Skill UI

This skill outlines how to implement and manage Role-Based Access Control (RBAC) and namespace isolation for multi-team GPU workloads running on CoreWeave's Kubernetes platform. It provides guidance on setting strict resource quotas, preventing noisy-neighbor issues, and defining granular roles (e.g., ML Engineer, Inference Operator). This is essential for maintaining resource isolation, ensuring compliance (SOC 2, HIPAA), and managing access across large-scale cloud deployments.

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.

A comprehensive checklist for ensuring GPU workloads, such as inference services or model training pipelines, are fully prepared for production deployment on CoreWeave. It covers critical MLOps and DevOps aspects including autoscaling, resource limits, security policies, persistent storage validation, monitoring setup, and rollback procedures.

This reference architecture provides a comprehensive blueprint for deploying Machine Learning models on CoreWeave's GPU cloud infrastructure. It details the structure for multi-model serving (e.g., vLLM, TGI), scalable Kubernetes deployments, shared persistent storage (PVC), and autoscaling mechanisms using KServe/Knative. Use this when designing robust MLOps pipelines, planning high-performance multi-model inference services, or establishing standardized best practices for GPU cloud deployment.

Provides comprehensive guidelines for securing CoreWeave cloud deployments on Kubernetes. Covers critical security areas including credential management, implementing Role-Based Access Control (RBAC), enforcing network isolation policies, and handling sensitive secrets for ML model access. Essential for hardening GPU workloads and protecting data in cloud environments.

A comprehensive checklist guiding the safe and robust deployment of Text-to-Speech (TTS) integrations powered by ElevenLabs into a live production environment. It covers critical steps including API configuration, implementing health checks, setting up circuit breakers for resilience, and establishing thorough monitoring and rollback procedures, ensuring reliable voice feature go-live.

Establishes comprehensive Continuous Integration and Continuous Deployment (CI/CD) workflows for Fathom meeting intelligence. This setup includes unit tests using mocked transcripts to validate data parsing logic and robust integration tests that connect to the live Fathom API. It ensures the reliability of webhooks and data processing for real-time meeting summaries and action items upon every pull request or merge.

Automates the Continuous Integration (CI) and Continuous Deployment (CD) pipeline for Finta fundraising CRM data. It runs mocked unit tests on every pull request (PR) and executes comprehensive integration tests against the live API upon merging to the main branch. This ensures the integrity of data synchronization logic, pipeline stage transitions, and automated investor reporting workflows.

This skill provides comprehensive CI/CD pipeline setup for Fly.io edge deployments. It automates unit testing on pull requests, deploys to staging environments, and promotes changes to production upon merging to the main branch. It handles Docker builds, uses flyctl for deployment, and includes health checks to ensure service reliability and seamless automated delivery.

This comprehensive bundle collects all necessary diagnostic evidence for Fly.io applications, including machine status, application logs, volume metadata, and network diagnostics. It is crucial for generating detailed support tickets and troubleshooting complex infrastructure issues such as stuck deployments, boot failures, or edge networking problems.

This guide provides comprehensive strategies to significantly boost the performance and reliability of applications deployed on Fly.io. Techniques covered include eliminating cold starts (auto-stop/start), right-sizing Virtual Machines based on workload demands, implementing multi-region deployment for low latency, and optimizing connection pooling for databases. Essential for scaling modern SaaS applications.

This comprehensive checklist guides developers through hardening their application for production deployment on Fly.io. It covers critical aspects such as multi-region redundancy, secure secret management, robust health checks, graceful shutdown procedures, and automated rollback mechanisms. Use it to ensure your edge-deployed application is highly available, reliable, and resilient against common operational failures.