Skill collection
NVIDIA/skills agent skills
- skills
- 380
- official
- 380
- GitHub stars
- 3.5k
GitHub description: “Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.”
- Stars
- 3,539 (434 forks)
- Licence
- Apache-2.0
- Last push
- Oct 2026
- Created
- Feb 2026
- Homepage
- docs.nvidia.com/skills
- Source
- github.com/NVIDIA/skills
- agent-skills
- agentic-ai
- ai-agents
- claude-code
- codex
- coding-agents
- cuda
- developer-tools
- llm
- omniverse
- physical-ai
- rag
- robotics
- simulation
Install all skills
npx skills add NVIDIA/skillsAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in NVIDIA/skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | A skill your agent uses when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. | NVIDIA/ | 3.5k | 1 repo | ~4.5k | Automated safety check: Pass | Apache-2.0 | today |
| 2 | Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything. | NVIDIA/ | 3.5k | — | ~2.9k | Automated safety check: Pass | Apache-2.0 | today |
| 3 | Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server. | NVIDIA/ | 3.5k | — | ~4.8k | Automated safety check: Pass | Apache-2.0 | today |
| 4 | Orchestrates defect image generation for PCBA, metal surface and glass inspection with NVIDIA Cosmos AnomalyGen on OSMO, from cold-start Day 0 to real-photo Day 1 labeling. | NVIDIA/ | 3.5k | — | ~5k | Automated safety check: Notes | Apache-2.0 | today |
| 5 | Orchestrates video data augmentation and auto-labeling workflows on OSMO, from flow selection and preflight checks to submission, monitoring and output download. | NVIDIA/ | 3.5k | — | ~4.7k | Automated safety check: Notes | Apache-2.0 | today |
| 6 | Runs NVIDIA TAO Data Services KPI analysis on object detection results, comparing predictions to ground truth and writing per-class precision, recall and AP to a CSV. | NVIDIA/ | 3.5k | — | ~2.7k | Automated safety check: Notes | Apache-2.0 | today |
| 7 | Runs TAO Data Services gap analysis that compares ground-truth and predicted boxes to find weak images by per-class recall, precision and AP50. | NVIDIA/ | 3.5k | — | ~1.8k | Automated safety check: Notes | Apache-2.0 | today |
| 8 | Compares a vision-language model's yes/no predictions with ground truth and writes the false-positive and false-negative cases to a JSONL file with a summary report. | NVIDIA/ | 3.5k | — | ~1.3k | Automated safety check: Notes | Apache-2.0 | today |
| 9 | Turns a parquet of image file paths into a parquet of embeddings with CLIP, SigLIP or a TAO checkpoint, using the TAO Data Services container, ahead of neighbor mining. | NVIDIA/ | 3.5k | — | ~2k | Automated safety check: Notes | Apache-2.0 | today |
| 10 | Run TAO Data Services TMM nearest-neighbor mining from embedding parquet files. | NVIDIA/ | 3.5k | — | ~1.6k | Automated safety check: Notes | Apache-2.0 | today |
| 11 | Run TAO Data Services TMM unique-neighbor matching mining from embedding parquet files for object detection workflows. | NVIDIA/ | 3.5k | — | ~2.2k | Automated safety check: Notes | Apache-2.0 | today |
| 12 | Start or patch Dynamo router modes and run router endpoint smoke checks. | NVIDIA/ | 3.5k | 1 repo | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Diagnose failed or unhealthy Dynamo deployments. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.5k | 1 repo | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 14 | Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. | NVIDIA/ | 3.5k | 1 repo | ~2.4k | Automated safety check: Notes | Apache-2.0 | today |
| 15 | Generate multiple sequence alignments (MSAs) for protein sequences using the ColabFold MSA-Search NIM. | NVIDIA/ | 3.5k | 1 repo | ~4.6k | Automated safety check: Notes | Apache-2.0 | today |
| 16 | A skill your agent uses for agent-assisted Auto-FL optimization of an existing NVFLARE job in simulation, POC, or production. | NVIDIA/ | 3.5k | 1 repo | ~3.9k | Automated safety check: Pass | Apache-2.0 | today |
| 17 | Run ProteinMPNN inverse folding via NVIDIA NIM to design protein sequences for a target backbone. | NVIDIA/ | 3.5k | 1 repo | ~2k | Automated safety check: Notes | Apache-2.0 | today |
| 18 | A skill your agent uses for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. | NVIDIA/ | 3.5k | 1 repo | ~4.5k | Automated safety check: Notes | Apache-2.0 | today |
| 19 | Run the mining-based DEFT improvement workflow for ITS Cosmos-Reason binary video questions, focused on the non-reasoning classification/evaluation path. | NVIDIA/ | 3.5k | — | ~4.9k | Automated safety check: Notes | Apache-2.0 | today |
| 20 | Run DiffDock molecular docking via NVIDIA NIM to predict small-molecule binding poses against protein targets. | NVIDIA/ | 3.5k | 1 repo | ~1.1k | Automated safety check: Notes | Apache-2.0 | today |
| 21 | Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. | NVIDIA/ | 3.5k | 1 repo | ~1.6k | Automated safety check: Pass | Apache-2.0 | today |
| 22 | Generate novel drug-like molecules using the GenMol NIM microservice. | NVIDIA/ | 3.5k | 1 repo | ~1.4k | Automated safety check: Notes | Apache-2.0 | today |
| 23 | Flash the FPGA on an HSB board connected to an NVIDIA devkit. | NVIDIA/ | 3.5k | 1 repo | ~4.4k | Automated safety check: Notes | Apache-2.0 | today |
| 24 | Orient users to the i4h workflow runtime and route them to the correct stage skill. | NVIDIA/ | 3.5k | 1 repo | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 25 | Edit an existing workflow Scene or task contract. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.5k | 1 repo | ~4.8k | Automated safety check: Pass | Apache-2.0 | today |
