skills.rest
darantrute
darantruteCOMMUNITY
Explore all skills by this author →
GitHub

groq

Integrate Groq's LLM inference with streaming chat completions via Server-Sent Events.

Updated Aug 23, 2026
Search Tags:#API integration#Next.js#real-time#streaming#groq#chatbot#LLM inference
One-click install
npx skills add https://github.com/darantrute/userdecisiontree --skill groq
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: groq
Source: https://github.com/darantrute/userdecisiontree/tree/main/.claude/skills/groq
Command: npx skills add https://github.com/darantrute/userdecisiontree --skill groq

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires groq-sdk, @ai-sdk/groq, ai, and includes references (resource) components.

What problem does it solve?

This Skill empowers developers to integrate Groq's ultra-fast LLM inference capabilities, overcoming latency challenges in AI applications. It provides patterns for streaming responses, managing rate limits, and securely using API keys, ensuring highly responsive and scalable AI features that delight users.

Core Features & Use Cases

  • Ultra-Fast LLM Inference: Leverage Groq's LPU architecture for sub-second response times and high token throughput with models like Llama 3.3 and Mixtral.
  • Real-Time Streaming & Tool Calling: Implement streaming chat completions using Server-Sent Events (SSE) and integrate advanced tool/function calling for dynamic AI interactions.
  • Robust Integration Patterns: Provides guidance for secure API key management, comprehensive error handling, exponential backoff for rate limits, and seamless integration with Next.js and Vercel AI SDK.
  • Use Case: Develop a real-time chatbot that responds instantly, generate code suggestions on the fly, or power a dynamic content creation tool where speed is critical.

Quick Start

Use the groq skill to set up a streaming chat completion endpoint in Next.js using the Llama 3.3 model.