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.Detects object centers and regresses keypoint locations to estimate object pose. Supports TAO CenterPose training, evaluation, export, and inference.
Trains vision transformers without labels using teacher-student self-distillation. Supports training, export, and inference for TAO NVDINOv2 backbones that produce general-purpose visual features.
Provides deep security review patterns for Convex applications. Examines authorization logic, data access boundaries, action isolation, rate limiting, and protection of sensitive operations.
Supports reading, inspecting, writing, transforming, and preflighting local DICOM datasets. Covers metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
Addresses new features, UX behavior, architecture changes, unclear success criteria, and competing approaches before coding. Distinguishes these from mechanical refactors, known fixes, and unambiguous configuration changes.
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…
Learns visual representations by masking random image patches and reconstructing them. Supports pretraining, fine-tuning, evaluation, export, and inference.
Uses a ViT-MAE backbone for weakly supervised segmentation from point or bounding-box annotations. Supports TAO MAL training, evaluation, and inference.
Covers feature folders, endpoint grouping, and handler patterns using Mediator, Wolverine, or plain handler classes. Supports work in existing VSA projects and adding new feature slices.
Uses structured questions to assess domain complexity, team size, system lifetime, compliance, and integration requirements. Recommends Vertical Slice, Clean Architecture, DDD with Clean Architecture, or Modular Monolith for new projects or restructuring.
Supports naming workflows for founders, agencies, and businesses. Selects either name generation or evaluation based on the supplied brief or existing options, including feedback, ranking, and scoring.
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