nvidia-nim-api-builder

Community

Build and run LLM inference with NVIDIA's hosted API

Authormarktantongco
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill facilitates the construction and execution of LLM (Large Language Model) inference via NVIDIA's NIM (NVIDIA Inference Microservices) API, providing access to a variety of LLMs through an OpenAI-compatible interface.

Core Features & Use Cases

  • LLM Inference: Supports requests to NVIDIA NIM API for various LLMs including Meta Llama, Mistral, Google Gemma, and more.
  • API Integration: Enables authenticated requests to NVIDIA's hosted API.
  • Use Case: Ideal for integrating text generation, reasoning, summarization, or analysis into backend workflows, cron jobs, or automation pipelines.

Quick Start

Use the nvidia-nim-api-builder skill to generate a text summary of a given article with the command: nvidia-nim-api-builder --model meta/llama-4-maverick-17b-128e-instruct --prompt "Summarize the following article in 2 sentences." --input "AI adoption in healthcare is accelerating..."

Dependency Matrix

Required Modules

requests

Components

scripts

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: nvidia-nim-api-builder
Download link: https://github.com/marktantongco/remotion-video-pro/archive/main.zip#nvidia-nim-api-builder

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 620,000+ vetted skills library on demand.