N
Nvidia Skills
ego lite browser
sponsorego lite is the fastest browser for AI agents to run web automation, sharing your logged-in state with Codex or Claude Code, zero cost, zero config.
Alpha Vantage MCP Server
sponsorAccess financial market data: realtime & historical stock, ETF, options, forex, crypto, commodities, fundamentals, technical indicators, & more
accelerated-computing-cudf
nvidia
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and…
accessibility
nvidia
Unified accessibility auditing workflow across static analysis, runtime testing, ARIA patterns, keyboard navigation, and color contrast. Use this skill…
accessing-mlflow
nvidia
Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts…
accessing-mlflow
nvidia
Query and browse evaluation results stored in MLflow. Use when the user wants to look up runs by invocation ID, compare metrics across models, fetch artifacts…
add-binding-feature
nvidia
Add or change a public NeMo Relay API surface across the core runtime and every affected binding
add-binding-feature
nvidia
Add or change a public NeMo Relay API surface across the core runtime and every affected binding
add-middleware
nvidia
Add a new guardrail or intercept type to the NeMo Relay middleware pipeline
add-middleware
nvidia
Add a new guardrail or intercept type to the NeMo Relay middleware pipeline
aicr-analyzing-snapshots
nvidia
Use when analyzing an AICR snapshot YAML file, reviewing cluster state, comparing provider characteristics, extracting GPU/network topology insights, or…
aicr-auditing-docs
nvidia
Use when reviewing AICR's Markdown documentation for duplication, drift, bloat, and gaps — to keep docs high-value as the project evolves. Triggers on "audit…
aicr-creating-guided-demos
nvidia
Scaffolds an interactive guided demo script (demos/*.sh), live or self-paced, with the Frame → Tell → Show → Close pattern. Triggers on "demo script", "guided…
aicr-creating-slide-decks
nvidia
Use when building a self-contained HTML slide deck or visual talking-point for a technical concept or workflow (e.g. a demos/*.html) — shown full-screen or…
aicr-managing-openvex
nvidia
Use when adding, updating, or removing CVE/GHSA suppressions in `.openvex.json` — the OpenVEX document consumed by the daily image vulnerability scan workflow.…
aicr-release-notes
nvidia
Use when drafting the human-readable GitHub release notes summary for an upcoming AICR release. Triggers on "release notes", "draft release…
aiq-deploy
nvidia
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
aiq-research
nvidia
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
amc-run-rtsp-calibration
nvidia
Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras;…
amc-run-sample-calibration
nvidia
Run end-to-end calibration on the shipped sample dataset (sdg_08_2_sample_data_010926.zip) against a running AMC microservice. Use when user says 'test sample…
amc-run-video-calibration
nvidia
Calibrate a new dataset from pre-recorded video files via the AutoMagicCalib REST API. Use when user has local MP4s and says 'calibrate my videos', 'run AMC on…
amc-setup-calibration-stack
nvidia
Launch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto…
analysis-methods
nvidia
Teaches the analyst agent how to write correct, robust Python analysis code for FHIR clinical data using pandas, matplotlib, and scipy.
analysis-methods
nvidia
Teaches the analyst agent how to write correct, robust Python analysis code for FHIR clinical data using pandas, matplotlib, and scipy.
api-design
nvidia
Component API design patterns following Elements conventions for properties, attributes, CSS custom properties, slots, and events. Use this skill whenever the…
apply-inference-optimizations
nvidia
Apply FlashDreams-style inference speedups to model integrations after a baseline exists: bounded windows and fixed K/V caches, cache/decode overlap,…
asset-harvester
nvidia
Use to install and run NVIDIA Asset Harvester (Apache-2.0) to extract per-object 3D Gaussian Splat assets (`gaussians.ply`) from AV NCore V4 clips or masked…
auto-research
nvidia
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle:…
availability-report
nvidia
Generate a production availability report for NVIDIA Elements packages and documentation.
benchmark-isaaclab
nvidia
Run Isaac Lab benchmark scripts and interpret their outputs. Covers RL training throughput, non-RL environment step FPS, camera/load/startup benchmarks, batch…
benchmark-isaaclab
nvidia
Run Isaac Lab benchmark scripts and interpret their outputs. Covers RL training throughput, non-RL environment step FPS, camera/load/startup benchmarks, batch…
benchmark-isaacsim
nvidia
Run Isaac Sim benchmark scripts and interpret benchmark outputs. Covers camera, SDG, scene-loading, robot, lidar/radar/sensor benchmark scripts, common…
benchmark-isaacsim
nvidia
Run Isaac Sim benchmark scripts and interpret benchmark outputs. Covers camera, SDG, scene-loading, robot, lidar/radar/sensor benchmark scripts, common…
blender-host-sandbox-boundary
nvidia
Route Blender, USD, OVRTX, and OVPhysX work when Hermes terminal and file tools run in an OpenShell sandbox but Blender MCP runs inside a host Blender process.…
blender-python-api-verification
nvidia
Verify Blender Python properties, enums, operators, animation APIs, and add-on interfaces against the running Blender build before writing or executing…
brev-etiquette
nvidia
Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional…
build-and-dependency
nvidia
Container-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and…
build-from-issue
nvidia
Given a GitHub issue number, plan and implement the work described in the issue. Supports direct user requests and unattended queue processing through the…
build-from-issue
nvidia
Given a GitHub issue number, plan and implement the work described in the issue. Operates iteratively - creates an implementation plan, responds to feedback,…
build-system
nvidia
Wireit orchestration, build optimization, caching strategies, and build troubleshooting for the Elements monorepo. Use this skill whenever the user asks about…
case-summary
nvidia
Prepare a complete clinical case summary for a patient from FHIR endpoints. Use when asked to summarize a patient, compile a case, or prepare for tumor board.
case-summary
nvidia
Prepare a complete clinical case summary for a patient from FHIR endpoints. Use when asked to summarize a patient, compile a case, or prepare for tumor board.
changelog-audit
nvidia
Audit Warp CHANGELOG.md before a release: recover lost entries, sort by user impact, refine entry language, line-wrap, and (release-branch mode) bump compare…
changelog-audit
nvidia
Audit Warp CHANGELOG.md before a release: recover lost entries, sort by user impact, refine entry language, line-wrap, and (release-branch mode) bump compare…
chef-assistant
nvidia
Use when cooking or planning meals, troubleshooting recipes, learning culinary techniques
cicd
nvidia
CI/CD reference for NeMo-RL. Covers GitHub Actions pipeline structure, CI triggering via /ok to test, and CI failure investigation.
cicd
nvidia
CI/CD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI, and CI failure investigation.
clinical-delegation
nvidia
How to delegate clinical tasks to specialist agents. Always use sub-agent runtime with explicit agentId — never ACP. Never call FHIR via web_fetch.
clinical-delegation
nvidia
How to delegate clinical tasks to specialist agents. Always use sub-agent runtime with explicit agentId — never ACP. Never call FHIR via web_fetch.
clinical-knowledge
nvidia
Teaches agents clinical reference ranges, condition codes, quality measure definitions, drug classifications, and regulatory context so they can flag abnormal…
clinical-knowledge
nvidia
Teaches agents clinical reference ranges, condition codes, quality measure definitions, drug classifications, and regulatory context so they can flag abnormal…
cmake-structure
nvidia
IsaacTeleop CMake target layout and #include conventions. Use whenever you create or edit a CMakeLists.txt, add or move a module/library/executable/test…
coach-nemoclaw-hermes
nvidia
Coach a NemoClaw Hermes sub-agent through Blender, OVRTX, OVPhysX, USD, rendering, simulation, and live Blender-control tasks. Use when Codex should delegate…
code-formatter
nvidia
Formats Python code using the black formatter
code-review
nvidia
Comprehensive code review process for Elements monorepo changes. Provides structured feedback on type safety, testing, documentation, and adherence to project…
code-reviewer
nvidia
Reviews code changes and suggests improvements
cohort-compare
nvidia
Analyze a cohort of patients from FHIR endpoints to find care gaps and patterns. Use when asked to compare patients, find quality gaps, or analyze a population.
cohort-compare
nvidia
Analyze a cohort of patients from FHIR endpoints to find care gaps and patterns. Use when asked to compare patients, find quality gaps, or analyze a population.
compare-results
nvidia
Establish baseline-vs-candidate evaluation plans, delegate missing evaluations, compare validated results, and decide quantization feasibility. Use when the…
compare-results
nvidia
Establish baseline-vs-candidate evaluation plans, delegate missing evaluations, compare validated results, and decide quantization feasibility. Use when the…
compileiq-author-objective
nvidia
Use when writing the objective_function= passed to Search(). Covers the two legal signatures (compiler-only str vs mixed list), the baseline-knockout branch,…
compileiq-author-objective
nvidia
Use when writing the objective_function= passed to Search(). Covers the two legal signatures (compiler-only str vs mixed list), the baseline-knockout branch,…
compileiq-booster-pack
nvidia
Use BEFORE running a full CompileIQ search. Walks through downloading a Booster Pack from NVIDIA/CompileIQ GitHub Releases, applying ACF candidates one at a…
compileiq-booster-pack
nvidia
Use BEFORE running a full CompileIQ search. Walks through downloading a Booster Pack from NVIDIA/CompileIQ GitHub Releases, applying ACF candidates one at a…
compileiq-bootstrap
nvidia
Use when starting a fresh CompileIQ project, hitting a socket timeout, or before running any other compileiq-* skill. Verifies CUDA 13.3+, ptxas, GPU access,…
compileiq-bootstrap
nvidia
Use when starting a fresh CompileIQ project, hitting a socket timeout, or before running any other compileiq-* skill. Verifies CUDA 13.3+, ptxas, GPU access,…
compileiq-debug
nvidia
Use when something is wrong: Search() hangs, all evaluations return INVALID_SCORE, scores aren't improving, every config returns the same number, ptxas errors…
compileiq-debug
nvidia
Use when something is wrong: Search() hangs, all evaluations return INVALID_SCORE, scores aren't improving, every config returns the same number, ptxas errors…
compileiq-run-search
nvidia
Use when composing the Search(...) call and calling .start(). Covers the four worker classes (MultiProcessWorker / IsoMultiProcessWorker / RayWorker /…
compileiq-run-search
nvidia
Use when composing the Search(...) call and calling .start(). Covers the four worker classes (MultiProcessWorker / IsoMultiProcessWorker / RayWorker /…
compileiq-search-space
nvidia
Use when picking the search_space= argument for Search(). Covers the three provider classes (PtxasSearchSpace, NvccSearchSpace, LocalSearchSpaceBin), how to…
compileiq-search-space
nvidia
Use when picking the search_space= argument for Search(). Covers the three provider classes (PtxasSearchSpace, NvccSearchSpace, LocalSearchSpaceBin), how to…
compileiq-validate-result
nvidia
Use AFTER a Search has completed and BEFORE claiming any speedup or shipping an ACF. Loads the dump_results CSV, extracts top-K candidates (single-objective)…
compileiq-validate-result
nvidia
Use AFTER a Search has completed and BEFORE claiming any speedup or shipping an ACF. Loads the dump_results CSV, extracts top-K candidates (single-objective)…
component-creation
nvidia
Guide for creating new Elements components with all required files, base classes, metadata patterns, and test boilerplate. Use this skill whenever the user…
config-reader
nvidia
Reads and displays configuration files
contribute-adapter
nvidia
Add or substantially change a NeMo Fabric harness adapter, including its architecture, descriptor claims, package wiring, capability and policy mapping,…
contribute-api
nvidia
Contribute a new NeMo Fabric public API surface safely, with Rust, CLI, Python, schema, adapter, and documentation parity in mind
contribute-api
nvidia
Contribute a new NeMo Relay public API surface safely, with binding parity and docs in mind
contribute-api
nvidia
Contribute a new NeMo Relay public API surface safely, with binding parity and docs in mind
contribute-docs
nvidia
Contribute documentation or example changes that stay aligned with NeMo Fabric public behavior
contribute-docs
nvidia
Contribute documentation or example changes that stay aligned with NeMo Relay public behavior
contribute-docs
nvidia
Contribute documentation or example changes that stay aligned with NeMo Relay public behavior
contribute-integration
nvidia
Contribute a new or updated third-party framework integration for NeMo Relay
contribute-integration
nvidia
Contribute a new or updated third-party framework integration for NeMo Relay
coordinate-nemoclaw-blender
nvidia
Legacy compatibility entry point for prompts that explicitly request coordinate-nemoclaw-blender. Use coach-nemoclaw-hermes for new Codex-coached Blender,…
cosmos3-codebase-nav
nvidia
Navigate the Cosmos3 package codebase to find where parameters, configs, defaults, scripts, and documentation live. Use when the user asks "where is X in…
cosmos3-env-troubleshoot
nvidia
Diagnose and fix Cosmos3 environment, installation, and runtime errors. Use when the user encounters an ImportError, ModuleNotFoundError, CUDA error, Docker…
cosmos3-inference
nvidia
Guide users through running Cosmos3 inference — offline batch generation, online serving with Ray and Gradio, parallelism options, input formats, sampling…
cosmos3-post-training
nvidia
Guide users through Cosmos3 supervised fine-tuning (SFT) post-training: preparing the example dataset and Wan2.2 VAE, converting the base checkpoint to DCP,…
cosmos3-setup
nvidia
Guide users through Cosmos3 installation, environment setup, checkpoint downloading, and verification. Use when the user asks "how do I install cosmos3", "how…
create-github-issue
nvidia
Create GitHub issues using the gh CLI. Use when the user wants to create a new issue, report a bug, request a feature, or create a task in GitHub. Trigger…
create-github-issue
nvidia
Create GitHub issues using the gh CLI. Use when the user wants to create a new issue, report a bug, request a feature, or create a task in GitHub. Trigger…
create-github-pr
nvidia
Create GitHub pull requests using the gh CLI. Use when the user wants to create a new PR, submit code for review, or open a pull request. Trigger keywords -…
create-github-pr
nvidia
Create GitHub pull requests using the gh CLI. Use when the user wants to create a new PR, submit code for review, or open a pull request. Trigger keywords -…
create-issue
nvidia
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
create-rfc
nvidia
Create OpenShell RFC proposals in rfc/ from a design request. Use when the user asks to write, draft, start, create, or update an RFC, Request for Comments,…
create-rfc
nvidia
Create OpenShell RFC proposals in rfc/ from a design request. Use when the user asks to write, draft, start, create, or update an RFC, Request for Comments,…
create-spike
nvidia
Investigate a plain-language problem description by deeply exploring the codebase, then create a structured GitHub issue with technical findings. Prequel to…
create-spike
nvidia
Investigate a plain-language problem description by deeply exploring the codebase, then create a structured GitHub issue with technical findings. Prequel to…
creative-writing-coach
nvidia
Helps users with creative writing and storytelling
cudaq-guide
nvidia
CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.
cudaq-guide
nvidia
Use for CUDA-Q setup, simulation targets, QPU access, and @cudaq.kernel authoring guidance.
cuequivariance
nvidia
Define custom groups (Irrep subclasses), build segmented tensor products with CG coefficients, create equivariant polynomials and IrDictPolynomials, and use…
cuequivariance
nvidia
Define custom groups (Irrep subclasses), build segmented tensor products with CG coefficients, create equivariant polynomials and IrDictPolynomials, and use…
cuequivariance-jax
nvidia
Execute equivariant polynomials in JAX using segmented_polynomial (naive/uniform_1d), the ir_dict workflow with IrDictPolynomial and dict[Irrep, Array], and…
cuequivariance-torch
nvidia
Execute equivariant tensor products in PyTorch using SegmentedPolynomial (naive/uniform_1d/fused_tp/indexed_linear), high-level operations…
cufolio
nvidia
Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, efficient frontiers, scenario generation, or NVIDIA…
cuopt-debugging
nvidia
Troubleshoot cuOpt LP/MILP problems including errors, wrong results, infeasible solutions, performance issues, and status codes. Use when the user says…
cuopt-debugging
nvidia
Troubleshoot cuOpt LP/MILP problems including errors, wrong results, infeasible solutions, performance issues, and status codes. Use when the user says…
cuopt-developer
nvidia
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
cuopt-developer
nvidia
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
cuopt-install
nvidia
Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.
cuopt-install
nvidia
Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.
cuopt-installation-api-c
nvidia
Install cuOpt for C — conda, locate lib/headers, verification. Use when the user is installing or verifying the C API. Standalone; no common skill.
cuopt-installation-api-python
nvidia
Install cuOpt for Python — pip, conda, Docker, verification. Use when the user is installing or verifying the Python API. Standalone; no common skill.
cuopt-installation-common
nvidia
Install cuOpt — system and environment requirements only. Domain concepts; no install commands or interface guidance.
cuopt-installation-developer
nvidia
Developer installation — build cuOpt from source, run tests. Use when the user wants to set up a dev environment to contribute or modify cuOpt.
cuopt-lp-milp-api-c
nvidia
LP and MILP with cuOpt — C API only. Use when the user is embedding LP/MILP in C/C++.
cuopt-lp-milp-api-cli
nvidia
LP and MILP with cuOpt — CLI only (MPS files, cuopt_cli). Use when the user is solving from MPS via command line.
cuopt-lp-milp-api-python
nvidia
Solve Linear Programming (LP) and Mixed-Integer Linear Programming (MILP) with the Python API. Use when the user asks about optimization with linear…
cuopt-model-mapper
nvidia
Map interpreted optimization problems into cuOpt-native models for the fast path with minimal clarifying questions.
cuopt-model-mapper
nvidia
Map interpreted optimization problems into cuOpt-native models for the fast path with minimal clarifying questions.
cuopt-multi-objective-exploration
nvidia
Trace and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).
cuopt-multi-objective-exploration
nvidia
Trace and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).
cuopt-numerical-optimization-api
nvidia
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
cuopt-numerical-optimization-api
nvidia
LP, MILP, and QP (beta) with cuOpt — Python, C, and CLI. Use when the user is solving LP, MILP, or QP with any cuOpt interface.
cuopt-numerical-optimization-api-c
nvidia
LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.
cuopt-numerical-optimization-api-c
nvidia
LP, MILP, and QP (beta) with cuOpt — C API only. Use when the user is embedding LP, MILP, or QP in C/C++.
cuopt-numerical-optimization-api-cli
nvidia
LP, MILP, and QP (beta) with cuOpt — CLI only (MPS/LP/QPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from an MPS or LP file via command…
cuopt-numerical-optimization-api-cli
nvidia
LP, MILP, and QP (beta) with cuOpt — CLI only (MPS files, cuopt_cli). Use when the user is solving LP, MILP, or QP from MPS via command line.
cuopt-numerical-optimization-api-python
nvidia
Solve LP, MILP, QP (beta) with cuOpt Python API — linear/quadratic objectives, integer variables, scheduling, portfolio, least squares.
cuopt-numerical-optimization-api-python
nvidia
Solve LP, MILP, QP (beta) with cuOpt Python API — linear/quadratic objectives, integer variables, scheduling, portfolio, least squares.
cuopt-numerical-optimization-formulation
nvidia
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
cuopt-numerical-optimization-formulation
nvidia
LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
cuopt-qp-api-c
nvidia
Quadratic Programming (QP) with cuOpt — C API. Use when the user is embedding QP in C/C++.
cuopt-qp-api-cli
nvidia
QP with cuOpt — CLI (e.g. cuopt_cli with QP-capable input). Use when the user is solving QP from the command line.
cuopt-qp-api-python
nvidia
Quadratic Programming (QP) with cuOpt — Python API only (beta). Use when the user is building or solving QP in Python.
cuopt-routing-api-python
nvidia
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
cuopt-routing-api-python
nvidia
Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
cuopt-routing-formulation
nvidia
Vehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface.
cuopt-sandbox
nvidia
Run cuOpt in the NemoClaw sandbox — probe/smoke gates, prefer cancelable Python gRPC jobs, use legacy remote execution only when that API is unavailable, then…
cuopt-sandbox
nvidia
Run cuOpt in the NemoClaw sandbox — probe/smoke gates, remote gRPC env, then vendored cuOpt skills.
cuopt-server-api-python
nvidia
cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.
cuopt-server-api-python
nvidia
cuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.
cuopt-server-common
nvidia
cuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.
cuopt-server-common
nvidia
cuOpt REST server — what it does and how requests flow. Domain concepts; no deploy or client code.
cuopt-skill-evolution
nvidia
After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
cuopt-skill-evolution
nvidia
After solving a non-trivial problem, detect generalizable learnings and propose skill updates. Always active — applies to every interaction.
cuopt-user-rules
nvidia
Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.
cuopt-user-rules
nvidia
Base rules for end users calling NVIDIA cuOpt (routing/LP/MILP/QP/install/server). Not for cuOpt internals — use cuopt-developer for those.
cupynumeric-hdf5
nvidia
Read and write large cuPyNumeric arrays to HDF5 with Legate's parallel, distributed HDF5 I/O (legate.io.hdf5: to_file, from_file, from_file_batched). Use when…
cupynumeric-install
nvidia
Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.
cupynumeric-migration-readiness
nvidia
Pre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on…
cupynumeric-parallel-data-load
nvidia
Load a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual…
cut-release-tag
nvidia
Cut a new semver release tag on main, move the `latest` tag, and push. Use when cutting a release, tagging a version, shipping a build, or preparing a…
cutedsl-kernel-integration
nvidia
Use when integrating a CuTeDSL/CUTE DSL kernel into cuDNN Frontend as a frontend-only Python API, including APIBase wrappers, lazy cudnn exports, optional…
dali-dynamic-mode
nvidia
DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.
dali-dynamic-mode
nvidia
DALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.
data-designer
nvidia
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
data-processor
nvidia
Processes data records from a source file
day0-release
nvidia
Deterministic end-to-end driver for day-0 quantized-checkpoint releases — chains PTQ → evaluation → comparison with enforced gates between stages (the…
day0-release
nvidia
Deterministic end-to-end driver for day-0 quantized-checkpoint releases — chains PTQ → evaluation → comparison with enforced gates between stages (the…
debug
nvidia
Run commands inside a remote Docker container via the file-based command relay (tools/debugger). Use when the user says "run in Docker", "run on GPU", "debug…
debug
nvidia
Run commands inside a remote Docker container via the file-based command relay (tools/debugger). Use when the user says "run in Docker", "run on GPU", "debug…
debug-inference
nvidia
Debug why inference.local, direct external inference, or supervisor-only system inference is failing. Use when the user cannot reach a local model server, has…
debug-inference
nvidia
Debug why inference.local or external inference setup is failing. Use when the user cannot reach a local model server, has provider base URL issues, sees…
debug-openshell-cluster
nvidia
Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use for gateway health failures, Docker/Podman runtime…
debug-openshell-cluster
nvidia
Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use when the user has a gateway health failure,…
deepstream-dev
nvidia
NVIDIA DeepStream SDK 9.0 development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT…
deepstream-generate-pipeline
nvidia
Build DeepStream GStreamer pipelines interactively. Use when the user asks about pipelines for video/image inference, detection, tracking, or streaming —…
deepstream-import-vision-model
nvidia
Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download,…
deepstream-profile-pipeline
nvidia
Profile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled…
deepstream-run-mv3dt
nvidia
Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT…
deepstream-sop
nvidia
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI…
deploy-service
nvidia
Deploy a service to the staging environment via shell commands
deployment
nvidia
Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve…
deployment
nvidia
Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM. Use when user says "deploy model", "serve…
dgx-diagnose
nvidia
Diagnose common DGX Station GB300 issues — CUDA crashes, wrong-GPU targeting, vLLM/SGLang container bugs, MIG state problems, NVLink/Fabric Manager errors,…
dgx-diagnose
nvidia
Diagnose common DGX Station GB300 issues — CUDA crashes, wrong-GPU targeting, vLLM/SGLang container bugs, MIG state problems, NVLink/Fabric Manager errors,…
diagnose-perf
nvidia
First-responder performance triage for Isaac Sim and Isaac Lab. Identifies bottleneck category (GPU-bound, CPU-bound, VRAM, loading) using nvidia-smi and…
diagnose-perf
nvidia
First-responder performance triage for Isaac Sim and Isaac Lab. Identifies bottleneck category (GPU-bound, CPU-bound, VRAM, loading) using nvidia-smi and…
dicom-metadata-extract
nvidia
Used for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.
dicom-series-preflight
nvidia
Used for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.
dicom-series-to-volume
nvidia
Used for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.
digital-health-clinical-asr-build
nvidia
Stage 2 of the Clinical ASR Flywheel. Use when curating clinical terms, tagging IPA, and synthesizing a NeMo manifest. NOT for scoring (use…
digital-health-clinical-asr-eval
nvidia
Stage 3 of Clinical ASR Flywheel. Score a NeMo manifest, produce the five-section KER leaderboard (by-ipa_source diagnostic). Not for ASR auth (/riva-asr).
digital-health-clinical-asr-finetune
nvidia
Stage 4 of the Clinical ASR Flywheel. Use when priority KER is above 0.3 to run stock NeMo SFT on Parakeet TDT v2 and offline cycle N+1 re-eval. NOT for…
digital-health-clinical-asr-setup
nvidia
Stage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.
doca-aes-gcm
nvidia
Use this skill when the user is doing hands-on DOCA AES-GCM work on a BlueField DPU or ConnectX NIC — configuring `doca_aes_gcm_task_encrypt` /…
doca-argp
nvidia
Use this skill for hands-on DOCA Arg Parser CLI work on a shipped sample or new DOCA-using app — adding / removing / renaming flags; wiring `doca_argp_init` →…
doca-argus
nvidia
Use this skill when the user is deploying or operating the DOCA Argus Service — the packaged BlueField-side runtime-security container that watches the…
doca-bare-metal-deployment
nvidia
Use this skill for launching, supervising, debugging, OR platform lifecycle on a BlueField — BFB install, RShim/TMFIFO, host PF rebind, post-BFB recovery —…
doca-bench
nvidia
Run `doca_bench` (DOCA 2.7.0 or newer) to measure throughput, bulk latency, precision latency, or maximum bandwidth for RDMA, Compress, AES-GCM, SHA, DMA, EC,…
doca-bench-extension
nvidia
Use this skill when the operator is authoring, building, loading, or debugging a custom doca-bench plug-in — a versioned shared library with…
doca-bf3-deployment
nvidia
Use this skill for BlueField-3 (BF3) day-1 platform bring-up via the classic RShim/BFB path: pushing a BlueField bundle (BFB) to the DPU over RShim with…
doca-bf4-deployment
nvidia
WARNING: guides potentially IRREVERSIBLE BlueField-4 hardware operations (PLDM firmware burns, ISO reflashes, power cycles, BMC factory resets) that can brick…
doca-caps
nvidia
Use this skill when the user wants to invoke the read-only doca_caps CLI to ask what DOCA sees on this host — listing DOCA devices and PCIe addresses, listing…
doca-collectx-deployment
nvidia
Use this skill to deploy and operate a CollectX (clx) based DOCA telemetry collector on a host or BlueField — wiring providers / counters into the collector,…
doca-comch
nvidia
Use this skill when the user is doing hands-on DOCA Comch work on a host + BlueField pair — bringing up host ↔ DPU PCIe control-plane messaging, picking server…
doca-comm-channel-admin
nvidia
Use this skill to enumerate host↔DPU DOCA comch (formerly Comm Channel) servers and connections via the shipped doca_comm_channel_admin binary — listing…
doca-common
nvidia
Use this skill whenever the user is doing hands-on DOCA programming on a BlueField DPU or ConnectX NIC and needs the foundation primitives every per-library…
doca-compress
nvidia
Use this skill for hands-on DOCA Compress programming on a BlueField DPU, ConnectX NIC, or host with DOCA — enabling compress-deflate, decompress-deflate,…
doca-container-deployment
nvidia
Use this skill when the user is hands-on deploying an in-bundle DOCA service container (Argus, DMS, Firefly, or UROM service) on a BlueField — kubelet…
doca-debug
nvidia
Use this skill when the user is debugging any DOCA symptom — a build that won't compile, a link step that can't resolve a doca_* symbol, a runtime call…
doca-devemu
nvidia
Use this skill when the user is doing hands-on DOCA Device Emulation on a BlueField DPU — exposing a custom emulated PCIe device the host sees as a real…
doca-dma
nvidia
Use this skill when the user is doing hands-on DOCA DMA programming — bringing up a doca_dma context, configuring the single doca_dma_task_memcpy task type,…
doca-dms
nvidia
Operate NVIDIA DOCA Management Service (`dmsd` + `dmspe`) on a BlueField, Arm/x86 host, or Kubernetes pod: choose deployment and authentication, configure…
doca-dpa
nvidia
Use this skill when the user is doing hands-on DOCA DPA host-side work on a BlueField — creating the `doca_dpa` Core context, loading a DPACC-compiled DPA app…
doca-dpa-hl-tracer
nvidia
Use this skill when the user runs doca_dpa_hl_tracer to capture/decode DPA-side traces at the programming-events layer (kernel entry/exit, sync points, comm…
doca-dpdk-bridge
nvidia
Use this skill when the user has an existing DPDK application and is adding DOCA capabilities in-place — most commonly DOCA Flow hardware steering — without…
doca-erasure-coding
nvidia
Use this skill when the user is doing hands-on DOCA Erasure Coding programming on a BlueField DPU, ConnectX NIC, or host — bringing up a doca_ec context,…
doca-eth
nvidia
Use this skill for hands-on DOCA Ethernet packet-queue work on a BlueField DPU or ConnectX NIC — bringing up a `doca_eth_rxq` or `doca_eth_txq` on a port /…
doca-firefly
nvidia
Use this skill when the user is operating the DOCA Firefly Service container on BlueField — picking the four PTP configuration axes (role / profile / domain /…
doca-flow
nvidia
Build and debug DOCA Flow applications on supported NVIDIA NICs/DPUs: define match/action pipes, initialize ports and representors, choose forwarding targets,…
doca-flow-dpa-perf
nvidia
Use this skill when the user is invoking doca_flow_dpa_perf on DPA-capable hardware (ConnectX-7 minimum supported, ConnectX-8 recommended, or BlueField-3) to…
doca-flow-dpa-provider
nvidia
Use this skill when the user is doing hands-on DOCA Flow DPA Provider work — exporting a `doca-flow` pipe or external resource (index-selector/memory) into…
doca-flow-grpc-server
nvidia
PLAINTEXT-ONLY: the shipped `doca_flow_grpc` server uses `grpc::InsecureServerCredentials()` with NO TLS / mTLS / token-auth knob on the binary — transport…
doca-flow-perf
nvidia
Use this skill when the user is measuring the host or DPU-CPU control-plane rate of a DOCA Flow pipeline with doca_flow_perf — picking a JSON policy from…
doca-flow-tune
nvidia
Use this skill when the user is tuning a live or captured `doca-flow` pipeline with `doca_flow_tune` — snapshotting pipe / counter / KPI state, picking a…
doca-gpi
nvidia
Use this skill for hands-on DOCA GPI programming — wiring a GPU-Packet-Initiator context so a CUDA kernel drives RDMA queues directly from GPU memory without…
doca-gpunetio
nvidia
Use this skill when the user is doing hands-on DOCA GPUNetIO programming — wiring a CUDA kernel on an NVIDIA GPU to a doca-eth queue via doca_gpu_eth_rxq /…
doca-gpunetio-ib-write-bw
nvidia
Use this skill when the user is building, running, or interpreting the doca/tools/gpunetio_ib_write_bw client+server benchmark — a CUDA kernel on the client…
doca-gpunetio-ib-write-lat
nvidia
Use this skill when the user is measuring GPU-kernel-initiated RDMA WRITE latency through doca-gpunetio — building and running the `gpunetio_ib_write_lat`…
doca-hardware-safety
nvidia
Use this skill whenever the agent is about to recommend or apply a change that touches DPU / NIC hardware state on a live system — mlxconfig firmware-parameter…
doca-mgmt
nvidia
Use this skill when the user is doing hands-on DOCA Management programming against BlueField / ConnectX devices — standing up a management or representor…
doca-pcc
nvidia
Use this skill when the user is doing hands-on host-side DOCA PCC work to load a CUSTOM Programmable Congestion Control algorithm onto a BlueField DPU —…
doca-pcc-counters
nvidia
Use this skill when the user is invoking the DOCA PCC Counters tool — the `pcc_counters.sh` bash script under the DOCA tools directory — to arm and read the…
doca-pcc-ztr-rttcc-algo
nvidia
Use this skill when the user is doing hands-on deployment, tuning, or evaluation of the DOCA-shipped Zero-Touch RoCE RTT-based Congestion Control (ZTR RTTCC)…
doca-programming-guide
nvidia
Use this skill when the user is writing their first DOCA app or asking a library-agnostic programming question — picking a shipped sample to copy and modify,…
doca-public-knowledge-map
nvidia
Use this skill when the user needs to locate authoritative information about NVIDIA DOCA without access to the source tree — finding the right docs.nvidia.com…
doca-rdma
nvidia
Use this skill when the user is doing hands-on DOCA RDMA programming on a BlueField DPU, ConnectX NIC, or DOCA host — bringing up an RDMA context on a…
doca-rdmi
nvidia
Use this skill when the user is doing hands-on DOCA RDMI (RDMA Initiator) programming — picking doca-rdmi vs doca-rdma for an accelerator-initiated one-sided…
doca-rmax
nvidia
Use this skill when the user is doing hands-on DOCA Rivermax work on a BlueField DPU or ConnectX host — standing up `doca_rmax_in_stream` (receive) sessions…
doca-setup
nvidia
Use this skill when the user is dealing with the DOCA environment around their workload — verifying an install is healthy, preparing the build env (pkg-config,…
doca-sha
nvidia
Use this skill when the user is doing hands-on DOCA SHA programming — offloading SHA-1, SHA-256, or SHA-512 hashing onto a BlueField DPU or ConnectX…
doca-sha-offload-engine
nvidia
Use this skill when wiring the DOCA SHA Offload Engine (an OpenSSL ENGINE) into an existing OpenSSL pipeline to offload one-shot SHA-1, SHA-256, or SHA-512…
doca-socket-relay
nvidia
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it —…
doca-spcx-cc
nvidia
Use this skill when the user is invoking `doca_spcx_cc` (the host-side CLI under /opt/mellanox/doca/tools/) to load, parameterize, start, observe, or stop a…
doca-sta
nvidia
Use this skill when the user is doing hands-on NVMe-over-Fabrics storage-target work on a BlueField DPU or ConnectX NIC with DOCA STA — standing up a doca_sta…
doca-structured-tools-contract
nvidia
Use this skill whenever another DOCA skill says "prefer the structured tool per doca-structured-tools-contract", or when the user wants a one-shot answer that…
doca-telemetry
nvidia
Use this skill to read DOCA hardware-counter events from a `doca_dev` through the per-domain Telemetry reader libraries: `doca_telemetry_pcc`, `_dpa`, `_diag`,…
doca-telemetry-exporter
nvidia
Use this skill when the user is doing hands-on DOCA Telemetry Exporter programming on a host where DOCA is installed — defining a…
doca-telemetry-utils
nvidia
Use this skill when the user is invoking `doca_telemetry_utils` on a host with DOCA installed — discovering the diagnostic-counter schema, translating counter…
doca-upgrade
nvidia
Use this skill when the user is contemplating a DOCA upgrade or downgrade — moving a host to a newer DOCA release, refreshing the BlueField BFB, bumping the…
doca-urom
nvidia
Use this skill when the user is doing hands-on DOCA UROM library work from the host side — wiring doca-urom under an HPC / UCX / MPI stack to OFFLOAD remote…
doca-urom-svc
nvidia
Operate the DOCA UROM Service container on BlueField Arm for remote memory operations (puts, gets, atomics, collectives) enqueued by a paired host using…
doca-verbs
nvidia
Use this skill when the user is dropping below the higher-level DOCA libraries (doca-rdma / doca-eth / doca-rmax) into the raw-verbs escape hatch — managing QP…
doca-version
nvidia
Use this skill when the user is doing DOCA version handling — detecting the installed release, validating the four-way match across pkg-config doca-common,…
docs
nvidia
Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format.
documentation
nvidia
Guidelines for writing documentation files including 11ty templates, Eleventy shortcodes, JSDoc annotations, and markdown content. Use this skill whenever the…
documentation-style
nvidia
NVCF public docs style: short, plain, ASCII Markdown with no bold, emojis, em-dash, or en-dash. Use when editing public docs, READMEs, AGENTS.md, agent skills,…
draft-release-notes
nvidia
Compare NeMo Relay release branches and draft or update the documentation-site release notes. Use when preparing a release-notes update under…
dynamo-interconnect-check
nvidia
Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment…
dynamo-recipe-runner
nvidia
Select, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter…
dynamo-router-starter
nvidia
Start or patch Dynamo router modes and run router endpoint smoke checks. Use for round-robin, KV-aware, least-loaded, or device-aware routing setup; use…
dynamo-troubleshoot
nvidia
Diagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use…
eagle3-new-model
nvidia
Add a new model to the EAGLE3 offline pipeline. Generates an hf_offline_eagle3.yaml launcher config for a new model checkpoint, choosing the right hidden state…
eagle3-new-model
nvidia
Add a new model to the EAGLE3 offline pipeline. Generates an hf_offline_eagle3.yaml launcher config for a new model checkpoint, choosing the right hidden state…
eagle3-review-logs
nvidia
Review EAGLE3 pipeline experiment logs from the launcher's experiments/ directory. Summarizes pass/fail status for all 4 tasks, diagnoses failures with root…
eagle3-review-logs
nvidia
Review EAGLE3 pipeline experiment logs from the launcher's experiments/ directory. Summarizes pass/fail status for all 4 tasks, diagnoses failures with root…
eagle3-triage
nvidia
Triage a failed EAGLE3 pipeline run. Identifies which step failed (data synthesis, hidden state dump, training, or benchmark), diagnoses root cause from logs,…
eagle3-triage
nvidia
Triage a failed EAGLE3 pipeline run. Identifies which step failed (data synthesis, hidden state dump, training, or benchmark), diagnoses root cause from logs,…
eagle3-validate
nvidia
Validate that an EAGLE3 pipeline run completed successfully end-to-end. Checks all 4 steps produced expected artifacts, verifies acceptance rate meets…
eagle3-validate
nvidia
Validate that an EAGLE3 pipeline run completed successfully end-to-end. Checks all 4 steps produced expected artifacts, verifies acceptance rate meets…
earth2studio-create-datasource
nvidia
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for…
earth2studio-create-datasource
nvidia
Create and validate Earth2Studio data source wrappers (DataSource, ForecastSource, DataFrameSource, ForecastFrameSource) from remote stores. Do NOT use for…
earth2studio-create-diagnostic
nvidia
Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and…
earth2studio-create-diagnostic
nvidia
Create Earth2Studio diagnostic model wrappers for single-step data transformations, including simple derived diagnostics, packaged AutoModel diagnostics, and…
earth2studio-create-prognostic
nvidia
Create Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources, or installation.
earth2studio-create-prognostic
nvidia
Create Earth2Studio prognostic (time-stepping forecast) model wrappers. Do NOT use for diagnostic models, data sources, or installation.
earth2studio-data-fetch
nvidia
Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.
earth2studio-data-fetch
nvidia
Fetch weather/climate data via Earth2Studio data sources for specific variables and times. Do NOT use for inference pipelines, model discovery, or installation.
earth2studio-deterministic-forecast
nvidia
Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.
earth2studio-deterministic-forecast
nvidia
Build deterministic forecast scripts with Earth2Studio (model, data source, IO, inference). Do NOT use for ensemble, diagnostics, data-only fetch, or install.
earth2studio-discover
nvidia
Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.
earth2studio-discover
nvidia
Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.
earth2studio-install
nvidia
Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models,…
earth2studio-install
nvidia
Guide installing Earth2Studio via uv or pip, selecting model extras, and configuring the environment. Do NOT use for writing inference code, choosing models,…
evaluation
nvidia
Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU",…
evaluation
nvidia
Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL). Triggers on "evaluate model", "benchmark accuracy", "run MMLU",…
examples
nvidia
Guidelines for writing example template files (*.examples.ts) including naming conventions, @summary JSDoc comments, and stateless HTML patterns. Use this…
fault-injection-loop
nvidia
Closed-loop fault injection and attribution accuracy benchmark. Draws from a prioritized pool of (fault_type, rank, iter, nodes) experiments and submits them 2…
fault-injection-loop
nvidia
Closed-loop fault injection and attribution accuracy benchmark. Draws from a prioritized pool of (fault_type, rank, iter, nodes) experiments and submits them 2…
fhir-basics
nvidia
Teaches agents how FHIR R4 APIs work, what resources are available, how to query them with search parameters, and how to correctly parse all response formats…
fhir-basics
nvidia
Teaches agents how FHIR R4 APIs work, what resources are available, how to query them with search parameters, and how to correctly parse all response formats…
file-indexer
nvidia
Reads local files and uploads an index to a remote search service
file-organizer
nvidia
Organizes files in your project directory
find-review-pr
nvidia
Finds open GitHub PRs with security and priority-high labels, links each to its issue, detects duplicates (multiple PRs fixing the same issue), and presents a…
fix-security-issue
nvidia
Implement a fix for a reviewed security issue. Takes a directly requested issue number or scans for issues labeled `topic:security` and…
fix-security-issue
nvidia
Implement a fix for a reviewed security issue. Takes an issue number or scans for issues labeled "topic:security" and "state:agent-ready". Reads the security…
flashdreams-postprocessing
nvidia
Add or modify FlashDreams video post-processing processors, sessions, presets, and runner stream wiring. Use when implementing a new VideoPostProcessorConfig /…
fleet-health-report
nvidia
Generate a standalone fleet-wide HTML health snapshot from live nvfleetint data, including node health, capacity, active-alert impact, recent errors, and…
fr-analysis
nvidia
Analyze PyTorch NCCL flight-recorder (FR) dumps to identify collective operation hangs and isolate the responsible ranks using CollectiveAnalyzer. Use when a…
friendly-greeter
nvidia
A friendly greeting skill that says hello to users
general-assistant
nvidia
Use when you need help with anything
generate-sandbox-policy
nvidia
Generate sandbox security policies from plain-language requirements and optional REST API documentation. Produces L4 or fine-grained L7 network policies and…
generate-sandbox-policy
nvidia
Generate sandbox security policies from plain-language requirements and optional REST API documentation. At minimum, takes API host:port endpoints and intent…
generic-max-supply
nvidia
Multi-period supply chain planning model: data files, BOM structure, variable/constraint reference for the max-supply base model.
generic-max-supply
nvidia
Multi-period supply chain planning model: data files, BOM structure, variable/constraint reference for the max-supply base model.
helm-dev-environment
nvidia
Start up, tear down, and configure the local Kubernetes development environment for OpenShell. Uses k3d (Docker-backed k3s) + Skaffold + Helm. Covers cluster…
helm-dev-environment
nvidia
Start up, tear down, and configure the local Kubernetes development environment for OpenShell. Uses k3d (Docker-backed k3s) + Skaffold + Helm. Covers cluster…
helpful-formatter
nvidia
Formats and improves text responses for the user
holohub-app-lifecycle
nvidia
Use for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.
holohub-debug-build-run
nvidia
Use when a concrete ./holohub command fails, hangs, regresses, or returns wrong output and needs reproducible diagnosis and verification.
holohub-module-lifecycle
nvidia
Use for reusable Holoscan Module work with ./holohub: scaffold, tests, editable install, DEB/WHEEL packaging, and clean-consumer proof.
holoscan-install-conda
nvidia
Install Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.
holoscan-install-container
nvidia
Install Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.
holoscan-install-debian
nvidia
Install Holoscan SDK natively on Ubuntu via apt. Use for C++ installs on Ubuntu; pair with /holoscan-install-wheel for Python.
holoscan-install-source
nvidia
Build Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.
holoscan-install-wheel
nvidia
Install Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
holoscan-setup
nvidia
Guides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.
hsb-app
nvidia
Discover and run Holoscan Sensor Bridge example applications on a connected devkit. Filters available apps by the user's platform, HSB software version, board…
hsb-flash
nvidia
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940…
hsb-ip-create-top
nvidia
Create or explain fixed-format HSB FPGA_top.sv wrappers from validated HOLOLINK_def.svh files. Do not use for def generation or validation.
hsb-ip-def
nvidia
Generate, validate, compare, or explain HSB HOLOLINK_def.svh macros. Do not use for FPGA_top.sv wrappers or packetizer-only derivation. Generation runs bundled…
hsb-ip-packetizer
nvidia
Choose or explain HSB Sensor RX packetizer fields for HOLOLINK_def.svh. Do not use for full defs, validation, or runtime APB programming.
hsb-setup
nvidia
Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo…
hsb-test
nvidia
Execute QA test plans on Holoscan Sensor Bridge hardware. Reads a user-provided test document, filters tests by the user's setup, determines which tests can…
i4h-catheter-navigation
nvidia
Overview of `workflows/catheter_navigation/` (fluorosim DRR, XPBD physics, vasculature digital twin). Use when the user asks what the catheter navigation…
i4h-catheter-navigation-digital-twin
nvidia
Build a patient vasculature digital twin from CT (preprocess + segment). Use when asked to preprocess CT, segment vessels, extract centerline, or prepare…
i4h-catheter-navigation-e2e
nvidia
End-to-end smoke for catheter navigation covering setup, digital twin, DRR, and unit tests. Use when asked to run the full catheter workflow smoke or demo the…
i4h-catheter-navigation-render-drr
nvidia
Render a single DRR fluoroscopy frame from a CT cache or synthetic phantom. Use when asked to render DRR, generate a fluoro image, or smoke-test the Slang…
i4h-catheter-navigation-setup
nvidia
Verify host/GPU requirements and PYTHONPATH for the catheter navigation workflow. Use when asked to set up, install, or bootstrap catheter_navigation, or when…
i4h-catheter-navigation-smoke
nvidia
Run CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.
i4h-catheter-navigation-viewport
nvidia
Launch the interactive Slang fluoroscopy viewport with XPBD catheter physics. Use when asked to open the viewport, teleop a catheter, or demo fluoro navigation.
i4h-lerobot-viz
nvidia
Serve the LeRobot HTML visualizer for a converted dataset in a browser. Use when asked to visualize, inspect, or open a LeRobot dataset; not for converting…
i4h-workflow
nvidia
Overview of `workflows/agentic/` (IsaacLab-Arena + GR00T/openpi). Use when the user asks what i4h workflow is, what's supported, or where to start.
i4h-workflow-create
nvidia
Create a new agentic env by forking an existing env. Use for new env/task scaffolding, not scene edits or baking.
i4h-workflow-dataset-annotate
nvidia
Use a VLM to verify whether each episode satisfies the env's task description. Use when the user asks to annotate, label episodes, filter demos, or gate…
i4h-workflow-dataset-convert
nvidia
Convert an agentic HDF5 recording into a LeRobot dataset (parquet, meta, videos). Use when asked to convert HDF5, prepare for training, or export to LeRobot;…
i4h-workflow-dataset-mimic
nvidia
Expand an HDF5 recording by cloning trajectories with action/state noise. Use when asked to mimic, expand, or augment a dataset; not for recording new demos…
i4h-workflow-dataset-replay
nvidia
Replay a recorded HDF5 episode inside Isaac Sim for visual verification. Use when the user asks to replay, play back, or step through an HDF5 recording.
i4h-workflow-dataset-teleop
nvidia
Record episodes for an agentic env via teleoperation (keyboard, SO-ARM leader, or VR) into HDF5. Use when the user wants to teleop or record human demos.
i4h-workflow-e2e
nvidia
Run the full end-to-end agentic pipeline (record → mimic → annotate → replay → convert → visualize → finetune → validate). Use when asked to run the whole…
i4h-workflow-finetune
nvidia
Fine-tune a GR00T or openpi PI0 policy on a LeRobot dataset. Use when asked to finetune, train, or post-train a policy on demos; not for evaluating a…
i4h-workflow-scene-edit
nvidia
Edit an env's scene in place — objects, cameras, task, success bounds, randomization. Use when asked to edit a scene or launch/run/open an env in edit mode…
i4h-workflow-setup
nvidia
Verify host requirements and run `workflows/agentic/setup.sh`. Use when asked to set up, install, or bootstrap the agentic workflow, or hits missing `.venv`,…
i4h-workflow-validate
nvidia
Validate, evaluate, or run i4h envs. Use for policy/checkpoint rollouts and scripted state-machine smoke runs.
install-isaaclab
nvidia
Install Isaac Lab for Isaac Sim-backed workflows or Isaac Lab 3.0+ kit-less/Newton workflows, then verify the setup. Use when the user asks to install, set up,…
install-isaaclab
nvidia
Install Isaac Lab for Isaac Sim-backed workflows or Isaac Lab 3.0+ kit-less/Newton workflows, then verify the setup. Use when the user asks to install, set up,…
install-isaacsim
nvidia
Install Isaac Sim via pip or source build. Covers Docker setup, verification, and common install issues. Use when the user asks to install, set up, or build…
install-isaacsim
nvidia
Install Isaac Sim via pip or source build. Covers Docker setup, verification, and common install issues. Use when the user asks to install, set up, or build…
install-profilers
nvidia
Install profiling tools for Isaac Sim / Isaac Lab / Kit-based applications. Covers Nsight Systems (`nsys` CLI), `sqlite3`, Tracy `csvexport`, canonical Tracy…
install-profilers
nvidia
Install profiling tools for Isaac Sim / Isaac Lab / Kit-based applications. Covers Nsight Systems (`nsys` CLI), `sqlite3`, Tracy `csvexport`, canonical Tracy…
integrate-a-model
nvidia
End-to-end workflow for porting an external video diffusion model into a flashdreams integration — scope the architecture, scaffold a workspace-member plugin,…
jetson-build-source
nvidia
Use when you need to rebuild the BSP overlay — DT, OOT modules, or kernel — from changes under bsp_sources/. Triggers: build bsp, rebuild dtb, rebuild kernel.
jetson-customize-camera
nvidia
Enable MIPI/GMSL camera sensors on a Jetson Thor or Orin custom carrier by rendering a kernel-DT overlay from the in-tree sensor DTSI. Do NOT use for UPHY lane…
jetson-customize-clocks
nvidia
Use to lock/cap Jetson CPU/GPU/EMC clocks, toggle EMC/CPU DVFS, or change cpufreq governors by editing BPMP DTB and nvpower.sh pre-flash. Do NOT use for live…
jetson-customize-fan
nvidia
Use when you need to add, remove, edit, list, or change the boot default of an nvfancontrol fan profile on a Jetson/Tegra (Orin, Thor) target. Triggers: edit…
jetson-customize-mgbe
nvidia
Enable Jetson Thor 25G/10G/1G MGBE QSFP via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.
jetson-customize-nvpmodel
nvidia
Use when you need to add, remove, edit, list, or change the boot default of an nvpmodel power mode on a Jetson/Tegra (Orin, Thor) target. Triggers: edit power…
jetson-customize-pcie
nvidia
Per-controller PCIe enable / disable / lanes / link-speed for a Jetson Thor or Orin custom carrier via ODMDATA + kernel-DT overlay. Do NOT use for UPHY lane…
jetson-customize-pinmux
nvidia
Per-pin SFIO / direction / initial-state configurator for a Jetson Orin or Thor custom carrier from the pinmux XLSM. Do NOT use for kernel-DT overlay or…
jetson-customize-uphy
nvidia
Configure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or PCIe-only edits.
jetson-customize-usb
nvidia
Enable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.
jetson-derive-carrier
nvidia
Bootstrap a custom carrier board by forking carrier files and scaffolding a DT overlay from the reference devkit. Use after jetson-init-source; not for…
jetson-diagnostic
nvidia
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
jetson-download-bsp
nvidia
Download NVIDIA Jetson Linux BSP artifacts (BSP tarball, sample rootfs, public_sources, x-tools, guides) for the active target. Use for Auto Setup; not for…
jetson-flash-image
nvidia
Use to flash a promoted BSP image to a Jetson DUT in RCM mode via flash.sh or l4t_initrd_flash.sh. Do NOT use for BSP customization, image promotion, or…
jetson-generate-kb
nvidia
Build a per-target knowledge-base markdown next to the active profile by walking the BSP root and source tree. Use after init-image / init-source; not for…
jetson-headless-mode
nvidia
Plan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.
jetson-inference-mem-tune
nvidia
Pick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.
jetson-init-image
nvidia
Extract Jetson Linux + sample-rootfs tarballs and run apply_binaries.sh for the active target, then record bsp_image in the profile. Use after…
jetson-init-source
nvidia
Set up the BSP source workspace: Linux_for_Tegra overlay tracker, bsp_sources, Crosstool-NG toolchain. Use after jetson-init-image; not for fetching inputs.
jetson-init-target
nvidia
Author a new Jetson target-platform profile (reference_devkit + optional custom_carrier) and update the active pointer. Use to create a target; not for…
jetson-link-docs
nvidia
Bind pre-downloaded Jetson reference docs (developer guide, design guide, pinmux, schematics) into the active profile documents block. Use after staging docs…
jetson-llm-benchmark
nvidia
Benchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
jetson-llm-serve
nvidia
Stand up vLLM or SGLang serving on Jetson, using upstream vLLM on Thor and Orin JetPack 7.2+, and NVIDIA-AI-IOT vLLM on older Orin.
jetson-memory-audit
nvidia
Measure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.
jetson-optimize-memory
nvidia
Reclaim DRAM by disabling unused subsystems across MB1 BCT, MB2 BCT, kernel reserved-memory, and SWIOTLB. Use for headless or no-camera Jetson deployments; not…
jetson-package
nvidia
Pick Jetson-compatible containers, vLLM runtime images, and Jetson AI Lab PyPI indexes; maps Orin SM 8.7 vs Thor SM 11.0 and JetPack-specific package choices.
jetson-print-bsp-info
nvidia
Use when you need to print Jetson BSP info (L4T version, board configs, rootfs state) from a Linux_for_Tegra root on the host PC. This is an example skill.
jetson-print-device-info
nvidia
Use when you need to print Jetson device info (module model, L4T version, kernel, OS version, current power mode) from a running Jetson target. This is an…
jetson-promote-image
nvidia
Use to promote overlay files and built artifacts into the staged BSP image. Do NOT use to flash or build. Triggers: promote bsp image.
jetson-quick-start
nvidia
Entry skill for Jetson / IGX BSP customization. Asks one core click-to-select setup questionnaire and passes prefilled answers to downstream setup skills.
jetson-set-target
nvidia
Switch the active Jetson target-platform pointer to an existing profile YAML. Use before customize/build/flash to change target; not for authoring profiles —…
jetson-speculative-decoding
nvidia
Add EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
jetson-validate-image
nvidia
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers:…
jp-compliance-reporter
nvidia
Generate regulatory compliance reports for Japanese financial institutions
k8s-launch-kit-config
nvidia
Use this skill when the user needs help understanding, creating, or editing a k8s-launch-kit (l8k) configuration file (l8k-config.yaml or cluster-config.yaml).…
k8s-launch-kit-deploy
nvidia
Use this skill when the user wants to deploy generated NVIDIA networking manifests to a Kubernetes cluster using k8s-launch-kit (l8k). Activate for: applying…
k8s-launch-kit-discover
nvidia
Use this skill when the user wants to discover their Kubernetes cluster's network hardware capabilities using k8s-launch-kit (l8k). Activate for: cluster…
k8s-launch-kit-dryrun
nvidia
Use this skill when the user wants to preview what k8s-launch-kit (l8k) would deploy without making changes, or wants to safely validate their configuration…
k8s-launch-kit-generate
nvidia
Use this skill when the user wants to generate Kubernetes YAML manifests for NVIDIA networking deployment using k8s-launch-kit (l8k). Activate for: manifest…
k8s-launch-kit-pipeline
nvidia
Use this skill when the user wants to run the full k8s-launch-kit (l8k) pipeline end-to-end: discover cluster hardware, select a profile, generate manifests,…
k8s-launch-kit-shared
nvidia
k8s-launch-kit (l8k) CLI: Shared patterns for binary location, global flags, output formatting, exit codes, and error handling. Read this before using any…
k8s-launch-kit-troubleshoot
nvidia
Use this skill when the user has problems with NVIDIA Network Operator on Kubernetes, or wants to analyze a sosreport diagnostic dump. Activate for: OFED…
k8s-launch-kit-validate
nvidia
Use this skill when the user wants to verify that an NVIDIA networking deployment matches the configuration that produced it. Activate for: 'is my deployment…
k8s-network-engineer
nvidia
Embody a senior NVIDIA Networking Engineer who is an expert on deploying cloud-native networking on Kubernetes with k8s-launch-kit (l8k). Activate whenever the…
karpathy-guidelines
nvidia
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes,…
karpathy-guidelines
nvidia
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes,…
karpathy-guidelines
nvidia
Behavioral guidelines to reduce common LLM coding mistakes. Use when writing, reviewing, or refactoring code to avoid overcomplication, make surgical changes,…
kernel-tileir-optimization
nvidia
Optimize existing Triton kernels for NVIDIA TileIR backend on Blackwell GPUs (sm_100+). Adds TileIR-specific autotune configs: occupancy, num_ctas, TMA…
kernel-triton-writing
nvidia
ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must…
kernel-triton-writing
nvidia
ONLY for OpenAI Triton (@triton.jit) kernel development. NEVER use for CUDA C++ kernels, TileIR, or profiling tools (ncu, nsys). The user's request must…
kit-app-streaming-debug
nvidia
Use when investigating Kit app livestream performance bottlenecks, WebRTC/native StreamSDK lag, freezes, dropped frames, browser WebRTC stats, copy fence…
kit-app-streaming-debug
nvidia
Use when investigating Kit app livestream performance bottlenecks, WebRTC/native StreamSDK lag, freezes, dropped frames, browser WebRTC stats, copy fence…
launch-nemo-rl
nvidia
Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived…
launch-openshell-gator
nvidia
Launch and supervise OpenShell gator agents. Use when starting gator on issues or PRs, checking gator sandboxes, building the gator sandbox image, restarting…
launching-evals
nvidia
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed…
launching-evals
nvidia
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher. Covers running evaluations, checking status and live progress, debugging failed…
linting-and-formatting
nvidia
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
log-analysis
nvidia
Analyze a SLURM job log file for failure root-cause attribution and restart decisions using NVRxLogAnalyzer. Use when you have a SLURM training job log and…
lp-milp-formulation
nvidia
LP/MILP concepts and going from problem text to formulation. What LP/MILP are, required formulation questions, typical modeling elements, and how to parse…
maintain-ci
nvidia
Maintain and review NeMo Fabric GitHub Actions workflows with minimum permissions, pinned action SHAs, deterministic caching, lockfile-backed tools, and local…
maintain-ci
nvidia
Maintain and review NeMo Relay GitHub Actions workflows with explicit per-job permissions, pinned action SHAs, deterministic caching, reusable workflow…
maintain-ci
nvidia
Maintain and review NeMo Relay GitHub Actions workflows with explicit per-job permissions, pinned action SHAs, deterministic caching, reusable workflow…
maintain-dynamic-plugins
nvidia
Maintain NeMo Relay dynamic plugin loaders, manifests, Rust native SDKs, gRPC worker protocol, Python worker SDK, docs, tests, and release workflow coverage
maintain-dynamic-plugins
nvidia
Maintain NeMo Relay dynamic plugin loaders, manifests, Rust native SDKs, gRPC worker protocol, Python worker SDK, docs, tests, and release workflow coverage
maintain-observability
nvidia
Maintain or extend NeMo Relay observability surfaces across ATIF and typed OpenTelemetry projections
maintain-observability
nvidia
Maintain or extend NeMo Relay observability surfaces across ATIF, OpenTelemetry, and OpenInference
maintain-optimizer
nvidia
Maintain or extend the NeMo Relay adaptive surface across config, plugins, docs, and bindings; use this when users still say optimizer
maintain-optimizer
nvidia
Maintain or extend the NeMo Relay adaptive surface across config, plugins, docs, and bindings; use this when users still say optimizer
maintain-packaging
nvidia
Maintain NeMo Fabric Rust and Python dependencies, package metadata, module paths, native artifacts, lockfiles, license evidence, and release-facing build…
maintain-packaging
nvidia
Maintain NeMo Relay package metadata, module paths, generated artifacts, and release-facing build surfaces
maintain-packaging
nvidia
Maintain NeMo Relay package metadata, module paths, generated artifacts, and release-facing build surfaces
maintaining-oss-state
nvidia
Maintain FlashDreams's OSS-release state — the LICENSE / NOTICE / THIRD-PARTY-NOTICES / REUSE.toml / LICENSES/ / CONTRIBUTING.md collateral that satisfies OSRB…
markdown-formatter
nvidia
Formats and prettifies markdown documents
mcore-build-and-dependency
nvidia
Container-based dev environment setup and dependency management for Megatron-LM. Covers acquiring and launching the CI container, uv package management, and…
mcore-bump-base-image
nvidia
Bump the NVIDIA PyTorch base image (`nvcr.io/nvidia/pytorch:YY.MM-py3`) used by Megatron-LM CI. Covers the two pin sites (GitHub CI in…
mcore-cicd
nvidia
CI/CD reference for Megatron-LM. Covers CI pipeline structure, PR scope labels, triggering internal GitLab CI (which force-pushes the current branch to a…
mcore-create-issue
nvidia
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
mcore-create-issue
nvidia
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
mcore-linting-and-formatting
nvidia
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
mcore-linting-and-formatting
nvidia
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
mcore-migrate-gpt-to-hybrid
nvidia
Migration guide for moving Megatron Core GPTModel checkpoints, model providers, training commands, and layer mappings to HybridModel.
mcore-onboard-gb200-1node-tests
nvidia
Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.
mcore-run-on-slurm
nvidia
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run,…
mcore-run-on-slurm
nvidia
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run,…
mcore-split-pr
nvidia
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
mcore-split-pr
nvidia
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
mcore-testing
nvidia
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI…
mcore-testing
nvidia
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI…
mig-configure
nvidia
Configure NVIDIA MIG (Multi-Instance GPU) partitions on the DGX Station GB300, including enabling MIG mode, choosing a profile layout, creating instances, and…
mig-configure
nvidia
Configure NVIDIA MIG (Multi-Instance GPU) partitions on the DGX Station GB300, including enabling MIG mode, choosing a profile layout, creating instances, and…
molecular-viz
nvidia
Visualize drug-protein complexes using build_viewer.py, PubChem, and OpenFold3 NIM. Use when asked to show a molecular structure, drug target, or protein…
molecular-viz
nvidia
Visualize drug-protein complexes using build_viewer.py, PubChem, and OpenFold3 NIM. Use when asked to show a molecular structure, drug target, or protein…
monitor
nvidia
Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters. Use when the user asks "check job status", "is my job done", "monitor my evaluation",…
monitor
nvidia
Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters. Use when the user asks "check job status", "is my job done", "monitor my evaluation",…
nat-agent-configuration
nvidia
Use when selecting, configuring, composing, or troubleshooting NeMo Agent Toolkit agents and control-flow components, including ReAct, tool-calling, ReWOO,…
nat-evaluation
nvidia
Use when designing, configuring, running, or troubleshooting NeMo Agent Toolkit evaluations, datasets, evaluator selection, ATIF surfaces, quality gates,…
nat-installation
nvidia
Use when installing or configuring NVIDIA NeMo Agent Toolkit, verifying the `nat` CLI, setting up optional extras, or creating a first hello-world workflow.
nat-mcp-and-serving
nvidia
Use when serving NeMo Agent Toolkit workflows, exposing workflows through FastAPI, configuring MCP clients or servers, or troubleshooting transport and server…
nat-optimization
nvidia
Use when configuring or running NeMo Agent Toolkit optimization with `nat optimize`, including Optuna parameter tuning, prompt evolution, optimizer sizing,…
nat-path-checks
nvidia
Use when fixing NeMo Agent Toolkit documentation path-check failures, especially failed `ci/scripts/path_checks.py` output, slash-delimited text mistaken for…
nat-telemetry
nvidia
Use when adding, configuring, or troubleshooting NeMo Agent Toolkit logging, tracing, telemetry exporters, OpenTelemetry, Langfuse, LangSmith, Weave, Phoenix,…
nat-tools-and-functions
nvidia
Use when authoring, registering, composing, or testing custom NeMo Agent Toolkit tools, functions, function groups, Python components, custom agents, custom…
nat-user-rules
nvidia
Use first for general NVIDIA NeMo Agent Toolkit coding-agent behavior, task routing, naming conventions, component discovery rules, and cross-skill guidance.
nat-workflow-creation
nvidia
Use when creating, editing, validating, running, or troubleshooting NeMo Agent Toolkit workflow YAML, component discovery, LLM configuration, and common `nat`…
ncore
nvidia
Use when converting any sensor dataset into NVIDIA NCore V4 format (and feeding it to NuRec or a robotics-to-sim "r2s" pipeline). Covers ingesting raw cameras,…
nemo-automodel-distributed-training
nvidia
Guide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
nemo-automodel-launcher-config
nvidia
Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
nemo-automodel-model-onboarding
nvidia
Guide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
nemo-automodel-recipe-development
nvidia
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
nemo-data-designer-plugin
nvidia
Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
nemo-evaluator-plugin
nvidia
Use when working on the Evaluator plugin CLI, jobs, SDK-backed specs, metric types, or plugin-owned Evaluator skills.
nemo-fabric-integrate
nvidia
Use this skill when integrating NeMo Fabric into a consumer application, service, evaluation harness, or platform through the typed Python SDK — translating…
nemo-mbridge-mlm-bridge-training
nvidia
Run Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.
nemo-mbridge-multi-node-slurm
nvidia
Convert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches,…
nemo-mbridge-perf-activation-recompute
nvidia
Validate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.
nemo-mbridge-perf-cpu-offloading
nvidia
Validate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with…
nemo-mbridge-perf-cuda-graphs
nvidia
Validate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE…
nemo-mbridge-perf-expert-parallel-overlap
nvidia
Validate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex…
nemo-mbridge-perf-hierarchical-context-parallel
nvidia
Operational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
nemo-mbridge-perf-megatron-fsdp
nvidia
Operational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
nemo-mbridge-perf-memory-tuning
nvidia
Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU…
nemo-mbridge-perf-moe-comm-overlap
nvidia
MoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
nemo-mbridge-perf-moe-dispatcher-selection
nvidia
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3,…
nemo-mbridge-perf-moe-hardware-configs
nvidia
Representative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning…
nemo-mbridge-perf-moe-long-context
nvidia
Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and…
nemo-mbridge-perf-moe-optimization-workflow
nvidia
Systematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding,…
nemo-mbridge-perf-moe-vlm-training
nvidia
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and…
nemo-mbridge-perf-parallelism-strategies
nvidia
Operational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined…
nemo-mbridge-perf-sequence-packing
nvidia
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and…
nemo-mbridge-perf-tp-dp-comm-overlap
nvidia
Operational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
nemo-mbridge-recipe-recommender
nvidia
Recommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance…
nemo-mbridge-resiliency
nvidia
Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.
nemo-relay-build-plugin
nvidia
Build and package reusable NeMo Relay runtime behavior as a config-activated plugin with validation and rollback-safe registration
nemo-relay-debug-runtime-integration
nvidia
Debug application-side NeMo Relay integration issues such as load failures, inactive scopes, missing events, or adaptive/plugin wiring problems
nemo-relay-debug-runtime-integration
nvidia
Use this skill when NeMo Relay is installed or imported but application-side runtime behavior is missing or incorrect, including load failures, inactive…
nemo-relay-export-atif-trajectories
nvidia
Export NeMo Relay activity as ATIF trajectories for replay, analysis, or interchange
nemo-relay-export-openinference
nvidia
Configure and use NeMo Relay OpenInference export for OTLP backends that understand OpenInference semantics
nemo-relay-export-otel
nvidia
Configure and use NeMo Relay OpenTelemetry export for OTLP-compatible tracing backends
nemo-relay-get-started
nvidia
Use this skill when first-time NeMo Relay users want to try Relay, choose the least-complex supported quick start, or verify initial value through the CLI, a…
nemo-relay-get-started
nvidia
Use this skill when first-time NeMo Relay users want to try Relay, choose the least-complex supported quick start, or verify initial value through the CLI, a…
nemo-relay-install
nvidia
Use this skill when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, Hermes, or maintained framework integrations…
nemo-relay-install
nvidia
Use this skill when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, Hermes, or maintained framework integrations…
nemo-relay-instrument-calls
nvidia
Wrap application tool calls and LLM/provider calls with NeMo Relay scopes and managed execution APIs
nemo-relay-instrument-calls
nvidia
Use this skill when an application owns tool or LLM/provider call sites and needs to wrap them with NeMo Relay scopes and managed execution APIs for lifecycle…
nemo-relay-instrument-context-isolation
nvidia
Use this skill when concurrent requests, async tasks, threads, workers, goroutines, or agents need independent NeMo Relay scope stacks and correct ancestry…
nemo-relay-instrument-context-isolation
nvidia
Use this skill when concurrent requests, async tasks, threads, workers, goroutines, or agents need independent NeMo Relay scope stacks and correct ancestry…
nemo-relay-instrument-typed-wrappers
nvidia
Use this skill when adding NeMo Relay typed wrappers, domain types, or provider codecs while preserving JSON middleware semantics and caller-visible behavior.
nemo-relay-instrument-typed-wrappers
nvidia
Use this skill when adding NeMo Relay typed wrappers, domain types, or provider codecs while preserving JSON middleware semantics and caller-visible behavior.
nemo-relay-migrate-from-flow
nvidia
Use this skill when migrating applications, examples, integrations, documentation, manifests, or repository code from NeMo Flow to NeMo Relay across Python,…
nemo-relay-migrate-from-flow
nvidia
Migrate applications, examples, integrations, documentation, package manifests, and repository code from NeMo Flow naming and packages to NeMo Relay across…
nemo-relay-plugin-adaptive-tuning
nvidia
Use this skill when baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin behavior, including telemetry,…
nemo-relay-plugin-adaptive-tuning
nvidia
Use this skill when baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin behavior, including telemetry,…
nemo-relay-plugin-build
nvidia
Use this skill when building or packaging reusable NeMo Relay runtime behavior as a configuration-activated plugin with deterministic validation and…
nemo-relay-plugin-build
nvidia
Use this skill when building or packaging reusable NeMo Relay runtime behavior as an embedded configuration component or a manifest-backed `rust_dynamic`…
nemo-relay-plugin-observability
nvidia
Use this skill when choosing or configuring NeMo Relay 0.6 or 0.7 observability through the built-in plugin, subscribers, or exporters, including raw ATOF…
nemo-relay-plugin-observability
nvidia
Use this skill when choosing or configuring NeMo Relay 0.6 or 0.7 observability through the built-in plugin, subscribers, or exporters, including raw ATOF…
nemo-relay-setup-observability
nvidia
Choose and set up the right NeMo Relay observability path for an application
nemo-relay-start
nvidia
Help application developers pick a NeMo Relay binding and get to a first working scope, tool call, and LLM call
nemo-relay-tune-adaptive-config
nvidia
Configure the NeMo Relay adaptive plugin component through the shared plugin system; use this skill for state, telemetry, adaptive_hints, tool_parallelism,…
nemo-relay-tune-adaptive-hints
nvidia
Consume NeMo Relay adaptive hints, predictions, latency sensitivity, ACG diagnostics, or tool-parallelism guidance safely in application logic after the…
nemo-relay-tune-performance
nvidia
Plan a measured NeMo Relay adaptive tuning rollout after baseline scopes, tool calls, LLM calls, and observability are working; use this skill to improve…
nemo-relay-typed-wrappers-codecs
nvidia
Use NeMo Relay typed wrappers and codecs without losing middleware behavior
nemo-relay-use-context-isolation
nvidia
Set up and reason about NeMo Relay scope-stack isolation for concurrent application work
nemo-retriever
nvidia
Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg`…
nemo-retriever
nvidia
Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg`…
nemo-rl-auto-research
nvidia
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle:…
nemo-rl-brev-etiquette
nvidia
Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional…
nemo-rl-docs
nvidia
Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring,…
nemo-rl-session-memory
nvidia
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts,…
nemoclaw-community-contributor-examples
nvidia
Guide NemoClaw Community contributors through classifying, naming, adding, moving, renaming, and reviewing repository examples. Use when work affects examples,…
nemoclaw-configure-inference
nvidia
Lists all inference providers offered during NemoClaw onboarding. Use when explaining which providers are available, what the onboard wizard presents, or how…
nemoclaw-contributor-create-pr
nvidia
Create GitHub pull requests that follow the NemoClaw PR template, then monitor CI and automated review feedback. Use when the user wants to create a new PR,…
nemoclaw-contributor-onboard
nvidia
Prepare a NemoClaw source checkout for compliant contribution through the repository's one-command setup and readiness doctor. Use when a new contributor asks…
nemoclaw-contributor-onboard
nvidia
Prepare a NemoClaw source checkout for compliant contribution through the repository's one-command setup and readiness doctor. Use when a new contributor asks…
nemoclaw-contributor-onboard-messaging-channel
nvidia
Guide NemoClaw contributors through adding or reviewing a new messaging channel in the manifest-first messaging architecture. Use when onboarding a channel for…
nemoclaw-contributor-onboard-messaging-channel
nvidia
Guide NemoClaw contributors through adding or reviewing a new messaging channel in the manifest-first messaging architecture. Use when onboarding a channel for…
nemoclaw-contributor-update-dependencies
nvidia
Audit and implement dependency upgrades as semantic migrations rather than version-only bumps. Use when changing a library, CLI, service, container image,…
nemoclaw-contributor-update-docs
nvidia
Scan recent git commits for user-facing changes, update the corresponding documentation, and create the canonical dated MDX changelog entry for pre-tag release…
nemoclaw-contributor-update-docs
nvidia
Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages for release prep. Use when…
nemoclaw-contributor-update-hermes
nvidia
Audit, implement, and validate Hermes Agent upgrades in NVIDIA/NemoClaw. Use when changing the pinned Hermes CalVer tag or semver, reviewing a Hermes release,…
nemoclaw-deploy-remote
nvidia
Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow.…
nemoclaw-get-started
nvidia
Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time.
nemoclaw-maintainer-cross-issue-sweep
nvidia
Scans other open issues to find ones a given PR may also fix or accidentally break. Outputs adjacent-fix opportunities and contradiction risks with file:line…
nemoclaw-maintainer-cross-issue-sweep
nvidia
Scan open issues to find issues that a PR can also fix or conflict with. Report each relationship with file and line evidence. Use this skill during PR review…
nemoclaw-maintainer-cut-release-tag
nvidia
Creates deterministic NemoClaw semver release tags on origin/main after verifying the pre-tag dated changelog entry, handles release housekeeping, drafts…
nemoclaw-maintainer-cut-release-tag
nvidia
Creates deterministic NemoClaw semver release tags on origin/main, handles release housekeeping, drafts release notes, and verifies the maintainer-published…
nemoclaw-maintainer-day
nvidia
Runs the daytime maintainer loop for NemoClaw, prioritizing items labeled with the current version target. Picks the highest-value item, executes the right…
nemoclaw-maintainer-e2e
nvidia
Dispatches and verifies trusted GitHub Actions E2E for NemoClaw maintainers. Use for requests such as run the E2E suite, run the Launchable E2E, run the full…
nemoclaw-maintainer-evening
nvidia
Runs the end-of-day maintainer handoff for NemoClaw. Checks version target progress, records stragglers for an automatic post-tag bump, generates a QA handoff…
nemoclaw-maintainer-find-review-pr
nvidia
Finds open security-labeled GitHub PRs with Urgent or High Project Priority, links each to its issue, detects duplicates, and presents a table of review…
nemoclaw-maintainer-find-review-pr
nvidia
Find open PRs with the security label and Urgent or High Project Priority. Link each PR to its issue. Identify competing or superseded PRs and report review…
nemoclaw-maintainer-morning
nvidia
Runs the morning maintainer standup for NemoClaw. Triages the backlog, determines the day's target version, labels selected items, surfaces stragglers from…
nemoclaw-maintainer-normalize-title-tags
nvidia
Normalizes GitHub issue and PR titles by removing any bracketed [NemoClaw] tag case-insensitively, even when the tag appears later in the title. Use when…
nemoclaw-maintainer-normalize-title-tags
nvidia
Normalizes GitHub issue and PR titles by removing any bracketed [NemoClaw] tag case-insensitively, even when the tag appears later in the title. Use when…
nemoclaw-maintainer-policies
nvidia
Provide read-only NemoClaw maintainer policy. Use for questions about Issue Type, labels, Project fields, release labels, triage, duplicates, blocked items,…
nemoclaw-maintainer-policies
nvidia
Read-only maintainer policy reference for NemoClaw agents, engineers, and maintainers. Use when answering NemoClaw project-management workflow questions,…
nemoclaw-maintainer-pr-comparator
nvidia
Compare open PRs that address the same issue and recommend one to merge. Apply eligibility, correctness, quality, and tie-break checks. Report the score and…
nemoclaw-maintainer-pr-comparator
nvidia
Compares competing PRs that target the same issue and recommends which one to merge. Runs gate, correctness, and quality checks; outputs a deterministic…
nemoclaw-maintainer-refactor-docs
nvidia
Plan and execute maintainer-owned refactors of oversized NemoClaw Fern documentation sections into focused one-topic pages with concise prose, journey-based…
nemoclaw-maintainer-release-notes
nvidia
Drafts NemoClaw release notes from live GitHub tag and compare data. Produces the repo's narrative release-note style with three lead paragraphs, categorized…
nemoclaw-maintainer-security-code-review
nvidia
Performs a comprehensive security review of code changes in a GitHub PR or issue. Checks out the branch, analyzes changed files against a 9-category security…
nemoclaw-maintainer-security-code-review
nvidia
Review a PR, or a PR linked to an issue, for security risks. Check nine categories and report PASS, WARNING, or FAIL. Use when reviewing code for…
nemoclaw-maintainer-triage
nvidia
AI-assisted triage for NVIDIA/NemoClaw issues and PRs using native Issue Type, Project fields, and the canonical label taxonomy. Supports single-item and batch…
nemoclaw-maintainer-verify-stale
nvidia
Verifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the latest tag. Use when maintainers ask to verify stale issues, reproduce old bugs on…
nemoclaw-maintainer-verify-stale
nvidia
Verifies whether stale NVIDIA/NemoClaw bug reports still reproduce on the latest tag. Use when maintainers ask to verify stale issues, reproduce old bugs on…
nemoclaw-manage-policy
nvidia
Reviews and approves blocked agent network requests in the TUI. Use when approving or denying sandbox egress requests, managing blocked network calls, or using…
nemoclaw-monitor-sandbox
nvidia
Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox logs.
nemoclaw-reference
nvidia
Describes how NemoClaw combines a CLI plugin with a versioned blueprint to move OpenClaw into a controlled sandbox. Use when looking up NemoClaw architecture,…
nemoclaw-security-best
nvidia
Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or…
nemoclaw-skills-guide
nvidia
Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task. Use when discovering NemoClaw capabilities,…
nemoclaw-skills-guide
nvidia
Start here. Introduces what NemoClaw is, what agent skills are available, and which skill to use for a given task. Use when discovering NemoClaw capabilities,…
nemoclaw-user-agent-skills
nvidia
Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant…
nemoclaw-user-agent-skills
nvidia
Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant…
nemoclaw-user-configure-inference
nvidia
Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw.…
nemoclaw-user-configure-inference
nvidia
Connects NemoClaw to a local inference server. Use when setting up Ollama, vLLM, TensorRT-LLM, NIM, or any OpenAI-compatible local model server with NemoClaw.…
nemoclaw-user-configure-security
nvidia
Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or…
nemoclaw-user-configure-security
nvidia
Presents a risk framework for every configurable security control in NemoClaw. Use when evaluating security posture, reviewing sandbox security defaults, or…
nemoclaw-user-deploy-remote
nvidia
Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when…
nemoclaw-user-deploy-remote
nvidia
Explains how to run NemoClaw on a remote GPU instance, including the deprecated Brev compatibility path and the preferred installer plus onboard flow. Use when…
nemoclaw-user-get-started
nvidia
Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time.…
nemoclaw-user-get-started
nvidia
Installs NemoClaw, launches a sandbox, and runs the first agent prompt. Use when onboarding, installing, or launching a NemoClaw sandbox for the first time.…
nemoclaw-user-guide
nvidia
Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure,…
nemoclaw-user-guide
nvidia
Guides human users' AI agents to the NemoClaw docs MCP server and canonical Fern documentation in Markdown form. Use when users ask how to install, configure,…
nemoclaw-user-manage-policy
nvidia
Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint…
nemoclaw-user-manage-policy
nvidia
Adds, removes, or modifies allowed endpoints in the sandbox policy. Use when customizing network policy, changing egress rules, or configuring sandbox endpoint…
nemoclaw-user-manage-sandboxes
nvidia
Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential…
nemoclaw-user-manage-sandboxes
nvidia
Explains operational tasks after the quickstart: listing sandboxes, status and health checks, logs, diagnostics, port forwards, multiple sandboxes, credential…
nemoclaw-user-monitor-sandbox
nvidia
Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox…
nemoclaw-user-monitor-sandbox
nvidia
Inspects sandbox health, traces agent behavior, and diagnoses problems. Use when monitoring a running sandbox, debugging agent issues, or checking sandbox…
nemoclaw-user-overview
nvidia
Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when…
nemoclaw-user-overview
nvidia
Explains how OpenClaw, OpenShell, and NemoClaw form the ecosystem, NemoClaw's position in the stack, what NemoClaw adds beyond the community sandbox, and when…
nemoclaw-user-reference
nvidia
Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture,…
nemoclaw-user-reference
nvidia
Describes the NemoClaw integration layer and blueprint architecture and how they orchestrate compatible agent sandboxes. Use when looking up architecture,…
nemoclaw-user-skills-coding
nvidia
Describes the agent skills shipped with NemoClaw and how to access them by cloning the repository. Use when users ask about AI agent support, coding assistant…
nemoclaw-user-workspace
nvidia
Hows to back up and restore OpenClaw workspace files before destructive operations. Whats workspace personality and configuration files are, where they live,…
nemoclaw-workspace
nvidia
Backs up and restores OpenClaw workspace files before destructive operations. Use when backing up a sandbox, restoring workspace state, or preparing for a…
nemotron-asr-finetune
nvidia
Orchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal like "improve/fine-tune ASR for my domain or…
nemotron-customize
nvidia
Plan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or…
nemotron-policy-generator
nvidia
Generates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal…
nemotron-retrieval-recipes
nvidia
Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.
nemotron-speech
nvidia
Routes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.
nightly-sync
nvidia
Domain knowledge for the nightly main-to-dev sync workflow. Covers merge strategy, CI architecture, failure investigation, and known issues.
nim-operator-install
nvidia
Install NVIDIA NIM Operator on Kubernetes with prerequisite checks, optional NVIDIA GPU Operator dependency installation, public or local Helm chart selection,…
nim-operator-install
nvidia
Install NVIDIA NIM Operator on Kubernetes with prerequisite checks, optional NVIDIA GPU Operator dependency installation, public or local Helm chart selection,…
nim-operator-uninstall
nvidia
Safely uninstall NVIDIA NIM Operator from Kubernetes with inventory checks, explicit approval gates for destructive actions, optional custom resource cleanup,…
nim-operator-uninstall
nvidia
Safely uninstall NVIDIA NIM Operator from Kubernetes with inventory checks, explicit approval gates for destructive actions, optional custom resource cleanup,…
node-rca-rcca
nvidia
Investigate one NVIDIA Fleet Intelligence node and generate an evidence-backed HTML RCA/RCCA from live current and historical alerts plus authoritative…
nre
nvidia
Use to drive NVIDIA Omniverse NuRec / Neural Reconstruction Engine (NRE) via the public NGC containers nvcr.io/nvidia/nre/nre and nvcr.io/nvidia/nre/nre-tools…
nsys-analyze
nvidia
Analyze profiling data from Kit-based apps. Covers Omniverse-specific NVTX zone interpretation, phase detection using sqlite3, Tracy Statistics/Range Limit…
nsys-analyze
nvidia
Analyze profiling data from Kit-based apps. Covers Omniverse-specific NVTX zone interpretation, phase detection using sqlite3, Tracy Statistics/Range Limit…
nurec-fixer
nvidia
Use to run NVIDIA DiffusionHarmonizer (public successor to the older Fixer recipes) to enhance, harmonize, evaluate, or fine-tune novel-view frames from NRE /…
nurec-index
nvidia
Router for NVIDIA NuRec / NRE / 3DGUT / USDZ / NCore V4 / asset harvest / frame cleanup tasks — picks the right sibling (nre, ncore, asset-harvester,…
nv-generate-ct-rflow
nvidia
Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data without review.
nv-generate-mr
nvidia
Used for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr. Not for paired masks or production training data.
nv-generate-mr-brain
nvidia
Used for generating synthetic brain MRI volumes with NV-Generate-CTMR rflow-mr-brain. Not for production training data.
nv-generate-mr-brain-finetune
nvidia
Used for finetuning NV-Generate-CTMR MR-brain diffusion UNet from a NIfTI datalist. Not for clinical or production data approval.
nv-generate-vae-finetune
nvidia
Used for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval.
nv-reason-cxr
nvidia
Used for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting.
nv-segment-ct
nvidia
Used for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.
nv-segment-ct-finetune
nvidia
Used for smoke or dataset finetuning of NV-Segment-CT VISTA3D on CT NIfTI labels. Not for clinical validation.
nv-segment-ctmr
nvidia
Used for running NV-Segment-CTMR on CT or MRI NIfTI volumes and recording label-map evidence. Not for clinical interpretation.
nvalchemi-data-storage
nvidia
How to write, read, compose, and load atomic data using nvalchemi's composable Zarr-backed storage pipeline (Writer, Reader, Dataset, MultiDataset,…
nvalchemi-data-storage
nvidia
How to write, read, compose, and load atomic data using nvalchemi's composable Zarr-backed storage pipeline (Writer, Reader, Dataset, MultiDataset,…
nvalchemi-data-structures
nvidia
How to use AtomicData and Batch, the core graph-based data structures for representing atomic systems and batching them for GPU computation. Use when building…
nvalchemi-data-structures
nvidia
How to use AtomicData and Batch, the core graph-based data structures for representing atomic systems and batching them for GPU computation. Use when building…
nvalchemi-dynamics-api
nvidia
How to configure and run dynamics simulations, compose multi-stage pipelines (FusedStage, DistributedPipeline), use inflight batching, and manage data sinks.…
nvalchemi-dynamics-api
nvidia
How to configure and run dynamics simulations, compose multi-stage pipelines (FusedStage, DistributedPipeline), use inflight batching, and manage data sinks.…
nvalchemi-dynamics-hooks
nvidia
How to use and write dynamics hooks — callbacks that observe or modify batch state at specific points during each simulation step. Use when a simulation needs…
nvalchemi-dynamics-hooks
nvidia
How to use and write dynamics hooks — callbacks that observe or modify batch state at specific points during each simulation step. Use when a simulation needs…
nvalchemi-dynamics-implementation
nvidia
How to implement a dynamics integrator by subclassing BaseDynamics and overriding pre_update() and post_update() methods. Use when creating a custom…
nvalchemi-dynamics-implementation
nvidia
How to implement a dynamics integrator by subclassing BaseDynamics and overriding pre_update() and post_update() methods. Use when creating a custom…
nvalchemi-fine-tuning
nvidia
How to fine-tune nvalchemi-compatible models with FineTuningStrategy, pretrained checkpoint initialization, module patches, trainable-parameter filters,…
nvalchemi-fine-tuning
nvidia
How to fine-tune nvalchemi-compatible models with FineTuningStrategy, pretrained checkpoint initialization, module patches, trainable-parameter filters,…
nvalchemi-loss-api
nvidia
How to use built-in loss functions and implement custom losses using the BaseLossFunction template-method pattern — residual types, per-atom normalization,…
nvalchemi-loss-api
nvidia
How to use built-in loss functions and implement custom losses using the BaseLossFunction template-method pattern — residual types, per-atom normalization,…
nvalchemi-model-wrapping
nvidia
How to wrap an arbitrary MLIP (Machine Learning Interatomic Potential) using the BaseModelMixin interface to standardize inputs, outputs, and embeddings. Use…
nvalchemi-model-wrapping
nvidia
How to wrap an arbitrary MLIP (Machine Learning Interatomic Potential) using the BaseModelMixin interface to standardize inputs, outputs, and embeddings. Use…
nvalchemi-reporting
nvidia
How to add observability to nvalchemi dynamics and training workflows using ReportingOrchestrator, RichReporter, TensorBoardReporter, scalar extraction, custom…
nvalchemi-reporting
nvidia
How to add observability to nvalchemi dynamics and training workflows using ReportingOrchestrator, RichReporter, TensorBoardReporter, scalar extraction, custom…
nvalchemi-training-api
nvidia
How to configure nvalchemi training workflows with TrainingStrategy, custom training functions, standalone or composed losses, loss-weight schedules, optimizer…
nvalchemi-training-api
nvidia
How to configure nvalchemi training workflows with TrainingStrategy, custom training functions, standalone or composed losses, loss-weight schedules, optimizer…
nvalchemi-zarr-perf
nvidia
Performance tuning for nvalchemi's Zarr-backed Reader, Dataset, and DataLoader pipeline. Use when configuring AtomicDataZarrReader, Dataset, DataLoader,…
nvalchemi-zarr-perf
nvidia
Performance tuning for nvalchemi's Zarr-backed Reader, Dataset, and DataLoader pipeline. Use when configuring AtomicDataZarrReader, Dataset, DataLoader,…
nvcf-explore-stack
nvidia
Navigate and explain the NVCF self-hosted stack inside the monorepo. Maps helmfile releases to their charts, image-source subtrees, helm hooks, namespaces, and…
nvcf-self-managed-cli
nvidia
Install, operate, and tear down self-hosted NVIDIA Cloud Functions (NVCF) deployments with nvcf-cli. Use for control-plane or compute-plane install, status…
nvcf-self-managed-installation
nvidia
Install and operate NVCF self-hosted control-plane and separate compute-plane stacks. Covers Helmfile values and CLI profile installation flows, teardown,…
nvcf-self-managed-prerequisite
nvidia
Install the prerequisites the NVCA operator / compute plane needs before nvcf-nvca-install can succeed: the operator tool nvcf-cli (required by the…
nvflare-convert-pytorch
nvidia
Convert existing PyTorch training code into an NVFLARE federated job using Client API model exchange, local validation, and job export; do not use for other…
nvflare-diagnose-job
nvidia
Diagnose failed, stalled, or suspicious NVFLARE jobs in simulation, POC, or production by collecting bounded evidence and mapping failure patterns to recovery…
nvflare-orient
nvidia
Route ambiguous NVFLARE requests by inspecting the local project, checking readiness, and recommending the next specific FLARE workflow skill without editing…
nvfleetint
nvidia
Query NVIDIA Fleet Intelligence with the nvfleetint CLI. Use for ad hoc questions about fleets, nodes, GPUs, node groups, compute zones, alerts, agent health,…
nvidia-kaggle-skill
nvidia
Use for Kaggle competition overview fetches, writeups, discussion/kernel research, submissions, and dataset uploads. Not for unrelated ML code.
nvidia-skill-finder
nvidia
Use for NVIDIA-related requests where an NVIDIA skill might help, even if the user did not ask for a skill. Trigger on NVIDIA products, hardware, software,…
nvrx-attr
nvidia
Orchestration layer over nvidia_resiliency_ext attribution modules. Provides log-analysis, fr-analysis, and a Megatron-LM-oriented fault-injection feedback…
nvtx-python
nvidia
Profile Python functions with NVTX in non-Kit environments (Isaac Lab 3.0+ standalone, any Python app without Carbonite). Uses a bundled PYTHONPATH-scoped…
nvtx-python
nvidia
Profile Python functions with NVTX in non-Kit environments (Isaac Lab 3.0+ standalone, any Python app without Carbonite). Uses a bundled PYTHONPATH-scoped…
omniverse-cad-to-simready
nvidia
Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop…
omniverse-realtime-viewer
nvidia
Use as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.
omniverse-usd-performance-tuning
nvidia
Top-level workflow skill for USD performance diagnosis and optimization. Use for slow loading, high memory, low FPS, or 'optimize my scene' requests; delegates…
onboard-gb200-1node-tests
nvidia
Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.
onboarding-guide
nvidia
Guides new users through a friendly onboarding experience
openshell-cli
nvidia
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, policy iteration,…
openshell-cli
nvidia
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration, policy iteration, BYOC…
optimization-from-data-orchestrator
nvidia
Coordinate uploaded data plus a natural-language question into interpretation, clarification, cuOpt solve, and a user-facing answer.
optimization-from-data-orchestrator
nvidia
Coordinate uploaded data plus a natural-language question into interpretation, clarification, cuOpt solve, and a user-facing answer.
optimization-intent-router
nvidia
Classify whether a data-backed request is LP, MILP, QP, routing, or non-optimization analytics.
optimization-intent-router
nvidia
Classify whether a data-backed request is LP, MILP, QP, routing, or non-optimization analytics.
optimization-mode-router
nvidia
Choose fast direct-to-cuOpt solve versus replayable or auditable model artifact mode.
optimization-mode-router
nvidia
Choose fast direct-to-cuOpt solve versus replayable or auditable model artifact mode.
osmo
nvidia
How to use the OSMO CLI to manage cloud compute resources for robotics development. Use this skill whenever the user asks about available resources, nodes,…
osmo-admin
nvidia
Use only for offline/local OSMO service-config admin requests involving explicit config roots or values files, or to ask for one when a file-specific config…
osmo-agent
nvidia
Operate the OSMO CLI to discover GPU resources, submit and monitor workflows, debug PENDING/FAILED/stuck workflows, interpret OSMO errors, surface OSMO…
osmo-deploy
nvidia
How to deploy OSMO to a Kubernetes cluster on Azure (AKS), AWS (EKS), MicroK8s (single-node), or any kubectl-reachable cluster (BYO). Use this skill whenever…
osmo-user
nvidia
Drive the OSMO CLI for cloud-robotics compute on behalf of an end user: check resources, submit/monitor/debug/explain workflows, fetch logs and…
over-privileged-helper
nvidia
A simple file reader utility
ovphysx-host-runtime-boundary
nvidia
Run configured native OVPhysX demos and report host GIF/status receipts when Hermes is sandboxed but the OVRTX/OVPhysX runtime and visible Blender process are…
paidf-anomalygen
nvidia
Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and search…
pattern-creation
nvidia
Convert validated playground templates or HTML compositions into reusable pattern files (*.examples.ts) in the pattern library. Use this skill whenever the…
payment-ops-playbook
nvidia
The standard FinGuard payment-operations workflow — screen, explain, prepare, hand off to a human. Never release.
payment-screening
nvidia
Screen an outbound payment against limits, sanctions/watchlists, and duplicate checks before a human releases it.
perf-nsight-compute-analysis
nvidia
Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp…
perf-nsight-compute-analysis
nvidia
Analyze ncu (NVIDIA Nsight Compute) profiling output: SOL% bottleneck classification, roofline analysis, occupancy diagnosis, memory hierarchy analysis, warp…
perf-optimization
nvidia
Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection,…
perf-optimization
nvidia
Performance optimization coordination playbook. Contains specialist routing table, TileIR two-step pipeline, kernel generation specialist selection,…
perf-torch-cuda-graphs
nvidia
Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager,…
perf-torch-cuda-graphs
nvidia
Apply CUDA Graphs to PyTorch workloads — API selection (torch.compile, PyTorch make_graphed_callables, TE make_graphed_callables, MCore CudaGraphManager,…
perf-torch-sync-free
nvidia
Identify and eliminate host-device synchronizations in PyTorch code. Detects sync points (.item(), .cpu(), boolean indexing, torch.tensor on CUDA), classifies…
perf-torch-sync-free
nvidia
Identify and eliminate host-device synchronizations in PyTorch code. Detects sync points (.item(), .cpu(), boolean indexing, torch.tensor on CUDA), classifies…
perf-tuning
nvidia
Resolve common Kit/Isaac Sim/Isaac Lab performance issues using specific settings and configuration changes. Covers PresentFrame stalls,…
perf-tuning
nvidia
Resolve common Kit/Isaac Sim/Isaac Lab performance issues using specific settings and configuration changes. Covers PresentFrame stalls,…
perf-workload-profiling
nvidia
Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec),…
perf-workload-profiling
nvidia
Code instrumentation for timing workloads. Two scenarios: (1) Training loop — inject manual timing to report per-iteration latency, throughput (samples/sec),…
personal-assistant
nvidia
A personalized assistant that remembers your preferences
physical-ai-datasets
nvidia
Use when the user wants to find, download, or pick a NVIDIA Physical AI dataset on Hugging Face for autonomous-vehicle, robotics, spatial intelligence,…
physical-ai-defect-image-generation
nvidia
Use when the user wants to orchestrate defect image generation with NVIDIA Cosmos AnomalyGen (Cosmos-Predict2-derived) on OSMO for PCBA, metal surface, and…
physical-ai-infrastructure-setup-and-resilient-scaling
nvidia
Use when the user wants to set up, scale, validate, or harden NVIDIA physical AI infrastructure for synthetic data generation workflows across local MicroK8s…
physical-ai-neural-reconstruction
nvidia
Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets. Do NOT use for SimReady or infra setup.
physical-ai-people-attribute-search
nvidia
Use when running people attribute search (PAS) image augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation,…
physical-ai-video-data-augmentation
nvidia
Use when running video data augmentation and auto-labeling workflows on OSMO: flow selection, preflight, submit-time interpolation, monitoring, and output…
physicsnemo-discover
nvidia
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting,…
physicsnemo-discover
nvidia
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting,…
physicsnemo-shard-tensor
nvidia
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or…
portfolio-optimization
nvidia
Use when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, Mean-Variance/SOCP variance caps, efficient…
prepare-code-freeze
nvidia
Prepare a NeMo Relay code freeze by creating the release branch, updating nightly alpha branch config, bumping main to the next version, and opening the…
prepare-code-freeze
nvidia
Prepare a NeMo Relay code freeze by creating the release branch, updating nightly alpha branch config, bumping main to the next version, and opening the…
prepare-pr
nvidia
Prepare, open, create, publish, update, or edit a NeMo Fabric pull request or PR body with the right tests, docs, scope, and review handoff details
prepare-pr
nvidia
Prepare, open, create, publish, update, or edit a NeMo Relay pull request or PR body with the right tests, docs, contributor hygiene, and repository pull…
prepare-pr
nvidia
Prepare, open, create, publish, update, or edit a NeMo Relay pull request or PR body with the right tests, docs, contributor hygiene, and repository pull…
profile-model-performance
nvidia
Inspect and baseline performance for FlashDreams-style model integrations and interactive demos: map the generation path, add trustworthy timing splits, build…
profiling
nvidia
Capture performance traces using CPU ChromeTrace, Tracy, and Nsight Systems/NVTX for Kit-based applications (Isaac Sim, Isaac Lab, Kit SDK). Covers…
profiling
nvidia
Capture performance traces using CPU ChromeTrace, Tracy, and Nsight Systems/NVTX for Kit-based applications (Isaac Sim, Isaac Lab, Kit SDK). Covers…
profiling-api
nvidia
Add profiling zones, metrics, and annotations to Kit-based C++ and Python code. Covers Carbonite macros (CARB_PROFILE_ZONE, CARB_PROFILE_FUNCTION, GPU zones),…
profiling-api
nvidia
Add profiling zones, metrics, and annotations to Kit-based C++ and Python code. Covers Carbonite macros (CARB_PROFILE_ZONE, CARB_PROFILE_FUNCTION, GPU zones),…
ptq
nvidia
Use when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4…
ptq
nvidia
This skill should be used when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8…
python-docstring-style
nvidia
Write Python docstrings and inline comments matching the flashdreams house style — SPDX header, one-line module docstring, Google-style function docstrings…
python-tests
nvidia
Python tests for NeMo Fabric; use this when writing tests
qiskit-to-cudaq
nvidia
Use when porting Qiskit Python circuits to CUDA-Q kernels while preserving algorithms and validation fidelity.
qp-formulation
nvidia
Quadratic Programming (QP) — problem form and constraints. Domain concepts; no API or interface. QP is beta.
quant-recipe-search
nvidia
Use when the user asks to find, search for, or optimize the best quantization recipe for a model, including direct requests like "find the best quantization…
quant-recipe-search
nvidia
Use when the user asks to find, search for, or optimize the best quantization recipe for a model, including direct requests like "find the best quantization…
rag-blueprint
nvidia
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure,…
rag-eval
nvidia
Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or…
rag-perf
nvidia
Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS…
rail-boundary-test
nvidia
Verify that OpenShell denies FinGuard access to the synthetic payment rail. This is a control test, never a payment release.
release-audit
nvidia
Generate a Warp release audit report (pre-release or RC, auto-detected from version string and head ref).
release-audit
nvidia
Generate a Warp release audit report (pre-release or RC, auto-detected from version string and head ref).
release-cherry-pick
nvidia
Cherry-pick merged PRs labeled for a release branch into that branch, then open a PR and apply the cherry-pick-done label. Use when asked to "cherry-pick PRs…
release-cherry-pick
nvidia
Cherry-pick merged PRs labeled for a release branch into that branch, then open a PR and apply the cherry-pick-done label. Use when asked to "cherry-pick PRs…
release-notes
nvidia
Generate a starting-point GitHub release notes draft for an upcoming Warp release (feature or bugfix, auto-detected from the version). Run from a release…
release-notes
nvidia
Generate a starting-point GitHub release notes draft for an upcoming Warp release (feature or bugfix, auto-detected from the version). Run from a release…
release-packet
nvidia
Prepare a human-approval release packet for a screened payment. Does not release funds — release requires a human checker.
rename-surfaces
nvidia
Perform a coordinated repository, package, crate, module, or symbol rename across NeMo Relay
rename-surfaces
nvidia
Perform a coordinated repository, package, crate, module, or symbol rename across NeMo Relay
report-generator
nvidia
Generate formatted reports from data
respond-to-issue
nvidia
Research and draft a response to a GitHub issue or question from an external contributor.
review-doc-style
nvidia
Review NeMo Fabric documentation, examples, and docs-heavy changes for NVIDIA technical writing style, terminology, repository accuracy, and current public…
review-doc-style
nvidia
Review documentation, examples, and docs-heavy changes for NVIDIA technical writing style, terminology, and repo accuracy
review-doc-style
nvidia
Review documentation, examples, and docs-heavy changes for NVIDIA technical writing style, terminology, and repo accuracy
review-github-pr
nvidia
Review a GitHub pull request by summarizing its diff and key design decisions. Use when the user wants to review a PR, understand changes in a branch, or get a…
review-github-pr
nvidia
Review a GitHub pull request by summarizing its diff and key design decisions. Use when the user wants to review a PR, understand changes in a branch, or get a…
review-security-issue
nvidia
Given a GitHub issue, review the issue for security implications. You'll make a determination if the claim in the issue is legitimate and should be addressed…
review-security-issue
nvidia
Given a GitHub issue, review the issue for security implications. You'll make a determination if the claim in the issue is legitimate and should be addressed…
routing-formulation
nvidia
Vehicle routing (VRP, TSP, PDP) — problem types and data requirements. Domain concepts; no API or interface.
rtvi-cv-customize-model
nvidia
How to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2d_cv) mode - covers ONNX export, custom bbox parsers, compose mount…
rtvi-cv-scaffold-vss-service
nvidia
Scaffold a standalone RTVI CV microservice that plugs into VSS Search and Alerts profiles via Kafka mdx-raw. The shipped scaffold script is a YOLO26 reference…
rtvi-vlm-customize-model
nvidia
How to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as-verifier,…
run-on-slurm
nvidia
How to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run,…
safe-greeting
nvidia
A simple greeting skill that says hello to users
sbom
nvidia
Generate and manage Software Bill of Materials (SBOMs) for the OpenShell project. Covers SBOM generation with Syft, license resolution via public registries,…
sbom
nvidia
Generate and manage Software Bill of Materials (SBOMs) for the OpenShell project. Covers SBOM generation with Syft, license resolution via public registries,…
security-code-review
nvidia
Performs a comprehensive security review of code changes in a GitHub PR or issue. Checks out the branch, analyzes changed files against a 9-category security…
session-memory
nvidia
Manage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts,…
sglang-setup
nvidia
Deploy an SGLang inference server on an NVIDIA DGX Station GB300 with the cu130 container, RadixAttention prefix caching, and structured JSON output support.…
sglang-setup
nvidia
Deploy an SGLang inference server on an NVIDIA DGX Station GB300 with the cu130 container, RadixAttention prefix caching, and structured JSON output support.…
simready-foundation-add-capability
nvidia
Add SimReady capability docs, requirement indexes, validation stubs, and registrations for new requirement families.
simready-foundation-add-feature
nvidia
Use for adding SimReady feature docs, manifests, requirement mappings, validation strategy, and index entries.
simready-foundation-add-feature-adapter
nvidia
Use for adding SimReady feature adapters that mutate USD assets between exact feature or profile versions.
simready-foundation-add-profile
nvidia
Use for adding SimReady profile versions with feature bundles, docs, indexes, and validation notes.
simready-foundation-add-requirement
nvidia
Use for adding atomic SimReady requirements with stable IDs, docs, examples, indexes, and validator follow-up.
simready-foundation-add-runtime-test
nvidia
Use for adding SimReady runtime tests, runner expectations, batch/job/report notes, and validation evidence.
simready-foundation-add-validator
nvidia
Use for adding executable SimReady validators that report requirement IDs with focused pass/fail coverage.
simready-foundation-conform-fet-000-core
nvidia
Use for repairing SimReady Core naming, asset layout, unresolved paths, and undefined prim failures.
simready-foundation-conform-fet-001-minimal
nvidia
Use for repairing SimReady Minimal assets: units, upAxis, defaultPrim, hierarchy, mesh quality, extents, and origin placement.
simready-foundation-conform-fet-003-rigid-body-physics
nvidia
Use for repairing SimReady rigid-body and collider conformance for neutral or PhysX prop assets.
simready-foundation-conform-fet-004-simulate-multi-body-physics
nvidia
Use for repairing SimReady multibody physics: rigid bodies, joints, articulation roots, and PhysX variants.
simready-foundation-conform-fet-005-simulate-grasp-physics
nvidia
Use for vision-guided SimReady grasp repair, grasp_identifier curves, and physics-material triage.
simready-foundation-conform-fet-006-materials
nvidia
Use for repairing SimReady material bindings, USDPreview or MDL shaders, texture paths, sizes, and color spaces.
simready-foundation-conform-fet-007-nonvisual-materials
nvidia
Use for repairing SimReady nonvisual sensor material attributes on bound USD materials.
simready-foundation-conform-fet-021-robot-core
nvidia
Use for repairing SimReady robot core layout, thumbnails, robot schema, relationships, and root joint pinning.
simready-foundation-conform-fet-023-robot-materials
nvidia
Use for repairing SimReady robot material organization under the top-level Looks scope.
simready-foundation-conform-fet-024-base-articulation
nvidia
Use for repairing SimReady base articulation roots and PhysX collision-clearance evidence.
simready-foundation-create-package
nvidia
Use for creating SimReady packages with package sample scripts, WRAPP setup, root USD inputs, validation phases, and fallback modes.
simready-foundation-update-capability
nvidia
Use for updating SimReady capability docs, requirement indexes, validation registration, and feature references.
simready-foundation-update-feature
nvidia
Use for updating SimReady features with new versions, requirement changes, manifests, docs, and profile notes.
simready-foundation-update-feature-adapter
nvidia
Use for updating SimReady feature adapters, USD mutation logic, tests, and source/target metadata.
simready-foundation-update-profile
nvidia
Use for updating SimReady profile versions, feature bundles, docs, and adapter notes.
simready-foundation-update-requirement
nvidia
Use for updating SimReady requirement docs, semantics, validator alignment, and profile impact notes.
simready-foundation-update-validator
nvidia
Use for updating SimReady validators, failure messages, edge cases, and tests while preserving requirement semantics.
simready-foundation-validate-foundation-change
nvidia
Use for auditing SimReady requirement, validator, feature, profile, adapter, test, and skill consistency.
skill-card-generator
nvidia
Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or…
skill-evolution
nvidia
After solving a non-trivial problem, detect generalizable learnings and propose skill updates so future interactions benefit automatically. Always active —…
skill-evolution
nvidia
Use before creating, editing, or deciding whether to update any AI coding agent skill in this repository, including corrections to existing skill behavior,…
skill-inspector
nvidia
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill…
small-fix
nvidia
Make a small, reviewable NeMo Fabric bug fix without widening scope unnecessarily. Use for narrowly scoped bug fixes or behavior corrections in NeMo Fabric.
small-fix
nvidia
Make a small, reviewable NeMo Relay bug fix without widening scope unnecessarily
small-fix
nvidia
Make a small, reviewable NeMo Relay bug fix without widening scope unnecessarily
split-pr
nvidia
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
sync-agent-infra
nvidia
Detect and fix drift across agent-first infrastructure files. Ensures skill inventories, workflow chains, architecture tables, issue/PR templates, and…
sync-agent-infra
nvidia
Detect and fix drift across agent-first infrastructure files. Ensures skill inventories, workflow chains, architecture tables, issue/PR templates, and…
tabular-optimization-ingestion
nvidia
Infer optimization structure from uploaded tables and identify minimal clarifications before cuOpt modeling.
tabular-optimization-ingestion
nvidia
Infer optimization structure from uploaded tables and identify minimal clarifications before cuOpt modeling.
