Skills from NVIDIA’s repositories that passed our trust, licence and security gates. Each keeps its author’s attribution.
| Repository | Tier | Verdict | Authorship | Checked | Skills |
|---|---|---|---|---|---|
| NVIDIA/skills | Vendor | Approved · created 2026-02-25, pushed 2026-11-06, 3888 stars | Written in-house | 2026-11-07 | 431 |
Files are mirrored only where the licence allows redistribution; otherwise we link to the source.
NVIDIAOfficial
Operating guidelines for managing storage and environment secrets on Brev instances for NeMo-RL agents.
NVIDIAOfficial
Authoritative JSON schemas and structural contracts for TAO execution pipeline artifacts.
NVIDIAOfficial
Install Holoscan SDK 5.x native C++ Debian packages on Ubuntu 24.04.
NVIDIAOfficial
Automated optimization campaign runner for NVFLARE federated learning jobs.
NVIDIAOfficial
GPU-accelerated, batched implementations of common RDKit cheminformatics operations.
NVIDIAOfficial
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.
NVIDIAOfficial
Measure Jetson memory usage and verify reclamation with live audit data and cache management.
NVIDIAOfficial
Automates the creation of prognostic model wrappers for the Earth2Studio framework.
NVIDIAOfficial
Procedures for deploying and supervising DOCA-linked binaries directly on bare-metal hardware.
NVIDIAOfficial
Orchestrate Cosmos Data Factory (CDF) pipelines for video and image augmentation, generation, and evaluation.
NVIDIAOfficial
A shared library of internal NVFLARE conversion policies, templates, and guidance for agent-based federated learning workflows.
NVIDIAOfficial
NOTE: your protein sequence and the retrieved MSA alignment are transmitted to external NVIDIA-hosted APIs (health.api.nvidia.com) on every call. Use local NIM containers for confidential or proprietary sequences. Run a complete protein structure prediction pipeline using NVIDIA BioNeMo NIMs: search for MSA alignments with MSA-Search (ColabFold), then predict the structure with OpenFold3 using the retrieved alignments. Use this skill whenever the user wants to predict a protein structure with maximum accuracy using MSA context, run the full AlphaFold3-style pipeline, generate MSA-informed structure predictions, or improve structure prediction accuracy by providing evolutionary information. Triggers on: MSA structure prediction pipeline, structure prediction pipeline, MSA-informed prediction, OpenFold3, ColabFold MSA, AlphaFold3 pipeline, protein structure, homology search, a3m alignment, UniRef30, NIM microservice. This pipeline chains MSA-Search and OpenFold3.
NVIDIAOfficial
Bootstrap a custom Jetson carrier board by forking reference files and scaffolding a device tree overlay.
NVIDIAOfficial
Configure and validate expert-parallel communication overlap for MoE models in Megatron-Bridge.
NVIDIAOfficial
Bootstrap the KERMT agent environment by verifying host requirements, building the container image, and running a GPU smoke test.
NVIDIAOfficial
Automated installation and configuration of the NVIDIA PVA SDK, NVVPU compiler, and L4T target runtime.
NVIDIAOfficial
Discover Earth2Studio models, data sources, and workflow examples for weather and climate research.
NVIDIAOfficial
Manage and execute public Nemotron embedding and reranking retrieval recipes.
NVIDIAOfficial
Detect and diagnose CUDA correctness bugs with NVIDIA Compute Sanitizer. Routes GPU memory errors, shared-memory data races, uninitialized-memory reads, and synchronization/barrier bugs to the right sub-tool (memcheck, racecheck, initcheck, synccheck) and explains how to build, run, and read the report. Use when debugging illegal memory access, out-of-bounds, misaligned access, leaks, WAW/WAR/RAW races, __shared__ hazards, uninitialized reads, garbage results, hangs, divergent __syncthreads/__syncwarp, or cuda::barrier / wgmma issues. Do NOT use for host/CPU-side bugs (use valgrind or AddressSanitizer) or global-memory data races (out of scope). Trigger keywords - compute-sanitizer, memcheck, racecheck, initcheck, synccheck, CUDA memory error, OOB, race condition, uninitialized memory, __syncthreads, barrier, deadlock.
NVIDIAOfficial
Switch the active Jetson target platform configuration by updating the active_target.yml pointer.
NVIDIAOfficial
Orchestrates the end-to-end finetuning of KERMT encoder models on labeled chemical datasets.
NVIDIAOfficial
NVIDIA TAO skill for self-supervised visual representation learning using NVDINOv2.
NVIDIAOfficial
A guide for building and debugging equivariant neural networks using cuEquivariance and PyTorch.
NVIDIAOfficial
Generate reproducible reports and summaries for completed NVFLARE Auto-FL campaigns.