Skill UI

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.

This skill guides users through setting up robust, production-grade infrastructure on Fly.io. It covers creating and connecting to Fly Postgres clusters for reliable data storage, provisioning persistent NVMe Volumes for durable file storage, and configuring private internal networking (6PN) for secure service-to-service communication. It is essential for modern microservices requiring stable databases and persistent state.

This framework manages the ingestion, organization, synchronization, and search of knowledge across multiple storage layers, including local files, persistent memory, vector stores, and Git repositories. It provides a structured approach for ensuring knowledge durability, deduplication, and maintaining a 'single source of truth' across complex development and operational contexts.

This skill facilitates the persistent storage of critical brand knowledge, including campaign learnings, brand guidelines, and competitive intelligence, into a specialized memory layer (such as a vector database). It automatically indexes content, deduplicates entries via hashing, and applies rich metadata tagging, ensuring that valuable institutional knowledge is preserved and retrievable through natural language search across different sessions.

Provides tiered persistent memory patterns for LLM conversations, including short-term, long-term, entity memory, storage, retrieval, and consolidation.

Cloudish enables deploying Docker containers, source code, or images to a live HTTPS URL without local Docker installation. It builds images server-side, manages API keys with prepaid credits, and supports persistent storage for databases. Agents can prepare projects, deploy them, and diagnose failures using build logs. Ideal for hosting apps, APIs, or bots on Cloudish's platform.