SKILLSET · TRACKS main
Agent Skills for NVIDIA products — install into Claude Code, Codex, and other coding agents to run Physical AI, robotics, simulation, CUDA, and RAG workflows end to end.
skillmarket install-set greatsage_sh/nvidia-skillsOfficial 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.
skillmarket install greatsage_sh/accelerated-computing-cudf|
skillmarket install greatsage_sh/aiq-deploy|
skillmarket install greatsage_sh/aiq-researchRun 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 dataset', 'run sample calibration', 'verify AMC install', or 'launch and test'.
skillmarket install greatsage_sh/amc-run-sample-calibrationCalibrate 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 these videos', or similar. For RTSP/live streams, use amc-run-rtsp-calibration instead.
skillmarket install greatsage_sh/amc-run-video-calibrationLaunch AutoMagicCalib microservice and web UI from NGC release images via Docker Compose. Use when user says 'deploy auto calibration', 'launch auto calibration', 'launch AMC', 'start MS+UI', or 'set up auto-magic-calib'. Requires NGC API key.
skillmarket install greatsage_sh/amc-setup-calibration-stackCUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.
skillmarket install greatsage_sh/cudaq-guideUse when a user asks to build, optimize, backtest, rebalance, or analyze a stock portfolio with Mean-CVaR, efficient frontiers, scenario generation, or NVIDIA cuOpt.
skillmarket install greatsage_sh/cufolioModify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
skillmarket install greatsage_sh/cuopt-developerInstall cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.
skillmarket install greatsage_sh/cuopt-installTrace and interpret the Pareto frontier across competing objectives using repeated single-objective cuOpt solves (weighted-sum and ε-constraint).
skillmarket install greatsage_sh/cuopt-multi-objective-explorationLP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.
skillmarket install greatsage_sh/cuopt-numerical-optimization-formulationVehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.
skillmarket install greatsage_sh/cuopt-routing-api-pythoncuOpt REST server — start server, endpoints, Python/curl client examples. Use when the user is deploying or calling the REST API.
skillmarket install greatsage_sh/cuopt-server-api-python>-
skillmarket install greatsage_sh/cupynumeric-hdf5Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.
skillmarket install greatsage_sh/cupynumeric-installPre-migration readiness assessor for porting NumPy to cuPyNumeric. Use BEFORE substantial porting work begins when the user asks whether code will scale on GPU, whether they should migrate to cuPyNumeric, which NumPy patterns transfer cleanly, what must be refactored before porting, or mentions pre-port assessment, scaling analysis, or refactor planning. Inspect the user's source code, look up NumPy usage, cross-reference the cuPyNumeric API support manifest, and distinguish distributed-scaling-
skillmarket install greatsage_sh/cupynumeric-migration-readinessLoad a sharded, on-disk dataset (sharded .npy, Parquet/Arrow, raw binary, sharded HDF5, custom layouts) into a distributed cuPyNumeric ndarray via a manual partition + leaf @task launch with CPU/OMP/GPU variants. Use when no single-call loader fits, including when per-shard row counts differ across files. Prefer cupynumeric.load or legate.io.hdf5.from_file when they apply.
skillmarket install greatsage_sh/cupynumeric-parallel-data-loadDALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.
skillmarket install greatsage_sh/dali-dynamic-modeUse when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
skillmarket install greatsage_sh/data-designerNVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.
skillmarket install greatsage_sh/deepstream-devProfile a DeepStream pipeline with Nsight Systems and derive its configs from the measurement. Use when the user asks for an efficient, performant, or profiled pipeline — or to benchmark, tune, or measure FPS.
skillmarket install greatsage_sh/deepstream-profile-pipelineUsed for extracting selected metadata from one DICOM file and flagging standard-tag PHI presence. Not for anonymization or clinical use.
skillmarket install greatsage_sh/dicom-metadata-extractUsed for header-only preflight of one DICOM series folder before conversion or inference. Not for de-identification or clinical clearance.
skillmarket install greatsage_sh/dicom-series-preflightUsed for converting one CT DICOM series folder to a HU NIfTI volume with affine evidence. Not for multi-frame DICOM or clinical use.
skillmarket install greatsage_sh/dicom-series-to-volumeStage 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).
skillmarket install greatsage_sh/digital-health-clinical-asr-buildStage 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).
skillmarket install greatsage_sh/digital-health-clinical-asr-evalStage 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 generic word boosting (use /finetune-asr).
skillmarket install greatsage_sh/digital-health-clinical-asr-finetuneStage 1 of Clinical ASR Flywheel. Use when bootstrapping a cycle: NVCF+MW disclosure, NVIDIA_API_KEY check, deps install, TTS+ASR smoke test.
skillmarket install greatsage_sh/digital-health-clinical-asr-setup>
skillmarket install greatsage_sh/doca-aes-gcm>
skillmarket install greatsage_sh/doca-argp>
skillmarket install greatsage_sh/doca-argus>
skillmarket install greatsage_sh/doca-bare-metal-deployment>
skillmarket install greatsage_sh/doca-bench>
skillmarket install greatsage_sh/doca-bench-extension>
skillmarket install greatsage_sh/doca-bf3-deployment>
skillmarket install greatsage_sh/doca-bf4-deployment>
skillmarket install greatsage_sh/doca-caps>
skillmarket install greatsage_sh/doca-collectx-deployment>
skillmarket install greatsage_sh/doca-comch>
skillmarket install greatsage_sh/doca-comm-channel-admin>
skillmarket install greatsage_sh/doca-common>
skillmarket install greatsage_sh/doca-compress>
skillmarket install greatsage_sh/doca-container-deployment>
skillmarket install greatsage_sh/doca-debug>
skillmarket install greatsage_sh/doca-devemu>
skillmarket install greatsage_sh/doca-dma>
skillmarket install greatsage_sh/doca-dms>
skillmarket install greatsage_sh/doca-dpa>
skillmarket install greatsage_sh/doca-dpa-hl-tracer>
skillmarket install greatsage_sh/doca-dpdk-bridge>
skillmarket install greatsage_sh/doca-erasure-coding>
skillmarket install greatsage_sh/doca-eth>
skillmarket install greatsage_sh/doca-firefly>
skillmarket install greatsage_sh/doca-flow>
skillmarket install greatsage_sh/doca-flow-dpa-perf>
skillmarket install greatsage_sh/doca-flow-dpa-provider>
skillmarket install greatsage_sh/doca-flow-grpc-server>
skillmarket install greatsage_sh/doca-flow-perf>
skillmarket install greatsage_sh/doca-flow-tune>
skillmarket install greatsage_sh/doca-gpi>
skillmarket install greatsage_sh/doca-gpunetio>
skillmarket install greatsage_sh/doca-gpunetio-ib-write-bw>
skillmarket install greatsage_sh/doca-gpunetio-ib-write-lat>
skillmarket install greatsage_sh/doca-hardware-safety>
skillmarket install greatsage_sh/doca-mgmt>
skillmarket install greatsage_sh/doca-pcc>
skillmarket install greatsage_sh/doca-pcc-counters>
skillmarket install greatsage_sh/doca-pcc-ztr-rttcc-algo>
skillmarket install greatsage_sh/doca-programming-guide>
skillmarket install greatsage_sh/doca-public-knowledge-map>
skillmarket install greatsage_sh/doca-rdma>
skillmarket install greatsage_sh/doca-rdmi>
skillmarket install greatsage_sh/doca-rmax>
skillmarket install greatsage_sh/doca-setup>
skillmarket install greatsage_sh/doca-sha>
skillmarket install greatsage_sh/doca-sha-offload-engine>
skillmarket install greatsage_sh/doca-socket-relay>
skillmarket install greatsage_sh/doca-spcx-cc>
skillmarket install greatsage_sh/doca-sta>
skillmarket install greatsage_sh/doca-structured-tools-contract>
skillmarket install greatsage_sh/doca-telemetry>
skillmarket install greatsage_sh/doca-telemetry-exporter>
skillmarket install greatsage_sh/doca-telemetry-utils>
skillmarket install greatsage_sh/doca-upgrade>
skillmarket install greatsage_sh/doca-urom>
skillmarket install greatsage_sh/doca-urom-svc>
skillmarket install greatsage_sh/doca-verbs>
skillmarket install greatsage_sh/doca-versionValidate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink. Use after recipe-runner brings a deployment up (especially disagg/multi-node) to confirm the KV transport is correct; use troubleshoot for diagnosing already-failed pods.
skillmarket install greatsage_sh/dynamo-interconnect-checkSelect, validate, patch, and deploy existing NVIDIA Dynamo Kubernetes recipes. Use for model/backend/GPU/deployment-mode recipe bring-up; use router-starter for router-only mode work and troubleshoot for broken deployments.
skillmarket install greatsage_sh/dynamo-recipe-runnerStart 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 recipe-runner for recipe deployment and troubleshoot for failure diagnosis.
skillmarket install greatsage_sh/dynamo-router-starterDiagnose failed or unhealthy Dynamo deployments. Use when pods, model-cache jobs, PVCs, workers, frontend/router health, endpoints, or benchmark jobs fail; use recipe-runner/router-starter before this for normal bring-up.
skillmarket install greatsage_sh/dynamo-troubleshoot>
skillmarket install greatsage_sh/earth2studio-create-datasource>
skillmarket install greatsage_sh/earth2studio-create-diagnostic>
skillmarket install greatsage_sh/earth2studio-create-prognostic>
skillmarket install greatsage_sh/earth2studio-data-fetch>
skillmarket install greatsage_sh/earth2studio-deterministic-forecast>
skillmarket install greatsage_sh/earth2studio-discover>
skillmarket install greatsage_sh/earth2studio-installInstall Holoscan SDK v4.3+ via Conda in a CUDA 13 environment. Use for Conda installs; redirect CUDA 12 hosts to container/wheel.
skillmarket install greatsage_sh/holoscan-install-condaInstall Holoscan SDK via the NGC Docker container. Use for container-based installs; not for native apt/pip/Conda installs.
skillmarket install greatsage_sh/holoscan-install-containerInstall Holoscan SDK natively on Ubuntu via apt. Use for C++ installs on Ubuntu; pair with /holoscan-install-wheel for Python.
skillmarket install greatsage_sh/holoscan-install-debianBuild Holoscan SDK from source via the in-tree ./run script. Use only when published packages don't meet the user's needs.
skillmarket install greatsage_sh/holoscan-install-sourceInstall Holoscan SDK Python wheel via pip into a venv. Use for Python installs; not for native C++/apt or Conda installs.
skillmarket install greatsage_sh/holoscan-install-wheelGuides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.
skillmarket install greatsage_sh/holoscan-setupDiscover and run Holoscan Sensor Bridge example applications on a connected devkit. Filters available apps by the user's platform, HSB software version, board type, and sensors. Supports timed execution, failure analysis, code-edit suggestions, and iterative re-runs.
skillmarket install greatsage_sh/hsb-appFlash 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 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must never be mixed.
skillmarket install greatsage_sh/hsb-flashExecute 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 run automatically, executes them with pass/fail evaluation, and produces a structured test results report.
skillmarket install greatsage_sh/hsb-testOverview of `workflows/catheter_navigation/` (fluorosim DRR, XPBD physics, vasculature digital twin). Use when the user asks what the catheter navigation workflow is, what's supported, or where to start.
skillmarket install greatsage_sh/i4h-catheter-navigationBuild a patient vasculature digital twin from CT (preprocess + segment). Use when asked to preprocess CT, segment vessels, extract centerline, or prepare ct_cache for viewport/DRR.
skillmarket install greatsage_sh/i4h-catheter-navigation-digital-twinEnd-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 v0.7 pipeline.
skillmarket install greatsage_sh/i4h-catheter-navigation-e2eRender 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 renderer.
skillmarket install greatsage_sh/i4h-catheter-navigation-render-drrVerify host/GPU requirements and PYTHONPATH for the catheter navigation workflow. Use when asked to set up, install, or bootstrap catheter_navigation, or when hitting import/GPU/slangpy errors.
skillmarket install greatsage_sh/i4h-catheter-navigation-setupRun CPU-only fluorosim smoke tests (imports, preprocessing, CLI parsers). Use when asked to smoke-test catheter navigation in CI or without a GPU.
skillmarket install greatsage_sh/i4h-catheter-navigation-smokeLaunch the interactive Slang fluoroscopy viewport with XPBD catheter physics. Use when asked to open the viewport, teleop a catheter, or demo fluoro navigation.
skillmarket install greatsage_sh/i4h-catheter-navigation-viewportServe 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 HDF5 (use [[i4h-workflow-dataset-convert]]).
skillmarket install greatsage_sh/i4h-lerobot-vizOverview of `workflows/agentic/` (IsaacLab-Arena + GR00T/openpi). Use when the user asks what i4h workflow is, what's supported, or where to start.
skillmarket install greatsage_sh/i4h-workflowCreate a new agentic env by forking an existing env. Use for new env/task scaffolding, not scene edits or baking.
skillmarket install greatsage_sh/i4h-workflow-createUse 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 finetuning on a success classifier.
skillmarket install greatsage_sh/i4h-workflow-dataset-annotateConvert an agentic HDF5 recording into a LeRobot dataset (parquet, meta, videos). Use when asked to convert HDF5, prepare for training, or export to LeRobot; not for viewing — use [[i4h-lerobot-viz]].
skillmarket install greatsage_sh/i4h-workflow-dataset-convertExpand 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 (use [[i4h-workflow-dataset-teleop]]).
skillmarket install greatsage_sh/i4h-workflow-dataset-mimicReplay 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.
skillmarket install greatsage_sh/i4h-workflow-dataset-replayRecord 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.
skillmarket install greatsage_sh/i4h-workflow-dataset-teleopRun the full end-to-end agentic pipeline (record → mimic → annotate → replay → convert → visualize → finetune → validate). Use when asked to run the whole pipeline or do an e2e, smoke, or demo run.
skillmarket install greatsage_sh/i4h-workflow-e2eFine-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 checkpoint (use [[i4h-workflow-validate]]).
skillmarket install greatsage_sh/i4h-workflow-finetuneEdit 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 (`--bridge`), incl. a just-created env.
skillmarket install greatsage_sh/i4h-workflow-scene-editVerify host requirements and run `workflows/agentic/setup.sh`. Use when asked to set up, install, or bootstrap the agentic workflow, or hits missing `.venv`, third-party checkout, or engine errors.
skillmarket install greatsage_sh/i4h-workflow-setupValidate, evaluate, or run i4h envs. Use for policy/checkpoint rollouts and scripted state-machine smoke runs.
skillmarket install greatsage_sh/i4h-workflow-validate>-
skillmarket install greatsage_sh/jetson-build-sourceUse 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 tuning or nvpmodel edits.
skillmarket install greatsage_sh/jetson-customize-clocks>-
skillmarket install greatsage_sh/jetson-customize-fan>-
skillmarket install greatsage_sh/jetson-customize-mgbe>-
skillmarket install greatsage_sh/jetson-customize-nvpmodel>-
skillmarket install greatsage_sh/jetson-customize-pcie>-
skillmarket install greatsage_sh/jetson-customize-pinmuxConfigure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or PCIe-only edits.
skillmarket install greatsage_sh/jetson-customize-uphyEnable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.
