Skill UI

This skill provides comprehensive guidance for deploying and managing GPU-accelerated AI inference services on CoreWeave Kubernetes (CKS). It covers best practices including containerization using NVIDIA CUDA base images, configuring specific GPU resource limits (A100/H100), setting up robust health checks, and executing controlled rolling updates. Ideal for managing multi-model inference and scaling demanding AI workloads in a cloud environment.

This runbook provides structured steps for responding to critical production incidents on the CoreWeave platform. Use it when dealing with GPU workload failures, inference service outages, or general Kubernetes resource issues. It guides users through checking pod status, node health, and diagnosing common model loading errors to ensure rapid service recovery.

This skill provides advanced integration for deploying applications on Fly.io, focusing on edge computing architectures. It covers building production-ready Docker images, configuring `fly.toml` for services and health checks, and executing sophisticated deployment strategies like blue-green and canary releases. It ensures reliable, scalable deployment across multiple regions, including automated rollbacks and micro-VM optimization.

This guide provides methods for robust monitoring and automation tailored for services deployed on Fly.io. It covers key areas including polling the Machines API to detect state changes, implementing comprehensive health check endpoints, processing structured logs using tools like `jq`, and automating deployment notifications within CI/CD pipelines. Essential for achieving high availability and reliable operations.

Provides a comprehensive, production-ready deployment solution for OneNote integrations in containerized environments. This skill addresses critical issues like MSAL token persistence (supporting both file and Redis caches), implementing deep health/readiness checks that validate actual Graph API connectivity, and managing graceful shutdowns. Ideal for containerizing OneNote services for robust, scalable production use with Docker and Kubernetes.

KubeEye is a comprehensive cluster inspection tool designed for Kubernetes environments, particularly within KubeSphere. It systematically detects issues across workloads, nodes, and configurations by integrating multiple policy engines, including OPA/Rego, PromQL, file integrity checks, kernel parameter validation, and systemd health checks. Users can define custom inspection rules (InspectRule), schedule checks (InspectPlan), and retrieve detailed reports (InspectResult) to ensure cluster compliance and stability.

This tool provides a comprehensive overview of the federation's operational status. It allows users to check overall health, list connected peers along with their trust levels and scores, and summarize crucial metrics like active sessions, message exchanges, PII redactions, and detected threats. Use it to inspect cross-installation agent connectivity and ensure the stability of the federated system.