Skip to main content
NeVibeCode · 2,385 items

Skills for AI and ML

Skills for AI and ML: what each one does, an install command and example prompts.

nemo-automodel-recipe-development NVIDIA skill Guides the agent in creating and editing NeMo AutoModel training and evaluation recipes. It covers YAML configuration, builder functions, and CLI execution flow. CX Codex +1 1,900installs earth2studio-deterministic-forecast NVIDIA Earth-2 Team skill A skill that walks you through building a deterministic weather forecast script with Earth2Studio: model, data source, IO backend and inference. CX Codex +1 1,900installs earth2studio-discover NVIDIA Earth-2 Team skill Finds compatible Earth2Studio models, data sources, and gallery examples for climate workflows. It focuses on discovery, not inference code or data downloads. CX Codex +1 1,900installs earth2studio-install NVIDIA Earth-2 Team skill Walks you through installing Earth2Studio and picking the model extras you need. Useful when the environment has to be right before any forecasting work starts. CX Codex +1 1,900installs physicsnemo-discover NVIDIA skill An NVIDIA skill that finds the right model, datapipe or example in PhysicsNeMo for a SciML task. It points at files and writes no code. CX Codex +1 1,900installs digital-health-clinical-asr-finetune Ben Randoing skill Skill for running stock NeMo SFT on Parakeet TDT v2 and measuring post-training KER. Useful at Stage 4 when priority Keyword Error Rate exceeds 0.3. CX Codex +1 1,900installs digital-health-clinical-asr-eval Ben Randoing skill Scores a NeMo manifest for clinical ASR, computes WER, CER, KER and SER, and builds a five-section leaderboard. Use it when you need to decide between fine-tuning and fixing pronunciation coverage. CX Codex +1 1,900installs digital-health-clinical-asr-build Ben Randoing skill Curates clinical terms, synthesizes eval audio through Magpie TTS and writes a NeMo manifest. Stage 2 of the Clinical ASR Flywheel. CX Codex +1 1,900installs digital-health-clinical-asr-setup Ben Randoing skill Sets up the environment for NVIDIA's Clinical ASR Flywheel, verifies the NVIDIA_API_KEY, installs Python dependencies, and runs an end-to-end smoke test. CX Codex +1 1,900installs dicom-series-to-volume NVIDIA MedTech Team skill Turns one CT DICOM series folder into an HU NIfTI volume plus a JSON summary with the affine. Handy before feeding scans to a segmentation model. CX Codex +1 1,900installs dicom-series-preflight NVIDIA MedTech Team skill Reads DICOM headers in a single series folder and returns JSON with a pass, warn or fail verdict before conversion or inference. CX Codex +1 1,900installs dicom-metadata-extract NVIDIA MedTech Team skill Runs a pydicom script on a single DICOM file to extract metadata and detect standard PHI tags. Useful for quick agent inspections of medical imaging files. CX Codex +1 1,900installs nemotron-policy-generator Shyamala Prayaga skill Turn moderation requirements or an existing policy into structured artifacts for NVIDIA Nemotron safety models. Useful when a project needs its rules prepared for model inference. CX Codex +1 1,900installs prompt-optimizer getsentry skill A skill that rewrites system and agent prompts against a set of eval cases instead of gut feeling. Useful when a prompt exists but behaves inconsistently. CX Codex +1 2,300installs ai-product-strategy RefoundAI skill Guides product decisions for AI features, helping you choose between RAG and fine-tuning and plan for non-deterministic model behavior. CX Codex +1 2,700installs alphaear-predictor RKiding skill This skill produces a Kronos-based forecast for a financial time series, then adjusts the numbers against fresh news. Useful when you need a short-horizon price view. CX Codex +1 584installs bailian-web-search modelstudioai skill This skill picks the search path for CLI bl: the model's built-in search or Bailian MCP. Useful when you work with Alibaba Bailian and keep mixing up keys. CX Codex +1 3,100installs holoscan-install-source Holoscan Team skill Builds and verifies NVIDIA Holoscan SDK 5.x from source using the repository container wrapper. Helps with Early Access branches and custom SDK components. CX Codex +1 1,800installs holoscan-install-debian Holoscan Team skill Installs native C++ Debian packages of Holoscan SDK 5.x on Ubuntu 24.04 and checks that the bundled examples build. CX Codex +1 1,800installs holoscan-install-wheel Holoscan Team skill Installs Holoscan SDK 5.x CUDA 13 Python