and APIs, and enhancing frontend rendering. Ideal for complex, scalable applications that require measurable performance improvements, reliability enhancements, and adherence to modern user experience standards.

This comprehensive skill guides the systematic optimization of end-to-end application performance across the entire stack. It covers establishing performance baselines through deep profiling (CPU, Memory, I/O), assessing observability gaps, optimizing databases, tuning backend services and APIs, and enhancing frontend rendering. Ideal for complex, scalable applications that require measurable performance improvements, reliability enhancements, and adherence to modern user experience standards.

A comprehensive Python SDK for interacting with Azure Monitor services. It enables developers to execute complex Kusto Query Language (KQL) queries against Log Analytics workspaces and retrieve various resource metrics (CPU usage, network traffic, etc.). Ideal for building robust monitoring dashboards, automated alerting systems, and custom data analysis pipelines in cloud environments.

Automates cpu profiler configuration guidance for performance testing, covering load, stress, benchmarking, and monitoring scenarios to ensure best practices.

Analyzes CPU, memory, I/O, and database traces to find and fix bottlenecks, offering remediation strategies when diagnosing slow applications, optimizing resource use, or preventing performance issues.

This guide details the use of the GGUF format and quantization techniques for running large language models (LLMs) efficiently. GGUF enables optimal inference on consumer hardware, Apple Silicon, and systems requiring CPU-only operation. By compressing models using various K-quant methods (like Q4_K_M), developers can significantly reduce memory footprint and hardware requirements while maintaining high performance.

Provides a comprehensive guide and Python implementation for creating container-based hosted agents in Azure AI Projects. It utilizes ImageBasedHostedAgentDefinition to define the agent's container image, required resources (CPU/memory), supported tools, and communication protocols. Essential for deploying robust, production-ready AI agents within the Azure ecosystem.

Execute complex and compute-intensive workloads directly on fully managed Hugging Face cloud infrastructure. This skill eliminates the need for local setup, allowing users to run jobs using cloud CPUs, GPUs, or TPUs. Ideal for large-scale data processing, batch inference, reproducible model training, and scheduled automation tasks, while persisting results to the Hugging Face Hub.

A systematic, multi-phase workflow designed for diagnosing and resolving complex Linux system issues. It guides users through initial assessment, resource analysis (CPU, memory, disk), process investigation, log analysis, network diagnostics, and service failure resolution. Ideal for system administrators and DevOps engineers handling production incidents.