Skill UI

A comprehensive guide for security teams on detecting and responding to unauthorized crypto mining operations in cloud environments (AWS, Azure). It details a multi-layered approach, utilizing cost anomaly detection, compute utilization monitoring, GuardDuty findings, and network flow log analysis (VPC/KQL) to identify resource hijacking attempts and suspicious activity across EC2, ECS, and EKS workloads.

This assistant provides comprehensive performance profiling for complex computing systems. It analyzes various targets, including Python scripts, running processes, GPU utilization, and memory bottlenecks. Utilizing both external tools (like nvidia-smi, cProfile) and advanced code instrumentation, it measures CPU, memory, and interconnect performance, generating a structured report with actionable insights and a mandatory changelog of all modifications.

A comprehensive guide for optimizing query latency in Qdrant. This resource explains advanced performance tuning techniques, focusing on critical resource management like RAM utilization, segment count adjustments, and HNSW parameter tuning. It details strategies for scaling, quantization, and hardware considerations (e.g., local NVMe) to ensure consistently low-latency search performance, and outlines common pitfalls to avoid.

This skill helps healthcare organizations optimize their Abridge AI spending. It provides structured analysis across provider utilization, session waste detection, and ROI calculation. Use it when reviewing complex billing statements, optimizing contract tiers, or ensuring maximum return on investment for AI adoption.

This workflow guides users through configuring CAST AI's autoscaler policies to achieve optimal cost management and resource utilization within a Kubernetes cluster. It covers enabling spot instances, setting node downscaler/evictor rules, defining cluster limits, and creating specialized node templates (e.g., for GPU or spot workers) using Terraform. Use this when implementing Phase 2 automation or optimizing cloud spend.

This skill provides comprehensive observability for CoreWeave's GPU-intensive workloads running on Kubernetes. It monitors critical operational metrics, including GPU utilization, memory usage, inference latency (p99), and job completion rates. Use it for setting up DCGM metrics dashboards, configuring proactive alerts for underutilization or Out-Of-Memory (OOM) conditions, and ensuring high reliability for AI/ML deployments.

This guide provides expert strategies for optimizing GPU inference performance on CoreWeave infrastructure. It covers GPU selection based on workload (LLM, image generation, training), advanced techniques like continuous batching (using vLLM), autoscaling setup (HPA), and benchmarking data. Use this to maximize GPU utilization, minimize latency, and optimize large-scale AI model deployment.

This guide provides methods for cost tuning and optimization for Linktree services. It addresses how high API usage from link views, clicks, and analytics queries can lead to unnecessary expenses. Techniques include implementing robust caching mechanisms (e.g., 5-min TTL for profiles, 15-min polling interval for analytics), client-side event aggregation, and auditing plan tiers to ensure efficient resource utilization and budget adherence.

Programmatically query Oracle Cloud Infrastructure (OCI) metrics using the Monitoring Query Language (MQL) and create monitoring alarms via the Python SDK. This skill bypasses the limitations of the OCI console query builder, allowing reliable retrieval of key infrastructure metrics such as CPU utilization, memory usage, network traffic, and disk I/O. Ideal for building robust dashboards, automating resource monitoring, and setting up complex alerting rules.

This guide provides best practices for scaling multi-tenant deployments in Qdrant. It advises against the inefficient 'one collection per tenant' approach. Solutions include using shared collections with payload filtering, implementing custom sharding for large-scale tenants (100k+), and employing tiered multitenancy for unevenly sized workloads, ensuring optimal resource utilization and performance.

A sophisticated tool for Operations Leaders (CX, Support, BizOps) to model team capacity, headcount requirements, and utilization risk. Built on Erlang-C queueing theory and Little's Law, it provides capacity sizing (P50/P90/P99), utilization health checks, and a detailed 12-month quarterly hiring plan that accounts for ramp-up and attrition. Use it for annual planning and budget defense.

This skill generates a comprehensive capacity plan document for any service. It assists technical teams in proactively managing infrastructure by modeling traffic growth, forecasting resource utilization (CPU, memory, connections), projecting costs, and defining clear scaling strategies. Use this when assessing current resource headroom, planning for seasonal peaks, or defining a long-term infrastructure action roadmap.