Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
1928 skills
NVIDIAOfficial
A guide to configuring and swapping Vision Language Models (VLM) within the VSS Alerts Blueprint.
NVIDIAOfficial
A guide to diagnosing and resolving GPU out-of-memory errors in Megatron Bridge training jobs.
NVIDIAOfficial
A guide for packaging and registering reusable NeMo Relay runtime behaviors as embedded components or dynamic plugins.
NVIDIAOfficial
A troubleshooting guide for resolving runtime integration issues with NeMo Relay.
NVIDIAOfficial
Benchmark LLM serving performance on NVIDIA Jetson devices across vLLM, llama.cpp, and Ollama with structured JSON output.
NVIDIAOfficial
Provides guidance for using cuEquivariance JAX for equivariant polynomial operations and Flax NNX layers.
NVIDIAOfficial
A disciplined framework for safely upgrading, downgrading, or recovering NVIDIA DOCA software environments.
NVIDIAOfficial
Validates NVIDIA TAO DAFT dataset structures, schemas, and cross-references using the tao-daft CLI.
NVIDIAOfficial
Reconciles Jetson video codec capabilities across APIs, official samples, and documentation.
NVIDIAOfficial
Provides foundational primitives and lifecycle management for NVIDIA DOCA applications on BlueField DPUs and ConnectX NICs.
NVIDIAOfficial
Automate the integration of MIPI and GMSL camera sensors on Jetson Thor and Orin platforms via kernel-DT overlays.
NVIDIAOfficial
A guide for configuring distributed training strategies and parallelism in NeMo AutoModel.
NVIDIAOfficial
Provides guidance for offloading SHA-1, SHA-256, and SHA-512 hashing to BlueField-2 DPU hardware using the NVIDIA DOCA SHA library.
NVIDIAOfficial
An iterative workflow for binary industrial defect detection using TAO RT-DETR and automated data mining.
NVIDIAOfficial
Manage and evaluate SPC-X congestion-control algorithms on BlueField DPA processors using the doca_spcx_cc CLI.
NVIDIAOfficial
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.
NVIDIAOfficial
Convert standard PyTorch training scripts into NVFLARE federated learning jobs using the Client API.
NVIDIAOfficial
Generates a minimal, blank workflow scaffold for Isaac for Healthcare projects.
NVIDIAOfficial
Integrate the DOCA SHA Offload Engine into OpenSSL pipelines to accelerate SHA-1, SHA-256, and SHA-512 on BlueField-2 DPU hardware.
NVIDIAOfficial
End-to-end workflow for implementing and validating new Earth2Studio data source wrappers for remote data stores.
NVIDIAOfficial
A systematic workflow for diagnosing and resolving failures in Holoscan CLI commands.
NVIDIAOfficial
Rebuilds Jetson BSP kernel-side artifacts and registers custom overlays based on source changes.
NVIDIAOfficial
Guide for host-side integration of custom Programmable Congestion Control (PCC) algorithms on NVIDIA BlueField DPUs using the DOCA PCC library.
NVIDIAOfficial
Hands-on guidance for integrating and debugging the NVIDIA DOCA Arg Parser CLI library in C/C++ applications.