wheels into an isolated venv and checks that the import works. CX Codex +1 1,800installs holoscan-install-conda Holoscan Team skill Checks Conda package availability for Holoscan SDK 5.x releases, flags missing 5.0 builds, and routes to supported installation alternatives. CX Codex +1 1,800installs holoscan-install-container Holoscan Team skill Checks a host and installs the Holoscan SDK 5.x CUDA 13 development container. Use it before running the SDK in Docker with GPU access. CX Codex +1 1,800installs holoscan-setup Holoscan Team skill Checks a Linux host and picks a Holoscan SDK 5.x install path: container, Debian packages, wheels or a source build. CX Codex +1 1,800installs tilegym-adding-cutile-kernel TileGym Team skill Guides AI coding agents through adding cuTile GPU kernel operators to TileGym. Useful when implementing custom kernels, tests, and benchmarks. CX Codex +1 1,800installs mcore-testing Philip Petrakian skill A skill that maps out the Megatron-LM test system: test layout, recipe YAML, golden values, and how to run unit tests locally. CX Codex +1 1,800installs mcore-run-on-slurm Philip Petrakian skill Prepare a SLURM launch for distributed Megatron-LM training, from an sbatch skeleton to rank-level failure checks. Useful when configuring or debugging a multi-node job. CX Codex +1 1,800installs nemo-rl-brev-etiquette NVIDIA skill A skill that tells the agent where files belong on a Brev box: code stays in the repo, heavy run output goes to /ephemeral. CX Codex +1 1,800installs mcore-linting-and-formatting Philip Petrakian skill Sets up linting and code formatting for Megatron-LM projects. It helps fix ruff and mypy violations and sort imports before opening a pull request. CX Codex +1 1,800installs nemo-mbridge-perf-tp-dp-comm-overlap NVIDIA skill A skill that walks through enabling TP, DP and PP communication overlap in Megatron-Bridge: which knobs to turn, where the code gates it, how to verify. CX Codex +1 1,800installs nemo-mbridge-perf-moe-dispatcher-selection NVIDIA skill Picks between alltoall, DeepEP and HybridEP for MoE token dispatch based on your hardware, EP degree and optimization stage. CX Codex +1 1,800installs nemo-mbridge-perf-megatron-fsdp NVIDIA skill Configures Megatron FSDP in Megatron-Bridge to replace standard DDP, helping resolve out-of-memory errors and verify training checkpoints. CX Codex +1 1,800installs nemo-rl-docs NVIDIA skill This skill hands your agent the documentation rules for NeMo-RL: keeping docs/index.md current and writing docstrings in Google style. Useful when you touch the docs. CX Codex +1 1,800installs nemo-mbridge-resiliency NVIDIA skill A skill covering resiliency setup in Megatron Bridge: fault tolerance, straggler detection, preemption and re-run state machine. CX Codex +1 1,800installs nemo-mbridge-perf-hierarchical-context-parallel NVIDIA skill Configures hierarchical context parallelism in Megatron-Bridge. Useful for scaling long-sequence model training when context length exceeds KV head counts. CX Codex +1 1,800installs nemo-mbridge-perf-moe-hardware-configs NVIDIA skill A reference of MoE training starting configurations for H100, B200, GB200, and GB300. Use it when selecting a dispatcher, parallelism layout, or planning throughput checks. CX Codex +1 1,800installs nemo-mbridge-perf-moe-comm-overlap NVIDIA skill A skill for MoE expert-parallel communication overlap in Megatron Bridge: dispatch/combine, flex dispatcher backends, expert wgrad scheduling. CX Codex +1 1,800installs nemo-mbridge-perf-moe-long-context NVIDIA skill Guides context parallelism sizing and selective recompute for long-context MoE training in Megatron Bridge. CX Codex +1 1,800installs nemo-mbridge-perf-expert-parallel-overlap NVIDIA skill A skill for enabling and validating MoE expert-parallel communication overlap in Megatron-Bridge, covering alltoall and flex dispatchers with DeepEP and HybridEP. CX Codex +1 1,800installs nemo-mbridge-perf-cpu-offloading NVIDIA skill A skill that validates and enables CPU offloading in Megatron Bridge: layer-level activation offloading and optimizer state offloading via HybridDeviceOptimizer. CX Codex +1 1,800installs nemo-mbridge-perf-moe-optimization-workflow NVIDIA skill Guides MoE throughput tuning and regression diagnosis in Megatron Bridge. Useful when diagnosing speed drops after commit or configuration changes. CX Codex +1 1,800installs

961–1,000 of 2,385

Narrow it down

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor