Official NVIDIA-verified skills for AI agents to use CUDA-X libraries and platform tools correctly.
NVIDIA Agent Skills is easy to set up with strong trust signals. Check agent compatibility and use-case fit before adding it to your workflow.
Repository setup guidance
npx skills add NVIDIA/skillsRun the command in your terminal.
Confirm that the skill files were added to your agent workspace.
Check the README requirements before invoking the skill in your agent.
This repository contains ready-made instruction sets that teach AI agents how to use NVIDIA's tools and libraries. Developers can install these skills into their AI coding agents so the agents can correctly perform tasks like solving optimization problems or deploying AI services. The skills are maintained by NVIDIA and updated daily.
NVIDIA Agent Skills is a public catalog of portable instruction sets that enable AI agents to correctly use NVIDIA CUDA-X libraries, AI Blueprints, and platform tools. Each skill is a structured set of instructions that guides an agent through a specific task, such as using the cuOpt solver for numerical optimization or deploying an AI-Q service. Skills are maintained in their respective product repositories and mirrored here daily via an automated sync pipeline. The repository includes a CLI tool for easy installation into popular AI coding agents like Claude Code, Codex, Cursor, and Kiro. The catalog covers products like AIQ (research and deployment), CUDA-Q (quantum computing), and more. This open-source project is licensed under Apache 2.0 and CC-BY-4.0.
Strong trust signals; still review the README and permissions before production use.
Last commit was about 51 days ago.
1081 GitHub stars indicate community interest.
20 open issues signal maintenance load.
NOASSERTION license detected.
Teach an AI agent to solve linear programming problems using NVIDIA cuOpt
Guide an agent through deploying a local AI-Q service for research workflows
Help an agent correctly use CUDA-Q for quantum computing tasks
Automate the installation of NVIDIA skills into multiple coding agents at once
Enable agents to perform shallow or deep research using AI-Q blueprints
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing.
Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Skills are mirrored from product repos; verify authenticity before use in production.
Skills may execute code; review skill instructions before installing in sensitive environments.
1,081
Stars
126
Forks
20
Issues
NOASSERTION
License
A public repository of example skills for Claude, demonstrating how to create reusable instructions and resources for specialized tasks.
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline finds security vulnerabilities, logic errors, and runtime bugs — then fixes them autonomously on a safe branch.
Official NVIDIA-verified skills for AI agents to use CUDA-X libraries and platform tools correctly.
AI agent developers who want to extend their agents' capabilities with NVIDIA tools, Data scientists and ML engineers using NVIDIA libraries who need agent assistance, DevOps engineers automating deployment of AI services with agent skills
The setup section provides repository-level starting guidance, not a guarantee of an independently verified installation. Check the official README and release notes.
Agent skills can change coding-agent behavior; review every SKILL.md and referenced script before installing. Check shell, network, file-system, credential, and API-key requirements before running skill workflows.
Similar or complementary options to evaluate include anthropic-skills, bug-hunter, Dify.
Jun 7, 2026
4 security/trust notes recorded.
Setup difficulty is 2/5.
Open-source LLM app development platform. Build AI workflows, RAG pipelines, and agents with a visual interface.