- Authoring TypescriptBest practices for TypeScript code including type safety, discriminated unions, type guards, and exhaustive checking. Use this skill whenever the user asks about TypeScript patterns, type safety, type assertions (as any, as unknown), non-null assertions, discriminated unions, exhaustive switch/never patterns, type guards, boolean trap parameters, race conditions in async code, memory leaks from closures, or sequential vs parallel async operations. Also trigger when reviewing TypeScript code for NVIDIA/elements93
- Build Your AppBuild, adapt, run, or verify an application on NVIDIA xr-ai, whether or not the repository has already been cloned.NVIDIA/xr-ai93
- Design Rule SweepPeriodic cleanup of srt-slurm drift - shrink the Design Rule baselines, fix stale agent docs, and open small focused PRs.NVIDIA/srt-slurm93
- Dsight QueryAnalyze existing DSight reports through the read-only SQLite-backed CLI, Python or MCP query interface. Use when inspecting request latency, lifecycle, metrics, Nsight ranges or CPU samples, comparing runs, or gathering evidence for a dashboard view.NVIDIA/srt-slurm93
- ElementsUse this skill by default for any UI-related work or with NVIDIA Elements (nve-*), including creating, editing, reviewing, or debugging HTML, CSS, layout, theming, components, applications, prototypes, Claude Artifacts, Codex Sites pages, and standalone UI artifacts.NVIDIA/elements93
- Getting StartedGet set up to build on the NVIDIA xr-ai stack (XR AI / DeviceIOHub). Use when a user asks to install, clone, or do initial setup of xr-ai; not for routine work in an already-set-up clone.NVIDIA/xr-ai93
- Gh Manage Xr Ai ReviewsManage a user-provided inbox of NVIDIA XR-AI pull request reviews and provide convenient overall status. Use when the user sends multiple PRs to review, asks what reviews remain, requests a review-status summary, asks to check for new feedback or commits, resumes several in-flight reviews, or authorizes a batch of review comments. Track each PR independently from intake through re-review, refresh GitHub state, use bounded subagents for analysis, and apply the comment-only XR-AI review contract wNVIDIA/xr-ai93
- Gh Review Xr AiReview NVIDIA XR-AI pull requests with strict change-scope discipline and independent subagent verification. Use when inspecting, re-reviewing, drafting feedback for, or posting a review on an XR-AI PR. Verify the PR description, diff, surrounding code, tests, scope, and existing reviews; report only change-caused blockers and nits in one top-level comment; route pre-existing or unrelated problems to self-contained follow-up work; and never approve automatically.NVIDIA/xr-ai93
- Github DependabotUse the GitHub CLI to retrieve current open `Dependabot` alerts for a repository, inspect affected dependencies and patched versions, update manifests and lock files, and verify the local fixes. Use whenever a user asks to inspect, address, resolve, remediate, or fix `Dependabot` alerts or dependency security vulnerabilities reported by GitHub. Use `gh`, rather than a browser or GitHub connector, for alert discovery.NVIDIA/elements93
- Guidance Api DesignComponent API design patterns following Elements conventions for properties, attributes, CSS custom properties, slots, and events. Use this skill whenever the user is designing or deciding on a component API, choosing between properties vs attributes vs slots, naming CSS custom properties, designing events, avoiding impossible states, deciding whether to reflect to an attribute, using CSS Parts, implementing the DataElement interface, or applying the internal-host pattern. Also trigger when the NVIDIA/elements93
- Guidance BuildWireit orchestration, build optimization, caching strategies, and build troubleshooting for the Elements monorepo. Use this skill whenever the user asks about Wireit configuration, build tasks, build dependencies, cache invalidation, build performance, adding new build tasks to package.json, cross-package dependency patterns, sideEffects declarations, CI pipeline configuration, or diagnosing slow or failing builds. Also trigger when the user mentions wireit, vite build issues, pnpm run ci, or buNVIDIA/elements93
