Skill UI

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.

This skill provides implementation patterns for cost tuning within the Retell AI platform, specifically tailored for voice agents and complex telephony workflows. It helps developers build, monitor, and optimize the operational costs of AI-powered voice automation systems, ensuring efficient resource management when integrating real-time voice services.

This skill provides implementation patterns for building enterprise-grade AI voice agents and automating complex phone call workflows using the Retell AI platform. It covers SDK integration, resource management, and handling common telephony APIs errors, making it ideal for developers building conversational AI applications and advanced communication systems.

This skill provides deep dive implementation patterns for migrating and utilizing Retell AI. It focuses on building sophisticated voice agents and automating phone call interactions using the official SDK. Users will learn how to manage agents, handle API calls, and implement robust error handling for complex telephony applications, making it ideal for building automated call centers or interactive voice systems.

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.

Sentence Transformers provides 5000+ pre-trained models that generate sentence, text, and image embeddings for RAG, semantic search, clustering, and multilingual production workloads without relying on external APIs.

Orchestrates Serpapi searches through Composio's Rube MCP by discovering current tool schemas, validating the connection, and executing schema-compliant calls with session reuse and explicit memory placeholders to keep automation workflows reliable.

This comprehensive guide demonstrates how to build a robust AI language tutoring session using the Speak SDK. It covers initiating conversations, submitting student responses (text or audio), performing deep pronunciation assessment at the phoneme level, and generating detailed session summaries with grammar and vocabulary metrics. Ideal for developing language education platforms and testing API integration.

This skill provides advanced guidelines for designing robust and effective tools specifically for autonomous AI agents. It shifts the focus from traditional developer APIs to contracts optimized for Language Models (LLMs). Key topics covered include treating tool descriptions as prompt engineering, implementing namespacing, applying the Consolidation Principle, and utilizing Architectural Reduction patterns (like file system access) to maximize agent reliability and workflow complexity.

torchforge is Meta's advanced PyTorch-native library designed for agentic Reinforcement Learning (RL). It fundamentally separates core RL algorithms from complex distributed infrastructure concerns. This allows researchers to rapidly prototype and experiment with novel RL methods (like GRPO) using clean, PyTorch-native abstractions, while automatically handling large-scale tasks like distributed training across thousands of GPUs using Monarch and TorchTitan.

This skill provides a comprehensive workflow for integrating TwinMind meeting transcription services into continuous integration/continuous deployment (CI/CD) pipelines. It automates the processes of meeting documentation, real-time transcription (using Ear-3), and structured action item extraction using advanced AI models like GPT-4 and Claude. Use this when setting up automated meeting intelligence operations or managing enterprise-level transcription workflows via API.

This guide provides comprehensive steps for deploying TwinMind integrations into production environments. It covers configuring the Chrome extension, setting up mobile app access, and managing API keys. TwinMind utilizes advanced AI models (including Ear-3 for transcription and GPT-4/Claude/Gemini for summarization) to provide real-time meeting transcription, summarization, and action item extraction. Ideal for professional teams managing high-volume AI meeting operations.