Skill UI

This is a production-grade reference architecture for building scalable video generation platforms powered by Kling AI. It details the complete pipeline, from the API gateway and job queuing (Redis/SQS) to the worker pool, object storage, and CDN delivery. Use this guide when designing high-throughput, resilient, and scalable AI video systems.

This blueprint provides a scalable, production-grade reference architecture for advanced LLM applications using LangChain. It guides the implementation of layered design, provider abstraction (allowing seamless switching between LLMs like OpenAI and Anthropic), dynamic chain registry, robust RAG pipelines, and complex multi-agent orchestration. Ideal for building enterprise-level, maintainable, and highly flexible AI systems.

This guide provides production-grade architecture patterns for implementing robust LLM observability using Langfuse. It covers singleton SDK setup, context propagation across asynchronous boundaries, Express middleware for automatic tracing, and cross-service trace correlation using OpenTelemetry. Ideal for designing enterprise-level, scalable tracing infrastructure for LLM applications.

This skill provides comprehensive reference architectures for integrating Lindy AI agents into production applications. It covers various complex patterns, including simple webhook callbacks, sophisticated event-driven pipelines, multi-agent delegation systems, scheduled workflows, and RAG-powered customer chat interfaces. Essential for designing and building robust, scalable, and reliable AI-powered systems.

This guide provides production-grade architectural patterns for integrating with the Linear API. It helps developers choose the optimal strategy—be it Simple SDK calls, Service-Oriented Gateways with caching, or Event-Driven Webhooks—based on system complexity, scale, and real-time requirements. Includes patterns like CQRS and rate limiting best practices.

Provides a comprehensive, production-ready reference architecture for integrating Lokalise Translation Management System (TMS) into web applications. This guide covers the entire end-to-end translation lifecycle, including best-practice project layouts, file organization for i18n, CI/CD workflows (build-time vs. OTA paths), and necessary API client implementations. Use this when establishing new multi-language support or standardizing localization practices across a team.

This comprehensive guide details production-grade architectural patterns for integrating MaintainX with large enterprise systems, including ERPs, SCADA, and data warehouses. It covers best practices for event-driven synchronization using webhooks and Pub/Sub, implementing bi-directional sync gateways, and establishing scalable analytics data pipelines.

This guide provides a production-ready, layered architecture pattern for integrating Mistral AI into TypeScript/Node.js projects. It implements best practices including singleton client management, Zod-validated configuration, custom error handling, caching mechanisms, and robust service layer design (e.g., RAG pipelines). Use this when setting up new Mistral AI applications or needing standardized, reliable project structure.

This guide provides the best-practice reference architecture for developing complex Obsidian plugins. It details a highly modular project structure, enforcing separation of concerns by implementing dedicated layers for commands, views, and services (e.g., vault operations). Use this when designing a new plugin, reviewing existing project structure, or establishing standardized development practices for maintainable and scalable Obsidian extensions.

This comprehensive reference architecture guides the integration of OpenEvidence into clinical decision support systems (CDS). It is designed for healthcare platforms needing evidence-based query processing, deterministic citation tracking, and full audit logging. Key considerations include HIPAA compliance, optimizing for sub-second response times in point-of-care workflows, and establishing robust data models and event pipelines.

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.

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.