Skill UI

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 reference architectures for building production-grade AI applications using OpenRouter as a unified LLM gateway. It covers three scaling patterns: simple single-service, standard microservice (with caching and budget enforcement), and enterprise event-driven systems (with message queues and workers). Use this when planning system design, reviewing complex AI pipelines, or ensuring scalability and cost control in your LLM integration.

Orchestrate PagerDuty incidents, services, on-call schedules, and analytics through Composio’s toolkit using Rube MCP, with mandatory schema discovery and active connections before each workflow.

This comprehensive runbook provides step-by-step procedures for rapidly responding to Perplexity API outages and service degradations. It covers initial triage (checking models, auth, DNS), handling common errors (401, 429, 500/503), implementing fallbacks, and structured post-incident activities, including evidence collection and postmortem documentation.

This guide outlines the comprehensive reference architecture for building advanced, AI-powered search and research applications, modeled after Perplexity. It covers three core tiers: a searchable service with model routing and caching, a citation pipeline for validation and rendering, and an orchestrator for multi-query research synthesis. Use this when designing complex, production-grade, search-augmented LLM integrations or reviewing advanced system patterns.

This skill provides comprehensive patterns for building highly reliable applications that interact with external Large Language Model (LLM) APIs, such as Perplexity Sonar. It implements critical reliability techniques including Circuit Breakers, Model Fallback, Streaming Timeout handling, and Caching layers. Use this to ensure your application maintains high availability and graceful degradation even when external services experience intermittent failures or variable performance.

This skill guides the complete setup and configuration of PostHog SDKs for modern applications. It covers best practices for implementing client-side (browser) and server-side (Node.js/Python) event tracking. Users will learn how to install the necessary SDKs via npm or pip, manage environment variables for both Project API Keys and secure Personal API Keys, and initialize the tracking service correctly to ensure accurate and reliable event capture in PostHog.

This comprehensive guide teaches the best practices for writing effective, blameless postmortem reports following technical incidents. It provides a structured approach to documenting timelines, conducting root cause analysis (RCA), identifying systemic failures, and creating actionable follow-up items. Mastering this skill is crucial for fostering organizational learning and preventing future service disruptions.

Diagnoses and fixes Prisma connection pool exhaustion in serverless deployments (Vercel, Lambda, Netlify) by routing through pooling services, limiting client connections, and tuning timeouts to stop P2024/too many connection errors under load.

An end-to-end workflow for building robust, production-ready Python backend APIs. This guide covers all stages, including project scaffolding, SQLAlchemy database integration, Pydantic validation, implementing JWT/OAuth2 authentication, comprehensive error handling, unit testing, and Docker deployment for modern microservices.

Automated guidance for setting up RabbitMQ queues in backend services, covering patterns, code snippets, and validation for Node.js, Python, Go, and microservices messaging scenarios.