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.
5813 skills
NVIDIAOfficial
An iterative workflow for binary industrial defect detection using TAO RT-DETR and automated data mining.
NVIDIAOfficial
A guide for launching distributed Megatron-LM training jobs on SLURM clusters.
NVIDIAOfficial
Configure Jetson Orin or Thor pinmux settings from a custom carrier XLSM file.
NVIDIAOfficial
Manage and evaluate SPC-X congestion-control algorithms on BlueField DPA processors using the doca_spcx_cc CLI.
NVIDIAOfficial
Train, evaluate, and export TAO person re-identification models using metric learning for cross-camera matching.
NVIDIAOfficial
Use when the user asks to deploy, install, reinstall, redeploy, upgrade, or connect to the CDF Orchestration Airflow controller. Owns the end-to-end deploy sequence and runs the cdf-orchestration-preflight audit first. Covers make setup, controller image builds, Helm installation, controller connection, port-forwarding, and post-install verification. Not for standalone prerequisite audits or remediation, K3s environments, authoring DAGs, or running workflow payloads.
NVIDIAOfficial
A wrapper for running NVIDIA VISTA3D segmentation on CT NIfTI volumes.
NVIDIAOfficial
Standardized workflow for deploying and debugging DOCA service containers on BlueField using kubelet standalone.
NVIDIAOfficial
A wrapper for running NV-Reason-CXR chest X-ray reasoning models via local inference or Hugging Face Space API.
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
Initializes the Jetson BSP image by extracting tarballs and applying binaries for a specific target platform.
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
A TAO toolkit integration for InternVideo2-CLIP L14 video-text retrieval, fine-tuning, and TensorRT deployment.
NVIDIAOfficial
End-to-end workflow for implementing and validating new Earth2Studio data source wrappers for remote data stores.
NVIDIAOfficial
Optimizes LLM/VLM inference runtime settings and memory flags for NVIDIA Jetson devices based on system audit snapshots.
NVIDIAOfficial
A systematic workflow for diagnosing and resolving failures in Holoscan CLI commands.
NVIDIAOfficial
Operate the NVIDIA DOCA Management Service (DMS) for BlueField and ConnectX platforms using gNMI and gNOI protocols.
NVIDIAOfficial
Automated setup and preflight verification for the Isaac for Healthcare workflow runtime environment.
NVIDIAOfficial
Inspects a Jetson Linux_for_Tegra BSP directory to report version, board configurations, and rootfs status.
NVIDIAOfficial
A routing skill for managing Cosmos Data Factory (CDF) auto-labeling pipelines, cookbooks, and stage configurations.
NVIDIAOfficial
A four-step pipeline that uses Vision-Language Models to generate grounded referring expressions and scene annotations from images with KITTI labels.
NVIDIAOfficial
Rebuilds Jetson BSP kernel-side artifacts and registers custom overlays based on source changes.