AI & ML
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
-
nvidia Bundle Tao Finetune ClipFine-tune and deploy CLIP vision-language models for zero-shot classification, image-text retrieval, and embedding extraction with ONNX and TensorRT support.
Audited 2.2k -
nvidia Bundle Tao Run On LeptonSubmit TAO jobs to Lepton managed GPU compute on DGX Cloud, with run/status/cancel interface and multi-node distributed training support.
Audited 2.2k -
nvidia Bundle Mcore Run On SlurmLaunch distributed Megatron-LM training jobs on a SLURM cluster with a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules, container conventions, monitoring, and per-rank failure diagnosis.
Audited 2.2k -
nvidia Bundle Nemotron CustomizePlan, configure, and chain Nemotron model customization steps into single-step or multi-step pipelines for curation, translation, fine-tuning, RL alignment, benchmarking, checkpoint conversion, optimization, and evaluation.
2.2k -
nvidia Bundle Tao Train Nvdinov2Trains vision transformers via self-distillation without labels for self-supervised visual representation learning, and supports export and inference of NVDINOv2 backbones.
Audited 2.2k -
nvidia Bundle Tao Train Sparse4dTrains, evaluates, exports, quantizes, and runs inference for Sparse4D multi-camera temporal 3D object detection and tracking models using TAO.
Audited 2.2k -
nvidia Bundle Vss Deploy ProfileSelects, configures, deploys, verifies, debugs, or tears down a VSS profile (base, search, lvs, warehouse, edge) for NVIDIA's video search and summarization stack.
2.2k -
nvidia Bundle Vss Search ArchiveSearch archived video using natural language, ingest video files or RTSP streams, and manage ingested sources.
Audited 2.2k -
nvidia Bundle Nemoclaw User GuideGuides AI coding assistants to the official NemoClaw documentation via MCP server or Markdown files for installation, configuration, operation, and troubleshooting.
Audited 2.2k -
nvidia Bundle Tao Launch WorkflowCollects launch inputs and runs preflight checks before executing TAO workflows such as AutoML, training, evaluation, inference, export, TensorRT engine generation, or DEFT jobs on supported platforms.
Audited 2.2k -
nvidia Bundle Tao Mine Aoi ImagesEmbeds target and source image parquets, then mines nearest-neighbour source images for augmentation in VCN AOI workflows.
Audited 2.2k -
nvidia Bundle Tao Train BevfusionTrains, evaluates, and runs inference for BEVFusion multi-sensor 3D object detection models that fuse LiDAR and camera data in bird's-eye-view space for autonomous driving.
Audited 2.2k -
nvidia Bundle Tao Train OneformerTrain, evaluate, export, quantize, and run inference for a TAO OneFormer model that performs panoptic, instance, and semantic segmentation using task-conditioned queries.
Audited 2.2k -
nvidia Bundle Tao Train SegformerTrains, evaluates, exports, quantizes, and runs inference for SegFormer semantic segmentation models using NVIDIA TAO.
Audited 2.2k -
nvidia Bundle Vss Query AnalyticsQueries video analytics incidents, alerts, metrics, and sensor data from Elasticsearch via the VA-MCP server.
Audited 2.2k -
nvidia Bundle Vss Summarize VideoSummarize recorded video clips using the LVS microservice with a VLM fallback, producing a narrative summary with timestamped events.
Audited 2.2k -
nvidia Bundle Dynamo Recipe RunnerSelect, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes for model serving with GPU support.
Audited 2.2k -
nvidia Bundle Earth2studio InstallGuides installing Earth2Studio via uv or pip, selecting model extras, and configuring environment variables.
Audited 2.2k -
nvidia Bundle Jetson LLM BenchmarkBenchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
Audited 2.2k -
nvidia Bundle Nv Generate Ct RflowGenerates synthetic CT volumes and masks using NVIDIA's rectified-flow pipeline for medical imaging research.
Audited 2.2k -
nvidia Bundle Nv Generate Mr BrainGenerates synthetic brain MRI volumes using NVIDIA's NV-Generate-CTMR workflow, with configurable modality and random seed.
Audited 2.2k -
nvidia Bundle Physicsnemo DiscoverNavigate the PhysicsNeMo repository by discovering model families, datapipes, and examples through live file search, without writing training code.
Audited 2.2k -
nvidia Bundle Skill Card GeneratorGenerates or updates a governance skill card for an existing agent skill directory by analyzing source signals, building a grounded JSON context, and rendering a deterministic markdown card.
Audited 2.2k -
nvidia Bundle Tao Train CenterposeTrain, evaluate, export, and run inference for CenterPose models used in 6-DoF object pose estimation with keypoint regression.
Audited 2.2k -
nvidia Bundle Cuopt Skill EvolutionDetects generalizable learnings from problem-solving interactions and proposes skill updates to improve future performance.
Audited 2.2k -
nvidia Bundle Dynamo Router StarterStart or patch Dynamo router modes and run router endpoint smoke checks for round-robin, KV-aware, least-loaded, or device-aware routing.
Audited 2.2k -
nvidia Bundle Earth2studio DiscoverFind Earth2Studio models, data sources, and examples for weather/climate use cases by consulting live documentation and verifying compatibility via the lexicon system.
Audited 2.2k -
nvidia Bundle Nemo Evaluator PluginRun evaluation tasks against a NeMo Platform server using the Evaluator plugin CLI and Python SDK.
Audited 2.2k -
nvidia Bundle Nemo Rl Auto ResearchGuides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.
2.2k -
nvidia Bundle Tao List CapabilitiesLists TAO Skill Bank capabilities, models, and AutoML support by running packaged scripts.
Audited 2.2k -
nvidia Bundle Tao Train Single StepFine-tune a TAO model with standard supervised training, evaluation, and export, with AutoML bypass and platform-specific credential intake.
Audited 2.2k -
nvidia Bundle Tilegym Cutile PythonWrite high-performance GPU kernels using cuTile's tile-based programming model with validation and optimization, including deep agent orchestration for complex multi-kernel tasks.
Audited 2.2k -
nvidia Bundle Dicom Series PreflightScans a DICOM series folder to extract header metadata and produce a preflight verdict without decoding pixel data.
Audited 2.2k -
nvidia Bundle Holoscan Install CondaInstall Holoscan SDK v4.3+ via Conda in a CUDA 13 environment, including Python bindings and C++ development headers.
Audited 2.2k -
nvidia Bundle Nemo Rl Brev EtiquetteProvides storage and environment conventions for NeMo-RL agents on Brev instances, ensuring large experiment outputs go to /ephemeral and secrets are loaded from .env.
2.2k -
nvidia Bundle Nv Segment Ct FinetuneFine-tune NV-Segment-CT VISTA3D on CT NIfTI labels for smoke testing or dataset adaptation, wrapping the upstream MONAI bundle entrypoint.
Audited 2.2k
Frequently asked questions
What are AI & ML agent skills?
AI & ML agent skills cover the machine-learning workflow itself: writing and evaluating prompts, building RAG pipelines, running evals, and wiring up model APIs. Each one is a SKILL.md file your agent loads on demand, so the know-how travels across Claude Code, Cursor, and 60+ agents.
Which AI & ML skills are most installed?
Popular AI & ML skills on SkillMD right now include nemoclaw-user-guide, tilegym-cutile-python, physicsnemo-discover. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do AI & ML skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.