RadarTopicsBuildersWeeklyReads
Open Source Radar
NVIDIA/

skills

GitHubWebsite

NVIDIA Agent Skills provides a catalog of Python-based agent skills for Claude Code, Codex, and other coding agents, installed via a CLI flow. It coordinates installation from the NVIDIA Skills catalog and includes per-agent installation options.

2.8kstars
324forks
16issues
Apache-2.0license
2026since
Star historydaily snapshots by VibeCrowd

Collecting history — the radar snapshots this repo daily. The trend line appears after 3 days of data (1 so far).

Alternatives & relatedmatched by topic overlap
Reviewgenerated from repository data · Aug 5, 2026

What it is

Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents. The repository acts as a catalog of skills, maintained in product repos and mirrored daily via an automated sync pipeline. Skills are continuously updated; contributions are welcome.

How it works

Skills are installed using the default skills CLI flow. The Quickstart shows installing via npx skills add nvidia/skills, which prompts for a skill and destination. There are options to install a single skill without prompts and to target a specific agent with --agent. Example commands are quoted exactly from the README:

npx skills add nvidia/skills
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --yes
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent claude-code
npx skills add nvidia/skills \
  --skill cuopt-numerical-optimization-api \
  --agent claude-code \
  --agent codex \
  --agent cursor \
  --agent kiro-cli
npx skills update
npx skills list
npx skills check
npx skills add nvidia/skills --list

Install for a Specific Agent

Use --agent to target a specific AI coding agent. The README lists several agents with corresponding examples, such as Claude Code and Codex. The exact commands are quoted above.

Skill Catalog (highlights)

The catalog section lists products and their associated skills, e.g., CUDA-Q, cuOpt, cuDF, DeepStream, Holoscan, and many more, with multiple skill identifiers per product. The catalog is presented in a table format in the README.

Keeping skills up to date

The README indicates: "New skills land continuously, and existing ones are revised, renamed, or consolidated as the catalog evolves. Refresh what you have installed with:" followed by the update command shown above.

Agent skills inside · 311
All skills →
omniverse-cad-to-simreadyCoordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that require conversion, material/physics assignment, SimReady conformance, validation, and optional package creation; deploy or verify Content Agents services first when property assignment is enabled; route single-stage work through nested references.DevOps & Cloudscriptsomniverse-usd-performance-tuningTop-level workflow skill for USD performance diagnosis and optimization. Handles slow loading, high memory, low FPS, and broad scene-optimization requests; delegates auth/runtime setup to Phase 0 owners.Securityscriptsphysical-ai-video-data-augmentationUse when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output retrieval. Trigger keywords: video data augmentation, data enrichment, auto labeling, VDA demo, OSMO workflow, pseudo labeling.Data & Analyticsscriptstao-finetune-huggingface-modelFine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / LLM model end-to-end, generate a reproducible HF training pipeline, smoke-test a HuggingFace model locally before scale-up, push a fine-tuned model to the HF Hub with a model card, or emit a self-contained rerun skill for an existing HuggingFace finetune. Supports image classification, object detection, semantic / instance / panoptic segmentation, depth estimation, image-text-to-text VLM (SFT / LoRTesting & QAscriptsphysical-ai-infrastructure-setup-and-resilient-scalingUse when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s or Azure AKS, including Kubernetes clusters, inference endpoint deployment, OSMO deployment, workload submission readiness, and infrastructure failure recovery. Trigger keywords: physical ai infrastructure, resilient scaling, SDG infrastructure, microk8s, azure aks, NVCF deployment, NIM Operator, OSMO deploy, workflow scaling. Don't trigger for: OSMO log summarization or workload-only operations unless infrastructure setup, scaling, vaDevOps & Cloudscriptsdeepstream-sopUse this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger fBackend & APIscripts
SharePost on XLinkedIn
All trending reposRevenue-verified startups →