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
Provides guidance for running the doca_perftest RDMA benchmark tool to measure network performance metrics.
NVIDIAOfficial
Orchestrates containerized continued pretraining for KERMT models on custom SMILES corpora.
NVIDIAOfficial
Guidance for integrating NVIDIA DOCA Rivermax to handle timing-precise media-over-IP streams on BlueField DPUs.
NVIDIAOfficial
Train, evaluate, and export Depth Anything v2 monocular depth estimation models using the NVIDIA TAO toolkit.
NVIDIAOfficial
Assists with developing, debugging, and upgrading Python code using NVIDIA cuML for GPU-accelerated machine learning.
NVIDIAOfficial
Evaluate if a code bottleneck is a suitable candidate for NVIDIA Warp acceleration.
NVIDIAOfficial
Captures an AI agent's intended behavior into a durable ethos.md contract through codebase analysis and a mandatory intent interview.
NVIDIAOfficial
A conceptual guide for translating business problems into linear, mixed-integer, and quadratic optimization formulations.
NVIDIAOfficial
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
NVIDIAOfficial
Inspect, install, and verify NVIDIA Video Codec SDK and PyNvVideoCodec readiness on Jetson devices.
NVIDIAOfficial
A workflow for querying and validating grounded answers from the Auto Ontology system using MCP or REST.
NVIDIAOfficial
Routes ambiguous NVFLARE requests to the appropriate specialized workflow skill based on project evidence.
NVIDIAOfficial
Read hardware-counter snapshots from NVIDIA DOCA-enabled devices using per-domain telemetry reader libraries.
NVIDIAOfficial
A three-phase pipeline chaining AutoML hyperparameter optimization with the DEFT iterative data-improvement loop for model refinement.
NVIDIAOfficial
Practical performance optimization and training strategies for Mixture-of-Experts (MoE) Vision Language Models (VLMs).
NVIDIAOfficial
A two-step pipeline that uses vision-language models to extract referring expressions from captions and ground them to pixel-space bounding boxes.
NVIDIAOfficial
A playbook for managing NeMo-RL training jobs and RayClusters on Kubernetes using the nrl-k8s CLI.
NVIDIAOfficial
Configure Jetson CPU, GPU, and EMC clock ceilings and DVFS behavior by modifying BPMP DTB and nvpower.sh before flashing.
NVIDIAOfficial
Build deterministic weather forecast inference scripts using the Earth2Studio framework.
NVIDIAOfficial
Generate and analyze DNA sequences using NVIDIA's Evo 2 BioNeMo NIM microservice. Use for Evo2/Evo 2, DNA generation, genomic sequence generation, hosted generation, local Docker deployment, local forward passes, layer outputs, logits, sampled probabilities, and BioNeMo NIM workflows.
NVIDIAOfficial
Convert PyTorch Lightning training code into an NVFLARE federated learning job.
NVIDIAOfficial
Extracts metadata from DICOM files and flags potential PHI using standard tags.
NVIDIAOfficial
Automated end-to-end calibration validation for the AutoMagicCalib microservice using a provided sample dataset.
NVIDIAOfficial
Operating guidelines for managing storage and environment secrets on Brev instances for NeMo-RL agents.