- Guidance Webgpu PerformanceDiagnose and improve browser WebGPU rendering performance, including frame pacing, draw and state-submission overhead, buffer uploads, shaders, and JavaScript work on the render critical path. Use for slow or stuttering GPU-backed interfaces, rendering regressions, CPU/GPU bottleneck analysis, renderer performance changes, or WebGPU resource, timing, diagnostic, and lifecycle test suites; do not use for general page-load, build performance, or CPU-only benchmark work.NVIDIA/elements93
- Perf Goal WriterWrite or refine a ready-to-use /goal prompt for a performance benchmark, regression investigation or optimization campaign. Define measurable targets, a matched baseline, change boundaries, diagnostic evidence and completion criteria. Use for drafting the goal, not executing the campaign.NVIDIA/srt-slurm93
- Slurm Job SizingSize Slurm allocations, warmup and traffic for short debugging jobs or full srt-slurm benchmarks.NVIDIA/srt-slurm93
- SrtctlRun srt-slurm (srtctl) inference benchmarks on a Slurm cluster. Use when setting up a checkout, writing or migrating a recipe, submitting a job, or reading its results.NVIDIA/srt-slurm93
- Summarize ReleasesCreate a monthly NVIDIA Elements “What’s New” docs page, matching video, and concise, copy-ready summary from local release tags, tagged changelogs, package versions, and commit history. Use for a scheduled release PR, monthly update, release roundup, changelog digest, Slack blurb, announcement, or plain-language explanation of recent Elements releases.NVIDIA/elements93
- Summarize Video ReleasesCreate the 24–36 second marketing video for a monthly NVIDIA Elements “What’s New” post, rendered to projects/site/public/static/video/releases/MM-YYYY.webm from real Elements components, with feature snapshots inserted into the post. Use after the summarize-releases skill creates or updates a post, and whenever someone asks for a release video, what’s new video, monthly recap clip, changelog teaser, social video, or animated summary of Elements releases, even if they do not say “video skill”.NVIDIA/elements93
- TroubleshootingDiagnose and resolve common issues including test failures, build errors, performance regressions, and development environment problems. Use this skill whenever the user reports something broken, failing, timing out, hanging, or producing unexpected results. Trigger on test failures (elementIsStable timeouts, flaky tests, screenshot diffs), build errors (Cannot find module, wireit cache issues, stale output), CI/CD failures, Git LFS problems, port conflicts, lighthouse score regressions, SSR errNVIDIA/elements93
- Validate Without ClusterVerify an srt-slurm change end to end without SLURM or GPUs, using dry-run, the mock orchestrator, and the launch snapshots.NVIDIA/srt-slurm93
- Update Rapids VersionUpdates python code (e.g. internal api calls) so that tests pass after running in conda environment with updated rapids version.NVIDIA/cuml-spark92
- Capture LearningAppend a learning to agent-learnings.md when the agent or user identifies a mistake, non-obvious pattern, or useful convention worth remembering. Use when the user says "capture this", "remember this", or "add to learnings".NVIDIA/multi-storage-client85
- Cloud Storage SetupSet up MSC credentials and MCP server integration for cloud storage access. Use when the user wants to interact with cloud storage (S3, GCS, Azure, OCI), asks to set up credentials, connect to a bucket, list objects, move files, or sync data. Checks for existing config first — only runs interactive setup if credentials are missing.NVIDIA/multi-storage-client85
- Fix CveFix CVE vulnerabilities by upgrading affected dependencies across Python (uv), and Rust layers. Use when the user mentions CVE numbers, asks to fix security vulnerabilities, or asks to patch dependencies for CVEs.NVIDIA/multi-storage-client85
- Generate SpecProduce a feature specification covering API changes, backward compatibility, cross-language impact, performance, and a file-level change plan. Use when designing a new feature, planning a significant change, or the user asks to spec something out.NVIDIA/multi-storage-client85
