Skill UI

This skill provides advanced patterns for handling high-volume Obsidian file operations, such as debouncing keystrokes, batching file reads, and throttling UI updates. It addresses single-threaded performance bottlenecks, ensuring plugins remain responsive and prevent UI freezes during bulk processing or rapid user interactions.

High-performance RLHF framework that combines Ray, vLLM, and ZeRO-3 to accelerate PPO/GRPO/RLOO/DPO training for 7B-70B+ models on distributed GPU clusters, providing a single-stack workflow for reward models and policy optimization.

OpenRouter provides a unified API gateway to access leading AI models (OpenAI, Anthropic, Google, Meta, etc.) from a single endpoint. This skill is essential for developers who need to compare model performance (latency, tokens) across different providers, build resilient cross-provider fallback workflows, or manage complex AI pipelines without writing provider-specific code. It supports feature normalization and BYOK (Bring Your Own Key) for high-volume production use.

This skill provides comprehensive best practices and Python code examples for optimizing API calls to Large Language Models (LLMs) via OpenRouter. It covers benchmarking model latency, implementing streaming to achieve low Time-To-First-Token (TTFT), and processing requests concurrently using asynchronous programming (asyncio). Use this when developing real-time, high-throughput applications that require predictable and fast model responses.

A comprehensive guide on handling API rate limits and throttling errors (429) when building high-throughput systems, particularly for LLM APIs like OpenRouter. This skill covers best practices, including using exponential backoff, implementing custom client-side rate limiters (Token Bucket), and managing concurrent requests for stable, reliable performance.

This skill simulates an expert performance engineer capable of diagnosing complex bottlenecks across the entire technology stack. It covers modern observability techniques (OpenTelemetry, APM), advanced profiling (CPU, Memory, I/O), and sophisticated load testing strategies (k6, Chaos Engineering). Use this when optimizing scalability, reducing latency, improving throughput, or architecting highly reliable, performant distributed systems in cloud environments.

A comprehensive guide covering the entire web performance optimization lifecycle. Learn how to measure Core Web Vitals (LCP, INP, CLS), identify bottlenecks using specialized tools like Lighthouse and DevTools, and apply advanced techniques such as code splitting, lazy loading, and memory leak fixes to ensure fast, stable, and high-quality user experiences.

A sophisticated AI tool that coordinates multiple specialized agents (e.g., Security, Architecture, Performance) to provide comprehensive, multi-perspective code assessments. It goes beyond single-point reviews by managing context, running hybrid execution workflows, resolving conflicts, and synthesizing unified, actionable reports for high-quality code assurance.

This guide provides comprehensive instructions for deploying applications powered by the Perplexity Sonar API. It covers setup for major cloud platforms like Vercel, Google Cloud Run, and Docker. Users can deploy production-ready endpoints, manage required secrets, implement edge functions, and utilize caching mechanisms (e.g., Redis) to ensure high availability and performance in production environments.

This skill provides comprehensive guidance on load testing and capacity planning for the Perplexity Sonar API. Users learn how to simulate high traffic volumes, respecting strict rate limits (like 50 RPM), benchmark latency, and estimate operational costs. It is essential for performance engineering, capacity architecture design, or stress testing APIs at scale.

Provides a comprehensive monitoring solution for the Perplexity Sonar API. It tracks critical performance metrics, including latency (p95), cost per query, error rates, and citation quality. This skill is essential for implementing production monitoring dashboards, configuring proactive alerts (e.g., high latency, zero citations), and ensuring the API's stability and high-quality output in real-world applications.

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.