skillmarket install greatsage_sh/jetson-customize-usb>-
skillmarket install greatsage_sh/jetson-derive-carrierRead-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
skillmarket install greatsage_sh/jetson-diagnostic>-
skillmarket install greatsage_sh/jetson-download-bspUse 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 carrier derivation.
skillmarket install greatsage_sh/jetson-flash-image>-
skillmarket install greatsage_sh/jetson-generate-kbPlan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.
skillmarket install greatsage_sh/jetson-headless-modePick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.
skillmarket install greatsage_sh/jetson-inference-mem-tune>-
skillmarket install greatsage_sh/jetson-init-image>-
skillmarket install greatsage_sh/jetson-init-source>-
skillmarket install greatsage_sh/jetson-init-target>-
skillmarket install greatsage_sh/jetson-link-docsBenchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.
skillmarket install greatsage_sh/jetson-llm-benchmarkStand 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.
skillmarket install greatsage_sh/jetson-llm-serveMeasure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.
skillmarket install greatsage_sh/jetson-memory-audit>-
skillmarket install greatsage_sh/jetson-optimize-memoryPick 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.
skillmarket install greatsage_sh/jetson-packageUse 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.
skillmarket install greatsage_sh/jetson-print-bsp-infoUse 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 example skill.
skillmarket install greatsage_sh/jetson-print-device-info>-
skillmarket install greatsage_sh/jetson-promote-image>-
skillmarket install greatsage_sh/jetson-quick-start>-
skillmarket install greatsage_sh/jetson-set-targetAdd EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.
skillmarket install greatsage_sh/jetson-speculative-decoding>-
skillmarket install greatsage_sh/jetson-validate-imagePlaybook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.
skillmarket install greatsage_sh/launch-nemo-rlInvestigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
skillmarket install greatsage_sh/mcore-create-issueLinting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
skillmarket install greatsage_sh/mcore-linting-and-formattingHow to launch distributed Megatron-LM training jobs on a SLURM cluster. Covers a minimal sbatch skeleton, environment-variable setup for torch.distributed.run, CUDA_DEVICE_MAX_CONNECTIONS rules across hardware and parallelism modes, container conventions, monitoring, and per-rank failure diagnosis.
skillmarket install greatsage_sh/mcore-run-on-slurmSplit a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
skillmarket install greatsage_sh/mcore-split-prTest system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.
skillmarket install greatsage_sh/mcore-testingGuide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.
skillmarket install greatsage_sh/nemo-automodel-distributed-trainingConfigure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.
skillmarket install greatsage_sh/nemo-automodel-launcher-configGuide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.
skillmarket install greatsage_sh/nemo-automodel-model-onboardingCreate and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
skillmarket install greatsage_sh/nemo-automodel-recipe-developmentUse when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.
skillmarket install greatsage_sh/nemo-data-designer-pluginUse when working on the Evaluator plugin CLI, jobs, SDK-backed specs, metric types, or plugin-owned Evaluator skills.
skillmarket install greatsage_sh/nemo-evaluator-pluginRun Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.
skillmarket install greatsage_sh/nemo-mbridge-mlm-bridge-trainingConvert single-node scripts to multi-node Slurm sbatch jobs and debug common multi-node failures. Covers srun-native vs uv run torch.distributed approaches, container setup, NCCL timeouts, OOM sizing for MoE models, and interactive allocation.
skillmarket install greatsage_sh/nemo-mbridge-multi-node-slurmValidate and use selective and full activation recompute in Megatron Bridge to reduce GPU memory usage at the cost of extra compute.
skillmarket install greatsage_sh/nemo-mbridge-perf-activation-recomputeValidate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.
skillmarket install greatsage_sh/nemo-mbridge-perf-cpu-offloadingValidate and use CUDA graph capture in Megatron Bridge, including local full-iteration graphs and Transformer Engine scoped graphs for attention, MLP, and MoE modules.