- Generate Test PlanProduce a test plan with specific test names, assertions, and coverage across Python and Rust. Use when planning tests for a feature, after generating a spec, or the user asks for a test plan.NVIDIA/multi-storage-client85
- Prepare MrStage files, commit with correct format, push, and generate an MR description. Manual invocation only — has side effects (git operations). Use when the user explicitly asks to prepare, create, or submit an MR.NVIDIA/multi-storage-client85
- Release AutomationPrepares and automates the release process for multi-storage-client (version bump, release notes, checklist). Use when the user wants to cut a release, bump version, prepare release, publish a new version, or automate release steps.NVIDIA/multi-storage-client85
- ResearchBefore designing a feature, research how comparable libraries solve the problem, check best practices, known pitfalls, and upstream changes. Use when starting a new feature, investigating an unfamiliar area, or the user asks to research something.NVIDIA/multi-storage-client85
- Cre TestUse when writing, running, or debugging tests in this repo. Covers the testutil.TestCaseParser golden-file pattern, integration tests, golden file regeneration, and the full verification suite.NVIDIA/cluster-readiness-engine71
- Managing OpenvexUse when adding, updating, or removing CVE/GHSA suppressions in `.openvex.json`, or when acting on a finding reported by the weekly image vulnerability scan. Triggers on "VEX", "OpenVEX", ".openvex.json", "suppress CVE", "ignore CVE", "vulnerability suppression", or any request to act on the Slack alert from `Vulnerability Scan (images)`.NVIDIA/cluster-readiness-engine71
- Release NotesUse when drafting the human-readable highlights summary for an NVCRE release. Triggers on "release notes", "draft release notes", "/release-notes", or any request to summarize what shipped since the last tag into a release announcement. Resolves the tag range from the GitHub releases API, groups changes into thematic highlights, and writes a Markdown draft to a temp file for hand-editing before it is pasted into the release body.NVIDIA/cluster-readiness-engine71
- Hoisa Deploy ProfileDeploy Halos Outside-In Safety (HOISA) closed-loop testing by PROFILE (base / sil / hil) on top of the VSS Warehouse 3.2.1 perception backend. Clone the OSS repo, pick a profile, deploy. Covers prerequisites, NGC artifacts (sil-data + PSF + VSS images), VSS SIL overrides, the Halos stack (PSF, comm-layer, Isaac Sim, forklift-controller), test scenario, and monitoring. Use when asked to deploy Halos, deploy HOISA, deploy SIL, set up warehouse safety simulation, or run outside-in safety testing.NVIDIA/halos-outside-in-safety67
- Hoisa Generate Regression ReportRun the Regression Testing Reporter (`srr`) multi-scenario test pipeline on the SIL stack. Picks one or more of 6 pre-built test cases (in-roi, psf-edge, psf-clear, balanced, fast, fixed), launches each in Isaac Sim with a clean compose restart, records 30 Hz parquet of GT + Safety Core state + BA / 3D perception Kafka events, splits by forklift tripwire crossings, and runs the aggregator to produce per-clip match% + Phase 2 perception reports, per-clip MP4 videos, and optional heatmaps. Use wheNVIDIA/halos-outside-in-safety67
- Docs ComplianceACCV-Lab documentation conventions and pre-PR compliance check. INVOKE when creating or editing any .md or .rst file under docs/ or packages/*/docs/, when modifying a Python module/class/function/method docstring, or before opening a PR that touches documentation. Provides hard rules for Sphinx role usage, docstring formatting, public-API export requirements, admonition syntax, and a pre-PR checklist with verification commands.NVIDIA/ACCV-Lab66
- Skill Card GeneratorUse only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.NVIDIA/Trustworthy-AI62
- Analysis ScriptsWrite and run Python scripts to analyze quantum experiment data stored in HDF5 files. Use when the user asks to analyze experiment results, fit peaks or curves, extract features from measurement arrays, or when reusable analysis logic should be saved alongside an experiment for future reuse.NVIDIA/Quantum-Calibration-Agent-Blueprint61
- Experiment ExecutionReference guide for running individual quantum calibration experiments and interpreting their results. Use when the user asks to run a single experiment (e.g. resonator spectroscopy, qubit spectroscopy, T1, T2), inspect experiment plots with the VLM, or query experiment history and schemas via the lab tool.NVIDIA/Quantum-Calibration-Agent-Blueprint61
- Vlm ConfigurationConfigure the Vision Language Model (VLM) used for analyzing experiment plots. Use when the user asks to change the VLM provider or model, adjust temperature or max_tokens, enable or disable thinking mode, or troubleshoot VLM-related behavior in config.yaml.NVIDIA/Quantum-Calibration-Agent-Blueprint61
- Workflow ExecutionExecute a previously planned calibration workflow node by node, tracking progress and handling failures. Use when the user asks to run, resume, or continue an existing workflow, or to execute a sequence of calibration steps that has already been defined in data/workflows/.NVIDIA/Quantum-Calibration-Agent-Blueprint61
- Workflow PlanningPlan a new calibration workflow by discussing experiment sequences, success/failure criteria, and extracted parameters with the user before any files are created. Use when the user asks to plan, design, or create a new calibration sequence, or to build a multi-step workflow for a qubit or device. Requires explicit user confirmation before writing workflow files.NVIDIA/Quantum-Calibration-Agent-Blueprint61
- Writing Experiment ScriptsAuthor new experiment scripts that are compatible with the lab system's auto-discovery. Use when the user asks to create a new experiment type, add a custom measurement, or write a Python script that should be discoverable via the `lab` and `run_experiment` tools. Covers required function signatures, type hints, docstrings, and return formats.NVIDIA/Quantum-Calibration-Agent-Blueprint61
- Deepstream SopUse this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on inNVIDIA/sop-monitoring-blueprints56
- Sop BuildOrchestrate the end-to-end SOP pipeline, including preflight prerequisite checks, verifying models and downloading assets, generating the DeepStream SOP microservice with RTSP output, evaluating the microservice, and building, deploying, and testing the VSS SOP blueprint. Use when asked to run the full SOP pipeline, set up the SOP pipeline from scratch, execute preflight checks, verify models, download assets, generate the SOP microservice, evaluate the microservice, build the VSS blueprint, depNVIDIA/sop-monitoring-blueprints56
- Sop By Action EvalUse when running by-action VLM evaluation (per-action-clip inference + accuracy metrics) against the BP evaluation-ms HTTP API. Invoked as /sop-by-action-eval <inputs.yaml> [natural language parameter overrides]NVIDIA/sop-monitoring-blueprints56
- Sop Cr FinetuningFine-tune Cosmos-Reason2 (CR2) VLM for SOP monitoring. Use when you need to launch and monitor a VLM training run with a given dataset ID.NVIDIA/sop-monitoring-blueprints56
- Sop Data AugmentationUse when the user wants to run data augmentation on an annotated dataset, configure augmentation parameters, check augmentation status, or understand what each QA augmentation type does (BCQ, MCQ, GQA, DMCQ, DSQA, ENQA, WMCQ)NVIDIA/sop-monitoring-blueprints56
- Sop Ddm FinetuningFine-tune DDM-Net temporal boundary detector for SOP monitoring. Use when you need to launch and monitor a DDM-Net training run with a given dataset ID.NVIDIA/sop-monitoring-blueprints56
- Sop E2e InferenceUse when running the e2e evaluation pipeline (temporal segmentation + action recognition + accuracy) against the BP evaluation-ms HTTP API. Invoked as /sop-e2e-inference <inputs.yaml> [natural language parameter overrides]NVIDIA/sop-monitoring-blueprints56
