GitHub organization
Agent skills by NVIDIA
- skills
- 526
- official
- 526
- repositories
- 20
Repositories by NVIDIA
- NemoClawOfficialRun agents like Hermes, LangChain Deep Agents, and OpenClaw more securely inside NVIDIA OpenShell with managed inference23k stars · 30 skills
- Megatron-LMOfficialOngoing research training transformer models at scale18k stars · 14 skills
- OpenShellOfficialOpenShell is the safe, private runtime for autonomous AI agents.15k stars · 23 skills
- aicrOfficialTooling for optimized, validated, and reproducible GPU-accelerated AI runtime in Kubernetes432 stars · 10 skills
- skillsOfficialAgent 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.3.5k stars · 380 skills
- CompileIQOfficialAn Optimizer for Nvidia Compilers.137 stars · 7 skills
- NeMo-RelayOfficialMulti-language agent runtime and library for execution scope management, lifecycle events, and middleware on tool and LLM calls.190 stars · 30 skills
- SkillEvaluatorOfficialMulti-tier framework for evaluating AI agent skills with quality gates, semantic overlap detection, synthetic evaluation dataset generation, and live agent evaluation that measures how skills affect agent behavior.544 stars · 5 skills
- cosmos-frameworkOfficialOur inference and training framework to run on the Cosmos Models556 stars · 5 skills
- Personal-AI-RouterOfficialRouter that virtually distributes inference across connected devices in the home.1.6k stars · 4 skills
- dcgm-exporterOfficialNVIDIA GPU metrics exporter for Prometheus leveraging DCGM1.9k stars · 3 skills
- physicsnemo-cfdOfficialLibrary for using the models trained in PhysicsNeMo in Engineering and CFD workflows 153 stars · 3 skills
- structured-data-modelsOfficialFoundation Models for Structured Data310 stars · 3 skills
- k8s-nim-operatorOfficialAn Operator for deployment and maintenance of NVIDIA NIMs and NeMo microservices in a Kubernetes environment.159 stars · 2 skills
- nemoclaw-communityOfficialOur repository of community driven examples, showcases, and integrations123 stars · 2 skills
- MagnumIOOfficialMagnum IO community repo125 stars · 1 skill
- SkillSpectorOfficialSecurity scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills before you install them.20k stars · 1 skill
- container-canaryOfficialA tool for testing and validating container requirements against versioned manifests309 stars · 1 skill
- cuda-pythonOfficialCUDA Python: Performance meets Productivity3.4k stars · 1 skill
- nvidia-kaggleOfficialNVIDIA Kaggle Plugin gives agents end-to-end Kaggle competition workflows through a single skill, nvidia-kaggle-skill. It can gather competition context, study public writeups and notebooks, reproduce kernels locally, submit to competitions, and manage Ka336 stars · 1 skill
Skills by NVIDIA, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | Decides whether an agent skill is safe to install by combining a SkillSpector static scan with the agent's own source review, ending in APPROVE, CAUTION or REJECT. | NVIDIA/ | 20k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | today |
| 2 | Find open issues that a NemoClaw PR may also fix or conflict with. | NVIDIA/ | 23k | — | ~893 | Automated safety check: Pass | Apache-2.0 | today |
| 3 | Refreshes stored golden values from a GitHub Actions run, reports signed percentage changes per model, and writes a summary ready for a pull request description. | NVIDIA/ | 18k | — | ~2.8k | Automated safety check: Pass | Unknown | today |
| 4 | Run a NemoClaw daytime maintainer pass over release-targeted work. | NVIDIA/ | 23k | — | ~1k | Automated safety check: Pass | Apache-2.0 | today |
| 5 | Create a CUDA Python pull request from an approved personal or organization-owned fork, including the GitHub CLI GraphQL fallback for renamed organization-owned forks. | NVIDIA/ | 3.4k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 6 | Maintain and validate OpenShell's build-only Windows MSVC lane for x64 and ARM64. | NVIDIA/ | 15k | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | today |
| 7 | Remove bracketed NemoClaw tags from GitHub issue and PR titles. | NVIDIA/ | 23k | — | ~693 | Automated safety check: Pass | Apache-2.0 | today |
| 8 | Create GitHub issues using the gh CLI. An agent skill from NVIDIA/OpenShell. | NVIDIA/ | 15k | — | ~1.7k | Automated safety check: Pass | Apache-2.0 | today |
| 9 | Call any REST API dynamically. An agent skill from NVIDIA/SkillEvaluator. | NVIDIA/ | 544 | 1 repo | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 10 | Walks an agent through working inside the Megatron-LM CI container and changing dependencies with uv, so lock files resolve the same locally and in CI. | NVIDIA/ | 18k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | today |
| 11 | Audit and implement a NemoClaw dependency version upgrade, including Hermes and base images. | NVIDIA/ | 23k | — | ~1.4k | Automated safety check: Pass | Apache-2.0 | today |
| 12 | Create GitHub pull requests using the gh CLI. An agent skill from NVIDIA/OpenShell. | NVIDIA/ | 15k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 13 | Fills GitHub pull request descriptions with the required PAIR pair-release-intent:v1 block so the release-intent check passes. | NVIDIA/ | 1.6k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 14 | Moves Megatron-LM CI to a newer NVIDIA PyTorch base image, updating both the GitHub and GitLab pins together and handling the CI follow-up. | NVIDIA/ | 18k | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | today |
| 15 | A skill your agent uses for Kaggle competition overview fetches, writeups, discussion/kernel research, submissions, and dataset uploads. | NVIDIA/ | 336 | — | ~2.3k | Automated safety check: Notes | MIT | 2 mo ago |
| 16 | Continuously maintain automatic NemoClaw main E2E results through coordinated repairs. | NVIDIA/ | 23k | — | ~2.6k | Automated safety check: Pass | Apache-2.0 | today |
| 17 | Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. | NVIDIA/ | 15k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | today |
| 18 | Explains Megatron-LM's CI pipeline, PR scope labels, triggering the internal GitLab CI with a dry run first, and investigating CI failures. | NVIDIA/ | 18k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | today |
| 19 | A skill your agent uses when diagnosing NVIDIA GPUDirect Storage with this repository: choose and run the right gds-diag.py subcommand, interpret its output, and explain operator next steps without… | NVIDIA/ | 125 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 8 days ago |
| 20 | 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 |
| 21 | Install NVIDIA NIM Operator on Kubernetes with prerequisite checks, optional NVIDIA GPU Operator dependency installation, public or local Helm chart selection, optional Dynamo support, and optional… | NVIDIA/ | 159 | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 22 | Kaizen UI (KUI) component library and design-pattern advisor for NVIDIA applications. | NVIDIA/ | 1.6k | — | ~4.7k | Automated safety check: Pass | Apache-2.0 | today |
| 23 | Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. | NVIDIA/ | 15k | — | ~19k | Automated safety check: Notes | Apache-2.0 | today |
| 24 | Navigate the Cosmos3 package codebase to find where parameters, configs, defaults, scripts, and documentation live. | NVIDIA/ | 556 | — | ~2.8k | Automated safety check: Pass | Unknown | 11 days ago |
| 25 | Investigates a failing GitHub Actions run or job for Megatron-LM, finds the root cause plus the PR and test author involved, and files a structured bug issue. | NVIDIA/ | 18k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | today |
| 26 | Analyze retained NemoClaw CI timings for slow CLI tests, runner queues, or base-image publication. | NVIDIA/ | 23k | — | ~644 | Automated safety check: Pass | Apache-2.0 | today |
| 27 | Required for 4+ step requests; add tasks at start and update status after each step. | NVIDIA/ | 544 | — | ~460 | Automated safety check: Pass | Apache-2.0 | today |
| 28 | Safely uninstall NVIDIA NIM Operator from Kubernetes with inventory checks, explicit approval gates for destructive actions, optional custom resource cleanup, optional CRD removal, and… | NVIDIA/ | 159 | — | ~3.6k | Automated safety check: Pass | Apache-2.0 | yesterday |
| 29 | A skill your agent uses when validating DCGM Exporter in a local GPU-backed k3d/Kubernetes environment. | NVIDIA/ | 1.9k | — | ~116 | Automated safety check: Pass | Apache-2.0 | 18 days ago |
| 30 | Write or review docstrings for public modules, classes, and functions in sdm/. | NVIDIA/ | 310 | — | ~1.2k | Automated safety check: Pass | Apache-2.0 | today |
