Skill UI

A comprehensive guide to setting up a full-cycle local Web3 development workflow. This skill utilizes Alchemy as the RPC provider, Hardhat for local unit testing, and integrates Mainnet forking and Sepolia testnet deployment. It covers initializing the project, configuring smart contract interactions, and implementing advanced testing patterns.

This utility collects comprehensive diagnostic evidence for Algolia support tickets or internal troubleshooting. It gathers index statistics, API key access control lists (ACLs), recent query logs, and network diagnostic information using API endpoints and shell scripting. Use it when diagnosing search performance or unexpected service behavior.

This guide details advanced strategies for optimizing Claude API usage to reduce latency and cost. Techniques covered include prompt caching (significant cost reduction), strategic model selection (Haiku, Sonnet, Opus) based on task complexity, implementing streaming for perceived speed, and managing token limits. Use this guide when building high-performance, cost-efficient LLM applications that interact with large language models.

Automate the deployment of CAST AI across various multi-cloud Kubernetes clusters, including EKS, GKE, and AKS. This module uses Terraform Infrastructure as Code (IaC) patterns to reliably configure necessary components like IAM roles, node autoscaling policies, and cluster resources, ensuring standardized onboarding across different cloud environments.

This guide outlines advanced strategies to optimize latency and throughput when integrating Anthropic's Claude API. Learn critical techniques such as streaming responses, prompt caching, model selection (Haiku, Sonnet, Opus), and request parallelization, ensuring your applications provide a low-latency, high-performance user experience.

Automate the entire deployment lifecycle for ML inference services on CoreWeave GPU cloud. This workflow integrates unit testing, container image building (to GHCR), and rolling deployment to CoreWeave Kubernetes clusters via GitHub Actions. Ideal for ensuring stable, high-performance deployment of GPU-dependent models. Key features include validating GPU manifest requests and managing deployments using standard Kubernetes APIs.

A comprehensive guide to diagnose and resolve common CoreWeave infrastructure errors. It covers issues related to GPU scheduling, Pod status (e.g., Pending), CUDA Out of Memory errors, NCCL timeouts, and Kubernetes resource allocation within AI/ML deployment pipelines.

A comprehensive guide and set of tools for establishing a local development workflow tailored for CoreWeave GPU deployments. This includes steps for building Docker containers, validating Kubernetes YAML manifests using dry-run, and managing the full deployment lifecycle for AI inference services before pushing to the cloud.

A comprehensive utility designed for managing CoreWeave cloud infrastructure migrations. It facilitates upgrading between GPU generations (e.g., A100 to H100), updating CUDA versions, and handling Kubernetes resource changes. The tool uses K8s APIs to audit deployments, detect deprecated instances, and execute controlled rollbacks.

This guide provides a systematic approach to deep debugging complex HubSpot API issues. It includes layer-by-layer network testing (DNS, TCP, TLS), correlation ID tracking, and timing analysis to isolate intermittent or hard-to-reproduce errors. Use this when standard troubleshooting fails or when compiling detailed evidence for technical support.

A comprehensive diagnostic guide for common issues encountered with CAST AI agents, Kubernetes autoscaling, API connectivity, and resource provisioning. Covers scenarios like agent crashes, 401 errors, and scaling failures, providing specific commands (kubectl, curl, helm) and detailed fixes for robust troubleshooting.

This skill guides the setup and configuration of the CAST AI Workload Autoscaler, enabling dynamic right-sizing of pod resource requests (CPU and Memory). It automatically adjusts resources based on actual usage, significantly reducing cloud over-provisioning costs. Use this guide to implement workload scaling policies, configure resource limits via Kubernetes annotations, and monitor scaling events in Kubernetes environments.