tao-analyze-changenet-rca
nvidia
Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing…
tao-analyze-gaps-visual-changenet
nvidia
Performs gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the data-services container (`tao_toolkit.data_services` from…
tao-analyze-gaps-vlm-bcq
nvidia
Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ…
tao-convert-dataset-format
nvidia
Run `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data. Use when the user asks to convert a DAFT…
tao-finetune-clip
nvidia
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning…
tao-finetune-cosmos-embed
nvidia
Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to…
tao-finetune-cosmos-reason
nvidia
Cosmos3-Nano video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video question-answering models, fine-tuning Cosmos3-Nano…
tao-finetune-huggingface-model
nvidia
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model…
tao-generate-image-grounding
nvidia
Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use…
tao-generate-referring-expressions
nvidia
Four-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region descriptions, scene captions, grounded referring…
tao-generate-video-reasoning-annotations
nvidia
Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs…
tao-launch-workflow
nvidia
Shared launch intake for any TAO workflow or action. Use when the user wants to run TAO AutoML, train, evaluate, infer, export, generate TensorRT engines, or…
tao-list-capabilities
nvidia
Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the…
tao-mine-aoi-images
nvidia
Runs the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour…
tao-port-huggingface-model
nvidia
Integrate a HuggingFace Computer Vision model into the NVIDIA TAO Toolkit ecosystem (tao-core config, tao-pytorch trainer, tao-deploy TensorRT pipeline). Use…
tao-route-visual-changenet-samples
nvidia
Routes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module subsets based on each module's label eligibility.…
tao-run-automl
nvidia
Run AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm,…
tao-run-automl-deft-pipeline
nvidia
Run the canonical NVIDIA AOI three-phase training pipeline — Phase 1 AutoML baseline (HPO), Phase 2 DEFT loop (RCA → SDG → mining → plain-train retrain), Phase…
tao-run-deft-aoi
nvidia
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, Cosmos AnomalyGen / AMP…
tao-run-inference-service
nvidia
Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the…
tao-run-on-brev
nvidia
Brev managed GPU instances with Docker support. Use when running TAO training, evaluation, or inference on Brev GPU instances, managing Brev deployments, or…
tao-run-on-docker
nvidia
Docker conventions for running NVIDIA GPU container workloads — NGC authentication, --gpus flag, mount patterns, env-var passthrough, container inspection,…
tao-run-on-kubernetes
nvidia
Kubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling. Use when running on EKS / GKE / AKS / on-prem…
tao-run-on-lepton
nvidia
DGX Cloud Lepton managed GPU compute platform with run/status/cancel interface. Use when submitting TAO jobs to DGX Cloud, dispatching training/eval/inference…
tao-run-on-local-docker
nvidia
Local or remote Docker execution for TAO SDK job containers using a Docker daemon with NVIDIA GPU runtime. Use when running TAO jobs on the current machine, a…
tao-run-on-slurm
nvidia
Remote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed results. Use when running TAO training/eval/inference…
tao-run-platform
nvidia
TAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM, local Docker, Kubernetes). Use when the user wants to…
tao-setup-nvidia-gpu-host
nvidia
Host setup for TAO GPU backends. Checks and, after user approval, installs NVIDIA driver branch 580, CUDA Toolkit 13.0, and NVIDIA Container Toolkit 1.19.0 for…
tao-train-action-recognition
nvidia
Action recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for classifying temporal actions in video clips. Use…
tao-train-bevfusion
nvidia
BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving for…
tao-train-centerpose
nvidia
CenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF object pose estimation. Use when training,…
tao-train-deformable-detr
nvidia
Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive accuracy.…
tao-train-depth-anything-v2
nvidia
Monocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts per-pixel depth from single RGB images. Use when…
tao-train-dino
nvidia
DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with denoising training, multi-scale features, and…
tao-train-fast-foundation-stereo
nvidia
Real-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of FoundationStereo. Predicts disparity maps from…
tao-train-foundation-stereo
nvidia
Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D reconstruction. Use when training, evaluating,…
tao-train-grounding-dino
nvidia
Grounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for language-guided detection — detects objects described…
tao-train-image-classification
nvidia
PyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.) with distillation and quantization for deployment.…
tao-train-mask-auto-encoder
nvidia
Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations; supports…
tao-train-mask-auto-label
nvidia
MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE…
tao-train-mask-grounding-dino
nvidia
Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for open-set segmentation guided by text prompts.…
tao-train-mask2former
nvidia
Mask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with masked attention for high-quality segmentation results.…
tao-train-metric-learning-recognition
nvidia
Metric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for retrieval-based matching (e.g., retail product recognition)…
tao-train-nvdinov2
nvidia
NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels and produces…
tao-train-nvpanoptix3d
nvidia
NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with…
tao-train-ocdnet
nvidia
OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach. Use when training,…
tao-train-ocrnet
nvidia
OCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC and attention-based decoders. Use when training,…
tao-train-oneformer
nvidia
OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries.…
tao-train-optical-inspection
nvidia
Optical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects, anomalies, or quality issues. Use when…
tao-train-pointpillars
nvidia
PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then applies 2D…
tao-train-pose-classification
nvidia
Pose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences into action categories from pose-keypoint data.…
tao-train-reid
nvidia
Person re-identification (ReID). Learns discriminative embeddings to match the same person across different camera views, based on metric learning. Use when…
tao-train-rtdetr
nvidia
RT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with competitive accuracy and supports distillation and…
tao-train-segformer
nvidia
SegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature extraction, efficient for real-time segmentation…
tao-train-single-step
nvidia
Standard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset without iterative data augmentation, AutoML, or…
tao-train-sparse4d
nvidia
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable attention across camera views and time for end-to-end…
tao-train-visual-changenet
nvidia
Visual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training, evaluating, exporting, or running inference for…
tao-validate-dataset-format
nvidia
Run `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do not use for non-DAFT formats. Use when the user…
terraform-deployer
nvidia
Deploy infrastructure using Terraform
test-ffi-surface
nvidia
Build and test the NeMo Relay FFI surface; use this for crates/ffi changes, header generation, or ABI-facing validation
test-ffi-surface
nvidia
Build and test the NeMo Relay FFI surface; use this for crates/ffi changes, header generation, or ABI-facing validation
test-go-binding
nvidia
Build and test the NeMo Relay Go binding; use this for go/nemo_relay changes or Go-facing integration checks
test-go-binding
nvidia
Build and test the NeMo Relay Go binding; use this for go/nemo_relay changes or Go-facing integration checks
test-node-binding
nvidia
Build and test the NeMo Relay Node.js binding; use this for crates/node changes or Node-facing integration checks
test-node-binding
nvidia
Build and test the NeMo Relay Node.js binding; use this for crates/node changes or Node-facing integration checks
test-python-binding
nvidia
Build and test the NeMo Relay Python binding and worker plugin SDK; use for python/nemo_relay, python/plugin, or crates/python changes
test-python-binding
nvidia
Build and test the NeMo Relay Python binding and worker plugin SDK; use for python/nemo_relay, python/plugin, or crates/python changes
test-release-canary
nvidia
Manually dispatch and iterate on the Release Canary workflow that smoke-tests published OpenShell artifacts (install.sh on macOS/Ubuntu/Fedora, Helm chart on…
test-release-canary
nvidia
Manually dispatch and iterate on the Release Canary workflow that smoke-tests published OpenShell artifacts (install.sh on macOS/Ubuntu/Fedora, Helm chart on…
test-rust-core
nvidia
Build and test NeMo Relay Rust core, adaptive, and dynamic plugin crates; use for crates/core, crates/adaptive, crates/plugin, crates/worker,…
test-rust-core
nvidia
Build and test NeMo Relay Rust core, adaptive, and dynamic plugin crates; use for crates/core, crates/adaptive, crates/plugin, crates/worker,…
testing
nvidia
Write and run automated tests for Elements components including unit, accessibility, visual, SSR, and lighthouse tests. Use this skill whenever the user wants…
testing
nvidia
Test system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI…
testsystem
nvidia
Test system, CI pipeline, and CI failure investigation for Megatron-LM. Covers test layout, recipe YAML structure, adding unit and functional tests, CI scope…
text-summarizer
nvidia
Summarizes text locally without any network access or external API calls
tilegym-adding-cutile-kernel
nvidia
Add a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and…
tilegym-converting-cutile-to-julia
nvidia
Converts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion,…
tilegym-converting-cutile-to-triton
nvidia
Converts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch,…
tilegym-cutile-autotuning
nvidia
Use when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` /…
tilegym-cutile-python
nvidia
Expert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization.…
tilegym-improve-cutile-kernel-perf
nvidia
Iteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes,…
tilegym-monkey-patch-kernels-to-transformers
nvidia
Integrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching…
tracy-memory
nvidia
Profile CPU and GPU memory allocations using Tracy in Kit-based applications after Tracy capture tooling is installed. Covers LD_PRELOAD setup for…
tracy-memory
nvidia
Profile CPU and GPU memory allocations using Tracy in Kit-based applications after Tracy capture tooling is installed. Covers LD_PRELOAD setup for…
triage-issue
nvidia
Assess, validate, and route community-filed issues for human disposition and roadmap placement. Takes a specific issue number or processes a confirmed batch of…
triage-issue
nvidia
Assess, classify, and route community-filed issues. Takes a specific issue number or processes all open issues with the state:triage-needed label in batch.…
tripy-compilation
nvidia
Work with the nvtripy compilation pipeline. Use when: using tp.compile, creating InputInfo or DimensionInputInfo, understanding the Trace → MLIR → TensorRT…
tripy-compilation
nvidia
Work with the nvtripy compilation pipeline. Use when: using tp.compile, creating InputInfo or DimensionInputInfo, understanding the Trace → MLIR → TensorRT…
tripy-constraints
nvidia
Author input/output constraints for nvtripy operations using the declarative constraint DSL. Use when: defining input_requirements or output_guarantees,…
tripy-constraints
nvidia
Author input/output constraints for nvtripy operations using the declarative constraint DSL. Use when: defining input_requirements or output_guarantees,…
tripy-debugging
nvidia
Debug and diagnose errors in nvtripy code. Use when: interpreting TripyException stack traces, enabling MLIR/TensorRT debug output, understanding error…
tripy-debugging
nvidia
Debug and diagnose errors in nvtripy code. Use when: interpreting TripyException stack traces, enabling MLIR/TensorRT debug output, understanding error…
tripy-documentation
nvidia
Write API documentation for nvtripy following project conventions. Use when: writing docstrings for ops or modules, adding code examples, using…
tripy-documentation
nvidia
Write API documentation for nvtripy following project conventions. Use when: writing docstrings for ops or modules, adding code examples, using…
tripy-new-module
nvidia
Add a new neural network module to nvtripy. Use when: creating an nn layer, implementing a Module subclass, adding a new layer like Linear/LayerNorm/Conv,…
tripy-new-module
nvidia
Add a new neural network module to nvtripy. Use when: creating an nn layer, implementing a Module subclass, adding a new layer like Linear/LayerNorm/Conv,…
tripy-new-operation
nvidia
Add a new operation to nvtripy. Use when: implementing a new op, adding a frontend op, creating a trace op, registering an op in the API. Covers the full…
tripy-new-operation
nvidia
Add a new operation to nvtripy. Use when: implementing a new op, adding a frontend op, creating a trace op, registering an op in the API. Covers the full…
tripy-testing
nvidia
Write tests for nvtripy following project conventions. Use when: adding tests for ops, modules, trace operations, or compilation, using pytest parametrize,…
tripy-testing
nvidia
Write tests for nvtripy following project conventions. Use when: adding tests for ops, modules, trace operations, or compilation, using pytest parametrize,…
troubleshooting
nvidia
Diagnose and resolve common issues including test failures, build errors, performance regressions, and development environment problems. Use this skill…
tui-development
nvidia
Guide for developing the OpenShell TUI — a ratatui-based terminal UI for the OpenShell platform. Covers architecture, navigation, data fetching, theming, UX…
tui-development
nvidia
Guide for developing the OpenShell TUI — a ratatui-based terminal UI for the OpenShell platform. Covers architecture, navigation, data fetching, theming, UX…
typescript
nvidia
Best practices for TypeScript code including type safety, discriminated unions, type guards, and exhaustive checking. Use this skill whenever the user asks…
underdeclared-agent
nvidia
A helpful assistant agent
update-docs
nvidia
Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages. Use when docs have fallen…
update-docs-from-commits
nvidia
Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages. Use when docs have fallen…
update-golden-values
nvidia
Refresh golden values from a GitHub Actions workflow run (failing-only or all jobs), score the change with average normalized relative differences, and produce…
update-project-version
nvidia
Update the NeMo Fabric release version across Cargo, setuptools package metadata, internal Python dependency pins, integration metadata, and lockfiles. Use…
update-project-version
nvidia
Update the NeMo Relay project version across Cargo, Node, and lockfiles without leaving release surfaces out of sync
update-project-version
nvidia
Update the NeMo Relay project version across Cargo, Node, and lockfiles without leaving release surfaces out of sync
validate-change
nvidia
Choose and run the right NeMo Relay validation matrix for a change instead of using one fixed test list
validate-change
nvidia
Choose and run the right NeMo Fabric validation matrix for a change instead of using one fixed test list
validate-change
nvidia
Choose and run the right NeMo Relay validation matrix for a change instead of using one fixed test list
validate-performance-quality
nvidia
Design benchmark, quality, and documentation validation for FlashDreams-style performance changes. Use when adding or updating sweep commands, profiler probes,…
vllm-setup
nvidia
Deploy a vLLM inference server on an NVIDIA DGX Station GB300 with validated container, GPU targeting, and tuning parameters. Use when the user asks to serve a…
vllm-setup
nvidia
Deploy a vLLM inference server on an NVIDIA DGX Station GB300 with validated container, GPU targeting, and tuning parameters. Use when the user asks to serve a…
vss-ask-video
nvidia
Use this skill to ask the VSS agent's video_understanding tool a fresh visual question about a recorded clip. Not for prior tool output, search hits, or…
vss-deploy-dense-captioning
nvidia
Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS…
vss-deploy-detection-tracking-2d
nvidia
Use this skill when the user wants to deploy, run, debug, tear down, or call the REST API of the RTVI-CV 2D detection / tracking microservice. Trigger when the…
vss-deploy-detection-tracking-3d
nvidia
Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the…
vss-deploy-profile
nvidia
Use to select, configure, deploy, verify, debug, or tear down a VSS profile (base, search, lvs, warehouse, edge). Not for standalone microservices — use the…
vss-deploy-video-embedding
nvidia
Use this skill when deploying, operating, or integrating the VSS 3.2 GA RT-Embed Video Embedding microservice. Covers Docker Compose bring-up, GPU and storage…
vss-generate-video-calibration
nvidia
Use to run AutoMagicCalib on local MP4s, RTSP, or the bundled sample dataset, and to deploy vss-auto-calibration when needed. Do not use for non-AMC…
vss-generate-video-report
nvidia
Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization,…
vss-manage-alerts
nvidia
Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert…
vss-manage-video-io-storage
nvidia
Use to call the VIOS REST API (sensor list, timelines, clip extraction, snapshots, add/delete sensors and streams). Not for VLM inference or search.
vss-query-analytics
nvidia
Use this skill when reading video-analytics metrics, incidents, alerts, and sensor data via the VA-MCP server (port 9901). Not for live VLM or incident-range…
vss-search-archive
nvidia
Use this skill to run top-level VSS fusion search on archived video, or to ingest video files / RTSP streams for search. Do NOT use for ad-hoc visual Q&A (use…
vss-setup-behavior-analytics
nvidia
Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
vss-setup-video-analytics-api
nvidia
Use to deploy the vss-video-analytics-api REST service standalone (config-source, data-log bind, Elasticsearch, optional Kafka). Not for full warehouse deploy.
vss-summarize-video
nvidia
Use to summarize a recorded video via the LVS summarization microservice (HITL-gated) with a VLM fallback. Not for report generation or live RTSP captioning.
warp-closing-issue
nvidia
Use when the user provides Warp commit SHA(s) and GitHub issue number(s) to assess, draft issue comments, post progress updates, or recommend whether issue…
warp-closing-issue
nvidia
Use when the user provides Warp commit SHA(s) and GitHub issue number(s) to assess, draft issue comments, post progress updates, or recommend whether issue…
warp-compile-time-optimizer
nvidia
Use when compile time or startup time is the problem in code that uses Warp: a request to improve, optimize, or cut compile times; an app that is slow to start…
warp-debug-gradients
nvidia
Use to diagnose and fix incorrect gradients in differentiable Warp programs. Anything trained, optimized, calibrated, or fit through Warp kernels depends on…
warp-eval
nvidia
Evaluate whether an existing hot path is a credible NVIDIA Warp candidate. Use for irregular or spatial queries, particle or geometry simulation, branch-heavy…
watch-github-actions
nvidia
Watch and monitor GitHub Actions workflow runs using the gh CLI. Use when the user wants to check workflow status, watch a running workflow, view CI/CD jobs,…
watch-github-actions
nvidia
Watch and monitor GitHub Actions workflow runs using the gh CLI. Use when the user wants to check workflow status, watch a running workflow, view CI/CD jobs,…
watchtower
nvidia
Run a scheduled web-surveillance sweep over a watchlist of topics using Tavily web_search, optional Tavily extraction, deterministic dedup/exclusion filtering,…