528 skills · sorted by relevance
Operate NVIDIA DOCA Management Service to read, change, and monitor BlueField or ConnectX settings locally or remotely. Get guidance on deployment, authentication, management requests, logs, and diagnosing failures across the service and its backend.
Fine-tune a pretrained KERMT model on a CSV of molecular structures and labeled targets. The workflow checks inputs, prepares features, launches training in a container, and saves trained models, logs, and test results.
Turn molecules listed in a SMILES CSV into numerical feature vectors using a KERMT model. The workflow checks the model and input, cleans molecular notation, and saves four sets of vectors with validity information.
Continue training a KERMT molecular model on a custom SMILES corpus, where text strings describe molecular structures. The skill validates data and checkpoints, prepares training inputs, and launches containerized training with saved logs and checkpoints.
Evaluate speech recognition on synthetic clinical audio listed in a NeMo manifest. Produce four error metrics and a five-section report highlighting missed medical terms, then use pronunciation and noise breakdowns to guide dataset improvements or fine-tuning decisions.
Generate small-molecule candidates from a starting structure, optimize supported molecular properties, and save results for validation. Local deployment also supports embeddings, numerical representations of molecules, and workflows that convert between molecular structures and learned internal representations.
Use NVIDIA Maxine / NVIDIA AI for Media audio effects for speech cleanup and enhancement in live or offline media pipelines, including Background Noise Removal, denoise+dereverb, room echo removal, acoustic echo cancellation, audio super-resolution, Studio Voice, Speaker Focus, and Voice Font. Use when selecting, integrating, prompting around, QAing, or privacy-reviewing NVIDIA AFX SDK or BNR NIM workflows for conferencing, broadcast, podcast, avatar, ad, social, and video post-production audio.
The English summary is being prepared. Showing the original description.
Use NVIDIA App's local MCP tools for application, driver, game-optimization, laptop-feature, and restricted In-Game Overlay operations and troubleshooting.
The English summary is being prepared. Showing the original description.
Use when controlling NVIDIA Broadcast through MCP to apply effects, process local media, select devices, or change camera resolution, or when Broadcast is missing or too old to expose the gateway and the user wants it installed; not for Broadcast app settings outside the MCP gateway.
The English summary is being prepared. Showing the original description.
Configure safety checks for LLM applications with NeMo Guardrails. Covers attempts to bypass safety rules, input and output validation, masking personal information, and checking factual claims through programmable rules and integrations.
Run language models locally with llama.cpp on CPUs, Apple Silicon, or AMD and Intel GPUs. The skill guides model setup, memory-saving GGUF format choices, interactive chat, and serving models through an OpenAI-compatible API.
Evaluate language models with over 100 benchmark tests covering knowledge, math, coding, safety, and image understanding. Configure runs on Docker, Slurm computing clusters, or cloud infrastructure, compare models, and export results.
Review agent skills for risky behavior, excessive permissions, and hidden data sharing. It combines static scanning, which checks known risk patterns without running code, with source review to produce an evidence-based installation verdict.
Guides LLM compression through pruning, which removes selected model weights. Covers Wanda and SparseGPT methods without retraining, accuracy comparisons, and structured weight patterns that can accelerate inference on compatible hardware.
Evaluate language models on knowledge, math, coding, safety, and image understanding benchmarks. The skill guides reproducible runs in containers using local Docker, Slurm clusters, or cloud execution, with shared configurations for model comparison and result export.
Guides the definition and publication of business terms, relationships, and measures in Auto Ontology. Covers SQL validation, model import and export, and persisted-change checks to verify that saved definitions reflect the intended business meaning.
Coordinate conversion of CAD and other source assets into simulation-ready USD, a 3D scene format. Organizes material and physics assignment, SimReady conformance checks, validation, and optional preview images and deliverable packages, with consolidated reports.
Generate videos from DEFT media samples using PAIDF Cosmos Predict. Prepare configuration, run generation in Docker, avoid repeated processing of duplicate media paths, and produce JSONL records linking each original sample ID to successful or missing video outputs.
Segment specified organs in CT NIfTI scans using NV-Segment-CT VISTA3D. Produces a label map identifying organ regions and JSON evidence covering labels, voxel counts, physical volumes, geometry checks, and model identity for engineering validation.
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).
The English summary is being prepared. Showing the original description.
Generate synthetic body MRI volumes, or three-dimensional images, with NV-Generate-CTMR rflow-mr. The skill stages configuration settings, runs the existing inference workflow, and records output geometry and data checks alongside the generated images.
Build, migrate, review, and maintain third-party NVIDIA NeMo Fabric adapters against the public adapter contract. Use when creating adapter or target descriptors, mapping AgentConfig into an agent harness or custom-agent runtime, implementing start/invoke/stop, declaring schemas and capabilities, packaging discovery metadata, or assessing adapter conformance. Do not use for consumer applications that only call the NVIDIA NeMo Fabric SDK.
The English summary is being prepared. Showing the original description.
Plan domain or language adaptation for Nemotron Speech recognition. Compare word boosting, language models, and fine-tuning based on available audio, accuracy targets, and budget, then route data preparation, training, evaluation, and deployment to the appropriate sub-skills.
Choose containers and Python package sources that match a Jetson device's GPU architecture, JetPack, and CUDA environment. Get compatibility hints for PyTorch, vLLM, and related stacks before installation, using NVIDIA catalogs and Jetson AI Lab indexes.