Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Orchestrates a three-phase training pipeline combining hyperparameter optimization with root cause analysis, synthetic data generation, mining, and retraining. Supports AOI and other DEFT applications, carrying winning baseline parameters into the improvement loop.
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP synthetic defects, k-NN mining, retraining, and deployment gating against a customer-defined primary metric and optional constraints. Use only when the request identifies an AOI / automated-optical-inspection, PCB-defect, VisualChangeNet, or Chang…
Resolves container images, constructs job-payload JSON, and manages the service registry. Delegates container execution to platform skills to deploy and operate inference endpoints for TAO checkpoints.
Run a TAO training/evaluation/inference container on an NVIDIA Brev GPU instance. Instance provisioning (create/search/stop/delete/login) is delegated to the official brev-cli agent skill or the Brev MCP server; this skill covers only the TAO-specific part — running the container over brev exec via the four-verb docker contract. Trigger phrases include "run on Brev", "Brev GPU instance", "TAO on…
Kubernetes execution platform — submits TAO container jobs as k8s Jobs with NVIDIA GPU scheduling; single-pod for one node, Indexed Jobs for multi-node distributed training. Use when running on EKS / GKE / AKS / on-prem clusters with the NVIDIA GPU Operator installed, or when integrating TAO into an existing k8s-native ML platform.
Submits training, evaluation, and inference jobs using sbatch or srun. Supports Pyxis/Enroot containers and Lustre-backed results on on-premises or DGX SLURM clusters.
Validates compatible NVIDIA driver, CUDA Toolkit, and Container Toolkit versions. Supports checks on Linux distributions and approval-based automated installation on Debian, RHEL, and SUSE families, with manual instructions elsewhere.
Supports RGB, optical flow, and joint multi-stream inputs for temporal action classification. Covers model training, evaluation, export, and inference.
Fuses LiDAR point clouds and camera images in bird's-eye-view space for multi-sensor perception. Supports training, evaluation, and inference with TAO BEVFusion models.
Detects object centers and regresses keypoint locations to estimate object pose. Supports TAO CenterPose training, evaluation, export, and inference.
Uses deformable attention for efficient multi-scale feature processing. Covers TAO model training, evaluation, export, quantization, and inference.
Supports Metric Depth Anything v2 and Relative Depth Anything architectures. Covers TAO model training, evaluation, export, and inference.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name