Skill UI

Use this tool to query, filter, and compare over 400 available AI models from OpenRouter. It allows users to check pricing, context lengths, model capabilities (e.g., tool calling), and select the best model based on specific needs, ensuring optimal performance and cost efficiency in AI development.

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.

Guides engineers through advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability across few-shot learning, reasoning patterns, templates, and system prompt design.

Qdrant is a high-performance, Rust-powered vector database designed for production-grade RAG (Retrieval-Augmented Generation) and semantic search applications. It provides fast nearest neighbor search, supports complex hybrid search using metadata filtering, and offers horizontal scalability through sharding and replication. Ideal for building real-time recommendation systems and enterprise-level knowledge retrieval.

This skill provides implementation patterns for managing API rate limits when integrating Retell AI for voice agents and telephony systems. It guides developers on handling common API errors (such as 429 Rate Limited) and implementing robust backoff strategies, ensuring stable and scalable operation for complex voice and communication applications.

This resource provides production-ready, structured patterns for building robust voice agent applications using the Retell AI SDK. It covers best practices such as implementing singleton client management, defining typed agent configurations with integrated LLMs, adding automatic retry logic for call failures, and managing large-scale outbound campaigns. Use this when building stable, scalable, and reliable voice automation systems.

This skill provides a dedicated lab environment and pattern guidance for exploring and utilizing advanced, complex capabilities within the Claude AI framework. Use it when you need a structured space to test, develop, and understand advanced AI workflows and powerful features.

A comprehensive guide demonstrating the full lifecycle of GPU resource utilization on Vast.ai. This includes searching for available hardware using CLI and REST APIs, provisioning a dedicated GPU instance (e.g., using PyTorch images), connecting via SSH, running deep learning workloads, and finally, securely destroying the instance to stop billing. Ideal for testing cloud integration or managing ML compute pipelines.

This guide details the production-grade reference architecture for running complex GPU compute workflows on Vast.ai. It covers the foundational three-tier pattern—Orchestrator, GPU Workers, and Artifact Storage—providing blueprints for job queue management, fault-tolerant training pipelines, and robust checkpointing. Use this when designing scalable and reliable ML/AI training systems.

This skill guides the development of advanced voice agents, representing the frontier of natural human-AI interaction. It covers both low-latency Speech-to-Speech (S2S) architectures (like OpenAI Realtime API) and fully controllable STT→LLM→TTS pipelines. Key focus areas include minimizing end-to-end latency (targeting <800ms), handling conversational nuances, background noise, and managing interruptions for applications like customer support, IVR, and live translation.

Designs and builds production-ready real-time voice agents with OpenAI Realtime, Vapi, Deepgram, ElevenLabs, LiveKit, and WebRTC, optimizing for latency, audio quality, and responsive UX.

Guides automating Wit AI through Composio’s Rube MCP by discovering available schemas, managing active connections, and executing schema-compliant tools across workflows.