Skill UI

Handles disaster recovery, PITR, and automated failover for production databases via the database-recovery-manager plugin, streamlining backup validation and recovery testing whenever users ask for database recovery support.

Automates database replication tasks with the database-replication-manager plugin, covering setup, failover, lag monitoring, and read scaling for PostgreSQL/MySQL clusters.

A comprehensive guide on implementing failover and fallback mechanisms for Large Language Models (LLMs) when using OpenRouter. This skill covers native model fallbacks, provider routing strategies, and advanced client-side fallback chains. Use this pattern when building mission-critical or highly resilient systems that must maintain service availability even if a primary model or an entire provider goes offline. It ensures robust API integration and graceful degradation.

This skill demonstrates advanced techniques for managing high-volume API calls to LLM services via OpenRouter. It implements multi-key round-robin strategies, incorporating health checks and circuit breakers to distribute load across multiple API keys. It also covers concurrent request processing using asyncio and provider-level failover, ensuring high availability and maximizing throughput when facing rate limits.

This skill provides comprehensive tools to monitor the real-time availability, status, and performance of various large language models (LLMs) accessed via OpenRouter. It supports active health probes, catalog checks, and scheduled monitoring via Python and Bash, ensuring robust fault detection and failover logic for production systems that rely on external AI APIs.

Generates tailored disaster recovery plans and setup code that automate infrastructure configuration, encryption, testing, and multi-region failover for AWS or other environments when you request DR strategy or business continuity support.

This skill enables Claude to run the load-balancer-tester plugin and validate traffic distribution, failover handling, sticky sessions, and health check behavior so teams can ensure high availability before deployment.

This comprehensive runbook provides a self-service solution for managing Oracle Cloud Infrastructure (OCI) outages when official status pages are misleading or silent. It guides users through independent service health probes (Identity, Compute, Networking), automated instance recovery actions (reboot, softreset), and critical procedures for cross-Availability Domain (AD) or cross-region failover using boot volume backups to ensure business continuity.

A comprehensive guide to implementing production-grade reliability patterns for Snowflake environments. Covers advanced techniques like Time Travel for point-in-time recovery, cross-region database replication, account failover groups for disaster recovery, and application-level resilience coding (e.g., connection failover logic). Essential for building fault-tolerant, highly available data pipelines.