- Sop Ft OrchestrateAutonomous end-to-end orchestrator for SOP fine-tuning. Runs the full Import → Augment → DDM Train → VLM Train → Evaluate → RCA loop. Interprets RCA findings across DDM, VLM and augment axes, applies config fixes autonomously, and iterates until success criteria are met or max_pipeline_iterations reached. Call with a path to an inputs.yaml or with natural language.NVIDIA/sop-monitoring-blueprints56
- Sop RcaRoot cause analysis for SOP monitoring pipeline failures. Analyzes end-to-end evaluation logs, DDM temporal segmentation, VLM action recognition, training data, and fine-tuning configs to identify failure patterns and produce an evidence-driven RCA report with actionable improvement recommendations.NVIDIA/sop-monitoring-blueprints56
- Vss Call Vios ApiInteract with the VIOS (Video IO & Storage) microservice in a running VSS profile — manage cameras/sensors, RTSP streams, recordings, snapshots, and storage. Use when asked to add a camera, add an RTSP stream, list sensors, show configured sensors/cameras/streams, what sources are available, check stream status, start/stop recording, get a snapshot, or manage video storage. Always query the VIOS API directly — do not navigate the UI to answer these questions.NVIDIA/sop-monitoring-blueprints56
- Vss Generate Video ReportGenerate and query incident reports from VSS — look up incidents in Elasticsearch, analyze incident patterns, generate narrative reports. Use when asked about incidents, incident reports, PPE violations, safety events, or "what happened". Requires the alerts profile to be deployed.NVIDIA/sop-monitoring-blueprints56
- Vss Query AnalyticsQuery video analytics incidents, alerts, sensor data, and metrics from Elasticsearch via the VA-MCP server (port 9901). Use for any question about what happened in video — PPE violations, alerts, incidents, object counts, speeds, occupancy, or anything that requires looking up recorded events. This is the primary way to answer "what happened", "show me alerts", "any violations", "how many people", etc.NVIDIA/sop-monitoring-blueprints56
- Vss Search ArchiveSearch video archives using natural language — find events, objects, actions, and people across recorded video using Cosmos Embed1 semantic search. Use when asked to search for something in video, find events, locate objects, or query video archives. Requires the search profile to be deployed.NVIDIA/sop-monitoring-blueprints56
- Vss Sop BuildBuild a custom VSS SOP blueprint from the VSS 3.1 base, then deploy and test in a loop until fully operational. Use when asked to create the SOP blueprint structure, customize VSS compose for SOP, configure SOP services, set up the VSS agent for SOP, or scaffold the SOP app layer on top of met-blueprints 3.1.NVIDIA/sop-monitoring-blueprints56
- Vss Sop DeployBuild the DS-SOP Docker image and deploy the VSS SOP blueprint end-to-end. Use when asked to deploy SOP, build DS SOP, install SOP, set up the SOP pipeline, verify SOP models, start the SOP blueprint, simulate RTSP for SOP, run the SOP API test, or tear down SOP.NVIDIA/sop-monitoring-blueprints56
- Vss Sop TestRun post-deployment tests for the VSS SOP blueprint. Checks service health, ELK data pipeline, VIOS recording/livestream, and VSS agent (MCP, LLM, VLM, snapshot, video, report). Auto-debugs failures. Use when asked to test SOP, verify SOP deployment, check SOP services, validate SOP, run SOP health checks, or troubleshoot SOP after deploy.NVIDIA/sop-monitoring-blueprints56
- Vss Summarize VideoSummarize long videos, generate shift reports, and analyze extended recordings. Use when asked to summarize a video, generate a shift summary, analyze a long recording, or create a daily activity report. Requires the LVS profile to be deployed.NVIDIA/sop-monitoring-blueprints56
- Add FilterGuide for adding a new filter to PhysicsNeMo Curator. Covers discovery questions, implementation patterns (pass-through, stateful, in-place), generator semantics, flush/artifacts, dashboard widgets, merge for parallel workers, testing, and registration.NVIDIA/physicsnemo-curator55
- Add SinkGuide for adding a new sink to PhysicsNeMo Curator. Covers discovery questions, implementation patterns (simple writer, append-based, split-based), output naming, parallel partitioning, testing, and registration.NVIDIA/physicsnemo-curator55