tao-train-nvpanoptix3d
Supports training, evaluation, export, and inference for NVPanoptix3D. The model produces semantic, instance, and panoptic masks with occupancy completion using a VGGT backbone and 3D frustum reconstruction.
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.Supports training, evaluation, export, and inference for NVPanoptix3D. The model produces semantic, instance, and panoptic masks with occupancy completion using a VGGT backbone and 3D frustum reconstruction.
Uses a Spatial Temporal Graph Convolutional Network to classify skeleton sequences into action categories. Supports model training, evaluation, export, and inference from pose-keypoint data.
Analyzes market OHLCV data using multiple technical indicators. Provides deterministic assessments of trend, momentum, volume, and divergence.
Supports Metric Depth Anything v2 and Relative Depth Anything architectures. Covers TAO model training, evaluation, export, and inference.
Combines cash forecasting, prioritized overdue-invoice reminders, and timesheet preparation with anomaly checks. Stages a Gusto run or produces a validated run sheet for QuickBooks Payroll or manual entry. Supports uploaded data and never submits payroll.
Prices swaps across tenors and overlays government and inflation curves. Supports swap spread calculations, real rate decomposition, cross-currency comparisons, and identification of steepener, flattener, and butterfly trades.
Analyzes prediction JSON for yes/no visual question classification workflows. Identifies failure cases for downstream DEFT root cause analysis.
Uses a transformer architecture with masked attention for universal image segmentation. Covers TAO training, evaluation, export, quantization, and inference.
Define formatting, numbering, and criteria for writing Architecture Decision Records in docs/adr/. Supports recording architectural decisions and reviewing ADRs.
Checks vulnerable packages, exposed secrets, OWASP code patterns, authentication configuration, CORS policies, and data protection. Produces severity-rated findings with specific remediation steps.
Learns discriminative embeddings through metric learning to match the same person across different cameras. Supports training, evaluation, export, and inference for TAO person re-identification models.
Applies cross-parameter rules for .NET project creation, including framework selection for native AOT, HTTPS with authentication, and mutually exclusive API options. Fills unset values and explains applied defaults.
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