| 26 | Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes. | NVIDIA/ | 3.5k | 1 repo | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 27 | Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data. | NVIDIA/ | 3.5k | 1 repo | ~2.3k | Automated safety check: Notes | Apache-2.0 | today |
| 28 | Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choices. | NVIDIA/ | 3.5k | 1 repo | ~1.8k | Automated safety check: Pass | Apache-2.0 | today |
| 29 | Continue KERMT pretraining on a custom SMILES corpus with a groverbase, cmim, or hybrid checkpoint. | NVIDIA/ | 3.5k | 1 repo | ~4.1k | Automated safety check: Pass | Apache-2.0 | today |
| 30 | Extract per-molecule embeddings from any encoder-bearing KERMT checkpoint. | NVIDIA/ | 3.5k | 1 repo | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 31 | Finetune a pretrained KERMT encoder on a labeled CSV. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.5k | 1 repo | ~4.1k | Automated safety check: Pass | Apache-2.0 | today |
| 32 | A skill your agent uses for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization. | NVIDIA/ | 3.5k | 1 repo | ~1.9k | Automated safety check: Notes | Apache-2.0 | today |
| 33 | Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL… | NVIDIA/ | 3.5k | 1 repo | ~4.1k | Automated safety check: Pass | Apache-2.0 | today |
| 34 | A skill your agent uses when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron embed/rerank retrieval recipes. | NVIDIA/ | 3.5k | 1 repo | ~2.6k | Automated safety check: Pass | Apache-2.0 | today |
| 35 | A skill your agent uses when writing or debugging nvMolKit Python code for GPU-accelerated RDKit fingerprints, similarity, conformers, clustering, and molecular searches. | NVIDIA/ | 3.5k | 1 repo | ~4.8k | Automated safety check: Pass | Apache-2.0 | today |
| 36 | A skill your agent uses for OpenFold2, NVIDIA's BioNeMo NIM microservice for monomer protein structure prediction. | NVIDIA/ | 3.5k | 1 repo | ~1.8k | Automated safety check: Notes | Apache-2.0 | today |
| 37 | A skill your agent uses for OpenFold3, NVIDIA's BioNeMo NIM microservice for biomolecular structure prediction. | NVIDIA/ | 3.5k | 1 repo | ~1.9k | Automated safety check: Notes | Apache-2.0 | today |
| 38 | Run RFDiffusion protein backbone design via NVIDIA NIM. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.5k | 1 repo | ~1.3k | Automated safety check: Notes | Apache-2.0 | today |
| 39 | Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed results. | NVIDIA/ | 3.5k | 1 repo | ~4.8k | Automated safety check: Notes | Apache-2.0 | today |
| 40 | Co-DETR (CoDINO) for object detection. An agent skill from NVIDIA/skills. | NVIDIA/ | 3.5k | 1 repo | ~4.8k | Automated safety check: Notes | Apache-2.0 | today |
| 41 | Person re-identification (ReID). An agent skill from NVIDIA/skills. | NVIDIA/ | 3.5k | 1 repo | ~3.6k | Automated safety check: Notes | Apache-2.0 | today |
| 42 | A skill your agent uses when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). | NVIDIA/ | 3.5k | 1 repo | ~3.3k | Automated safety check: Notes | Apache-2.0 | today |
| 43 | Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin. | NVIDIA/ | 3.5k | 2 repos | ~3k | Automated safety check: Notes | Apache-2.0 | today |
| 44 | Run the full DEFT smart-data-augmentation loop for NVIDIA TAO Grounding DINO object detection: zero-shot baseline inference, KPI analysis, per-class gap analysis, SigLIP embedding of weak images… | NVIDIA/ | 3.5k | — | ~3.3k | Automated safety check: Notes | Apache-2.0 | today |
| 45 | Port a published computer vision paper's official code and training recipe onto a customer's own dataset, or diagnose why such a transfer produced bad numbers. | NVIDIA/ | 3.5k | — | ~4.2k | Automated safety check: Notes | Apache-2.0 | today |
| 46 | Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. | NVIDIA/ | 3.5k | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | today |
| 47 | A skill your agent uses when the user is tuning a live or captured doca-flow pipeline with docaflowtune — snapshotting pipe / counter / KPI state, picking a tuning axis (rule placement, resource… | NVIDIA/ | 3.5k | 1 repo | ~4.8k | Automated safety check: Pass | Apache-2.0 | today |
| 48 | NOTE: molecule and target inputs and your NGCAPIKEY are transmitted to external NVIDIA-hosted API endpoints on every call. | NVIDIA/ | 3.5k | 1 repo | ~1.8k | Automated safety check: Notes | Apache-2.0 | today |
Questions, answered from the data.
What is the best skill in NVIDIA/skills?
Vss Deploy Detection Tracking 2D (official) from NVIDIA/skills ranks first of the 380 skills in NVIDIA/skills listed here, with the highest score: its repository has 3.5k GitHub stars, 1 other GitHub owner carry a copy, its SKILL.md loads about 4.5k tokens and it passes the automated safety check with no findings. Next come HSB IP Def File Tool and Isaac Sim Mission Control Showcase.
Are the skills in NVIDIA/skills official?
380 of the 380 skills in NVIDIA/skills are official, published by the vendor's own GitHub organization: Vss Deploy Detection Tracking 2D, HSB IP Def File Tool, Isaac Sim Mission Control Showcase, Defect Image Generation with Cosmos AnomalyGen, Physical AI Video Augmentation on OSMO and 375 more.
How do I install all skills from NVIDIA/skills?
Run npx skills add NVIDIA/skills in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.