groq-inference-skill
Use Groq for fast LLM inference with OpenAI-compatible client
npx skills add majiayu000/claude-skill-registry --skill skills-wajahatali3218664-hackathon-02-mytodo-4 --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Groq Inference Skill ## Instructions This skill provides guidance for using Groq's fast LLM inference with an OpenAI-compatible client for AI agent logic and natural language processing. ### Project Structure ``` src/lib/ ├── groq.ts # Groq client configuration ├── agents/ │ ├── task-agent.ts # Task management agent │ ├── planner-agent.ts # Task planning agent │ └── base-agent.ts # Base agent class └── prompts/ ├── system-prompts.ts # System prompt templates └── few-shot-examples.ts # Example conversations ``` ### Groq Client Setup ```tsx // src/lib/groq.ts import OpenAI from 'openai' // Groq uses OpenAI-compatible API export const groqClient = new OpenAI({ apiKey: process.env.GROQ_API_KEY, baseURL: 'https://api.groq.com/openai/v1', }) // Available Groq models (fast inference) export const GROQ_MODELS = { LLAMA3_8B: 'llama3-8b-8192', LLAMA3_70B: 'llama3-70b-8192', MIXTRAL: 'mixtral-8x7b-32768', GEMMA: 'gemma-7b-it', } as const export type GroqModel = (typeof GROQ_MODELS)[keyof typeof GROQ_MODELS] export interface GroqCompletionOptions { model?: GroqModel temperature?: number max_tokens?: number top_p?: number stream?: boolean stop?: string[] } ``` ### Basic Inference ```tsx // sr
- Instructions
- Project Structure
- Groq Client Setup
- Basic Inference
- Task Management Agent
- Task Planner Agent
- Streaming Inference
- Examples
- Natural Language Task Creation
- Smart Task Search
- Batch Processing with Groq
What does the groq-inference-skill skill do?
Use Groq for fast LLM inference with OpenAI-compatible client
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill skills-wajahatali3218664-hackathon-02-mytodo-4 --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.