Skill UI

Provides comprehensive patterns for creating production-grade client wrappers when integrating with OpenRouter via the OpenAI SDK. This skill covers handling advanced topics such as robust retry mechanisms, structured typing, caching strategies, and middleware implementation. It is essential for developers building stable, reliable SDKs or commercial client libraries that require enterprise-level API robustness.

This comprehensive guide provides developers with step-by-step instructions for migrating applications from direct calls to proprietary Large Language Model (LLM) APIs (such as OpenAI or Anthropic) to utilizing the unified OpenRouter gateway. It details essential code changes, including updating base URLs, managing API keys, adding custom headers, and correctly prefixing model identifiers. This ensures a seamless transition, enabling multi-model compatibility and simplified API management.

Enables Claude to orchestrate multi-agent systems using AI SDK v5, setting up agents, handoffs, intelligent routing, and workflows across OpenAI, Anthropic, and Google when users request complex agent coordination.

This guide provides comprehensive instructions for installing and configuring the Perplexity Sonar API authentication. It details setting up the necessary environment variables and using the standard OpenAI client library (for both Node.js and Python) to connect to Perplexity's API endpoint. Learning this process is essential for developers starting a new Perplexity integration, setting up API keys, or verifying API connectivity.

This skill provides production-ready patterns for integrating with the Perplexity Sonar API in both TypeScript and Python. It covers best practices for creating robust wrappers around the standard OpenAI client, including dedicated handling for citations, search results, and related questions. It also includes essential utilities like implementing exponential backoff for reliable retries. Use this when setting up complex search-augmented generation workflows or standardizing team coding practices around Perplexity usage.

Use Azure OpenAI Realtime Mini to turn text prompts into streamed PCM audio, convert it to WAV, and deliver base64 payloads for frontend playback, handling transcripts and voice tuning for podcast-style narration.

Covers prompt and response caching plus Cache Augmented Generation patterns for LLMs such as Claude and OpenAI to reuse stable context, reduce repeat work, and cut latency/cost on recurring queries.

Runs external LLM CLIs (OpenAI Codex or Google Gemini) to review uncommitted changes, branch diffs, or specific commits, providing an independent second opinion before merges or releases.

Serve production-grade LLM APIs with vLLM, leveraging PagedAttention, continuous batching, quantization, and tensor parallelism to maximize throughput while keeping latency, GPU usage, and scalability under control for OpenAI-compatible deployments.

A comprehensive diagnostic bundle designed for developers integrating with the Speak API. It systematically collects critical information, including authentication status, audio format validation (checking codecs, sample rates, and file size using ffprobe), and network connectivity tests for both Speak and OpenAI endpoints. Use this tool when troubleshooting complex language learning integration issues or verifying API setup.

This guide details how to set up the Speak language learning platform integration. It covers installing necessary SDKs (Speak SDK, OpenAI), configuring API keys, and establishing the connection required for sophisticated AI-powered tutoring. Use this when building applications that require real-time speech recognition, pronunciation feedback, and multilingual language support.

This guide provides a comprehensive deep dive for migrating language learning platforms, covering everything from importing student progress to transitioning from legacy speech APIs. It details configuration using modern SDKs, integrating services like OpenAI's GPT-4o and Whisper, and includes verification steps. It is essential for managing complex platform migrations and ensuring a smooth operational transition.