| 31 | Create a new model wrapper for the PhysicsNeMo CFD benchmarking workflow. | NVIDIA/ | 153 | — | ~5.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 32 | Validate and monitor OpenShell GitHub issues and PRs using the gator: state machine. | NVIDIA/ | 15k | — | ~19k | Automated safety check: Pass | Apache-2.0 | today |
| 33 | Multi-agent PR review using Claude Code, Codex, and CodeRabbit. | NVIDIA/ | 432 | — | ~15k | Automated safety check: Pass | Apache-2.0 | today |
| 34 | Diagnose and fix Cosmos3 environment, installation, and runtime errors. | NVIDIA/ | 556 | — | ~1.3k | Automated safety check: Notes | Unknown | 11 days ago |
| 35 | Guide NemoClaw Community contributors through classifying, naming, adding, moving, renaming, and reviewing repository examples. | NVIDIA/ | 123 | — | ~754 | Automated safety check: Pass | Apache-2.0 | yesterday |
| 36 | Guides moving Megatron Core GPTModel checkpoints, configs, training commands and launch scripts to HybridModel, following the repository's migration document. | NVIDIA/ | 18k | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | today |
| 37 | Analyze one NemoClaw PR lifetime to identify contributor, review, and automation delays or compare it with a latency target. | NVIDIA/ | 23k | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | today |
| 38 | Write, refactor, or review tests in Personal AI Router using focused cases, descriptive subtests, explicit error handling, and structured assertions. | NVIDIA/ | 1.6k | — | ~1k | Automated safety check: Pass | Apache-2.0 | today |
| 39 | Draft and revise concise, human-focused GitHub issues for pytest-kind-ng. | NVIDIA/ | 309 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 40 | A skill your agent uses when changing metric CSV files, exporter-owned counters, Prometheus labels, or metric rendering. | NVIDIA/ | 1.9k | — | ~149 | Automated safety check: Pass | Apache-2.0 | 18 days ago |
| 41 | Use BEFORE running a full CompileIQ search. An agent skill from NVIDIA/CompileIQ. | NVIDIA/ | 137 | — | ~2.1k | Automated safety check: Notes | Apache-2.0 | 13 days ago |
| 42 | Start up, tear down, and configure the local Kubernetes development environment for OpenShell. | NVIDIA/ | 15k | — | ~4.9k | Automated safety check: Pass | Apache-2.0 | today |
| 43 | A skill your agent uses when analyzing an AICR snapshot YAML file, reviewing cluster state, comparing provider characteristics, extracting GPU/network topology insights, or generating a cluster… | NVIDIA/ | 432 | — | ~3.5k | Automated safety check: Pass | Apache-2.0 | today |
| 44 | A skill your agent uses when converting an existing benchmark, rubric, verifier, task YAML/JSON, or domain check into SkillEvaluator BYOG/BYOT custom evaluation. | NVIDIA/ | 544 | — | ~2.1k | Automated safety check: Pass | Apache-2.0 | today |
| 45 | Creates one-node GitHub merge-request variants of existing two-node GB200 functional tests in Megatron-LM, adjusting parallelism settings to fit four GPUs. | NVIDIA/ | 18k | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | today |
| 46 | Compare competing NemoClaw PRs for one issue and recommend a merge or salvage candidate from review evidence. | NVIDIA/ | 23k | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | today |
| 47 | Compare NeMo Relay release refs and draft the current documentation release-notes page from verified repository evidence. | NVIDIA/ | 190 | — | ~575 | Automated safety check: Pass | Apache-2.0 | today |
| 48 | A skill your agent uses when starting a fresh CompileIQ project, hitting a socket timeout, or before running any other compileiq- skill. | NVIDIA/ | 137 | — | ~1.3k | Automated safety check: Notes | Apache-2.0 | 13 days ago |
Questions, answered from the data.
What is the best skill by NVIDIA?
Skill Inspector (official) from NVIDIA/SkillSpector ranks first of the 526 skills by NVIDIA listed here, with the highest score: its repository has 20k GitHub stars, its SKILL.md loads about 1.8k tokens and it passes the automated safety check with no findings. Next come Nemoclaw Maintainer Cross Issue Sweep and Update Megatron Golden Values.
Are NVIDIA's skills official?
526 of the 526 skills by NVIDIA are official, published by the vendor's own GitHub organization: Skill Inspector, Nemoclaw Maintainer Cross Issue Sweep, Update Megatron Golden Values, Nemoclaw Maintainer Day, Create Cuda Python Pull Request and 521 more.
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.