Skill Claude CodeCodex ✓ vendor
Review AI agent skills before installation using NVIDIA SkillSpector and source-aware semantic review. Use when asked whether a skill or downloaded skill folder is safe, trustworthy, installable, over-permissioned, or malicious.
Command Claude CodeOpenCode ✓ vendor
Scan an AI agent skill for security risks with SkillSpector (static analysis by default); use when vetting a skill before install or auditing one in use.
Skill Claude CodeCodex ✓ vendor
Debug inference clients that use an attached provider and its native endpoint, including hosted APIs and host-local Ollama, vLLM, SGLang, TRT-LLM, LM Studio, or NIM. Use for provider attachment, endpoint policy, credential substitution, topology, and migration from the removed managed inference endpoint. Trigger…
Skill Claude CodeCodex ✓ vendor
Debug why an OpenShell gateway deployment is unhealthy, unreachable, or unable to create sandboxes. Use for gateway health failures, Docker/Podman runtime issues, Helm failures, Kubernetes scheduling, TLS or auth, gateway interceptors, supervisor middleware startup or runtime failures, external compute-driver sockets…
Skill Claude CodeCodex ✓ vendor
Generate sandbox security policies from plain-language requirements and optional REST API documentation. Produces L4 or fine-grained L7 network policies and ordered network middleware configuration. Use for API access rules, middleware host selection, failure behavior, or built-in and operator-run middleware…
Skill Claude CodeCodex ✓ vendor
Guide agents through using the OpenShell CLI (openshell) for sandbox management, gateway registration, provider configuration and refresh, profile management, policy iteration, settings, service exposure, BYOC workflows, and attached-provider inference. Covers basic through advanced multi-step workflows. Trigger…
Skill Claude CodeCodex ✓ vendor
Use when an OpenShell sandbox returns policydenied, mentions policy.local, or needs a narrow network policy proposal.
Skill Claude CodeCodex ✓ vendor
Validate and monitor OpenShell GitHub issues and PRs using the gator: state machine. Use when asked to triage issues/PRs for project validity, gate PRs, run gator, validate submissions, or monitor PRs toward merge readiness.
Skill Claude Code ✓ vendor
Launch and operate this repo's perf-analyze workflow, which DIAGNOSES a TensorRT-LLM serving deployment without applying changes — benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill), nsys + ncu per-kernel…
Skill Claude Code ✓ vendor
Launch and operate this repo's perf-optimize workflow, which iteratively APPLIES TensorRT-LLM serving optimizations — baseline benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill) sizing the headroom the…
Skill Claude CodeCodex ✓ vendor
Load before implementing, modifying or certifying a TensorRT-LLM ModelingV2 catalog entry (OpWrapper) or its GPU test, including verification at new shapes/dtypes/architectures and target-local variants. Not needed for catalog discovery, assembling a target from unchanged entries, running model-level gates, or tuning…
Skill Claude CodeCodex ✓ vendor
Load when working on, testing or debugging a TensorRT-LLM engine feature around a ModelingV2 target -- KV-cache block (prefix) reuse, disaggregated serving, chunked prefill, KV-cache dtype (fp8/nvfp4 and their scales), CUDA graphs and the overlap scheduler, multimodal inputs, speculative decoding, or…
Plugin Claude Code ✓ vendor
Bundles 16 skills · 1,571 tokens together
Skills for Model Optimizer development, quantization, deployment, and evaluation.
Agent Claude Code ✓ vendor
../../plugins/modelopt/agents/modelopt-model-downloader.md.
Agent Claude Code ✓ vendor
../../plugins/modelopt/agents/modelopt-model-evaluator.md.
Agent Claude Code ✓ vendor
../../plugins/modelopt/agents/modelopt-model-performance-benchmarker.md.
Agent Claude Code ✓ vendor
../../plugins/modelopt/agents/modelopt-model-quantize-recipe-searcher.md.
Agent Claude Code ✓ vendor
../../plugins/modelopt/agents/modelopt-model-quantizer.md.
Agent Claude Code ✓ vendor
../../plugins/modelopt/agents/modelopt-model-distiller.md.
Plugin Claude Code ✓ vendor
Bundles 1 skill · 142 tokens together
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered workflows.
Skill Claude CodeCodex ✓ vendor
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
Skill Claude Code needs its repo ✓ vendor
Use when asked to install, deploy, run, validate, troubleshoot, or stop NVIDIA AI-Q Blueprint infrastructure.
Skill Claude Code ✓ vendor
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
Skill Claude CodeCodex ✓ vendor
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; VIOS records clips, AMC ingests them, then runs calibration.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: