nvidia-skills

Q: How to install nvidia-skills?

Create the skills directory: mkdir -p .claude/skills. Then run: mkdir -p .claude/skills && curl -o .claude/skills/nvidia-skills.md https://raw.githubusercontent.com/NVIDIA/skills/main/SKILL.md. Finally, /nvidia-skills in Claude Code.

Q: What is nvidia-skills best for?

nvidia-skills is categorized under Development. It covers: api, agent, python.

New

1.3kOfficial PluginDevelopmentby NVIDIA

NVIDIA agent skills for accelerated-computing workflows — starting with cuOpt vehicle-routing optimization (VRP, TSP, PDP) via the cuOpt Python API.

Python160 forks16 issuesUpdated 6/16/2026First seen 6/2/2026

Summary

This skill integrates NVIDIA cuOpt for accelerated vehicle-routing optimization, enabling Claude Code to solve complex routing problems like VRP, TSP, and PDP directly from the chat.

It leverages the cuOpt Python API to provide high-performance solutions for logistics and fleet management, saving developers time on implementing optimization algorithms from scratch.

Install & Usage

Create the skills directory

mkdir -p .claude/skills

Download the skill file

mkdir -p .claude/skills && curl -o .claude/skills/nvidia-skills.md https://raw.githubusercontent.com/NVIDIA/skills/main/SKILL.md

Invoke in Claude Code

/nvidia-skills

Use Cases

Optimize delivery routes for a fleet of vehicles to minimize total travel distance and time.

Solve the traveling salesman problem to find the shortest possible route visiting a set of locations.

Model pickup and delivery problems with time windows and capacity constraints for logistics planning.

Generate initial feasible solutions for large-scale routing problems using cuOpt heuristics.

Compare multiple routing scenarios by adjusting vehicle counts, depot locations, or demand patterns.

Integrate cuOpt optimization results into a broader supply chain or dispatch system.

Usage Examples

/nvidia-skills solve VRP with 50 customers and 5 vehicles starting from depot at [40.7128, -74.0060]

Use cuOpt to find the optimal TSP route for these 10 city coordinates: [list of lat/lon pairs]

Set up a PDP with 20 pickup and delivery pairs, each with time windows [8-10, 10-12, ...], and solve with cuOpt

View source on GitHub

apiagentpython

Security Audits

LicenseUnknownSourcePassRepositoryPass

Frequently Asked Questions

What is nvidia-skills?

This skill integrates NVIDIA cuOpt for accelerated vehicle-routing optimization, enabling Claude Code to solve complex routing problems like VRP, TSP, and PDP directly from the chat. It leverages the cuOpt Python API to provide high-performance solutions for logistics and fleet management, saving developers time on implementing optimization algorithms from scratch.

How to install nvidia-skills?

To install nvidia-skills: create the skills directory (mkdir -p .claude/skills), then run: mkdir -p .claude/skills && curl -o .claude/skills/nvidia-skills.md https://raw.githubusercontent.com/NVIDIA/skills/main/SKILL.md. Finally, /nvidia-skills in Claude Code.

What is nvidia-skills best for?

nvidia-skills is a skill categorized under Development. It is designed for: api, agent, python. Created by NVIDIA.

What can I use nvidia-skills for?

nvidia-skills is useful for: Optimize delivery routes for a fleet of vehicles to minimize total travel distance and time.; Solve the traveling salesman problem to find the shortest possible route visiting a set of locations.; Model pickup and delivery problems with time windows and capacity constraints for logistics planning.; Generate initial feasible solutions for large-scale routing problems using cuOpt heuristics.; Compare multiple routing scenarios by adjusting vehicle counts, depot locations, or demand patterns.; Integrate cuOpt optimization results into a broader supply chain or dispatch system..