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 video-text embeddings for text-to-video retrieval and video-to-video search. Covers Cosmos-Embed1 fine-tuning, inference, export, and semantic deduplication.
Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH or packaged backend image, optionally plans explicit clean source builds, prepares checkpoints, validates the first update in-process, and returns token-weighted losses and task-aware accuracy.
Fine-tunes vision, vision-language, and language models in NGC PyTorch containers when no dedicated TAO skill applies. Covers inspection, research, smoke testing, training, evaluation, inference, Hub publishing, and generation of a reusable rerun skill.
Runs a two-step pipeline that extracts referring expressions from image-caption pairs and grounds them to pixel-space bounding boxes with a VLM. Supports automatic labeling for image grounding datasets.
Uses VLM distillation to produce region descriptions, scene captions, and referring expressions tied to bounding boxes. Includes an optional verification pass for the generated expressions.
Runs a multi-step annotation pipeline using VLM and LLM distillation. Produces multi-level captions and multiple-choice, binary, or open-ended question-answer pairs with reasoning traces.
The mandatory pre-launch gate and four-verb execution contract for every TAO workflow or action. Invoke BEFORE launching anything side-effecting — AutoML, train, evaluate, inference, export, TensorRT engine generation, or DEFT/application workflows — on any execution platform. Covers platform selection, credentials, image confirmation, dataset intake, preflight, the launch review, job records, mon…
Generates capability summaries from application, data, model, AutoML, and platform manifests. Answers questions about available models, workflows, and AutoML support.
Embeds gap-analysis target samples and a source image pool, then selects nearby source images for augmentation. Follows sample routing in the DEFT workflow.
Covers model inspection, native trainer implementation, tao-core configuration, ONNX export, and deployment integration. Includes packaging, L0 tests, container-based end-to-end validation, and conditional accuracy or latency tuning across several vision tasks.
Processes the output of Visual ChangeNet gap analysis into subsets for individual augmentation modules. Prepares AOI samples for steps such as nearest-neighbor mining and AnomalyGen.
Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), WandB experiment tracking, job execution on any TAO SDK platform, result interpretation, and per-rec custom evaluation hooks. Use when the user mentions TAO AutoML, hyperparameter optimization, HPO, aut…
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