skillmarket install greatsage_sh/nemo-mbridge-perf-cuda-graphsValidate and use MoE expert-parallel communication overlap in Megatron-Bridge, including overlap_moe_expert_parallel_comm, delay_wgrad_compute, and flex dispatcher backends such as DeepEP and HybridEP.
skillmarket install greatsage_sh/nemo-mbridge-perf-expert-parallel-overlapOperational guide for enabling hierarchical context parallelism in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
skillmarket install greatsage_sh/nemo-mbridge-perf-hierarchical-context-parallelOperational guide for enabling Megatron FSDP in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
skillmarket install greatsage_sh/nemo-mbridge-perf-megatron-fsdpTechniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM fixes.
skillmarket install greatsage_sh/nemo-mbridge-perf-memory-tuningMoE expert-parallel communication overlap in Megatron Bridge. Covers dispatch/combine overlap, flex dispatcher backends, and expert wgrad scheduling.
skillmarket install greatsage_sh/nemo-mbridge-perf-moe-comm-overlapChoose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
skillmarket install greatsage_sh/nemo-mbridge-perf-moe-dispatcher-selectionRepresentative MoE training playbooks by hardware platform and model family. Summarizes rounded throughput bands, parallelism patterns, and common tuning stacks.
skillmarket install greatsage_sh/nemo-mbridge-perf-moe-hardware-configsLong-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.
skillmarket install greatsage_sh/nemo-mbridge-perf-moe-long-contextSystematic workflow for MoE training optimization in Megatron Bridge, based on the Megatron-Core MoE paper. Covers the Three Walls framework, parallel folding, recompute strategy, dispatcher choice, and CUDA-graph bring-up.
skillmarket install greatsage_sh/nemo-mbridge-perf-moe-optimization-workflowPractical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
skillmarket install greatsage_sh/nemo-mbridge-perf-moe-vlm-trainingOperational guide for choosing and combining parallelism strategies in Megatron Bridge, including sizing rules, hardware topology mapping, and combined parallelism configuration.
skillmarket install greatsage_sh/nemo-mbridge-perf-parallelism-strategiesValidate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying the right CP constraints.
skillmarket install greatsage_sh/nemo-mbridge-perf-sequence-packingOperational guide for enabling TP, DP, and PP communication overlap in Megatron-Bridge, including config knobs, code anchors, pitfalls, and verification.
skillmarket install greatsage_sh/nemo-mbridge-perf-tp-dp-comm-overlapRecommend and customize Megatron Bridge recipes for a user's model, GPU count, and training goal. Indexes library recipes (pretrain/SFT/PEFT) and performance recipes.
skillmarket install greatsage_sh/nemo-mbridge-recipe-recommenderResiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.
skillmarket install greatsage_sh/nemo-mbridge-resiliencyUse this skill when NeMo Relay is installed or imported but application-side runtime behavior is missing or incorrect, including load failures, inactive scopes, missing events, and plugin or adaptive wiring problems.
skillmarket install greatsage_sh/nemo-relay-debug-runtime-integrationUse 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 maintained integration, or direct Python, Node.js, or Rust instrumentation before production setup.
skillmarket install greatsage_sh/nemo-relay-get-startedUse this skill when choosing or running NeMo Relay installation for the CLI, Python, Node.js, Rust, OpenClaw, Hermes, or maintained framework integrations before runtime configuration or quick-start setup.
skillmarket install greatsage_sh/nemo-relay-installUse 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 events, middleware, or guardrails.
skillmarket install greatsage_sh/nemo-relay-instrument-callsUse this skill when concurrent requests, async tasks, threads, workers, goroutines, or agents need independent NeMo Relay scope stacks and correct ancestry propagation.
skillmarket install greatsage_sh/nemo-relay-instrument-context-isolationUse this skill when adding NeMo Relay typed wrappers, domain types, or provider codecs while preserving JSON middleware semantics and caller-visible behavior.
skillmarket install greatsage_sh/nemo-relay-instrument-typed-wrappersUse this skill when migrating applications, examples, integrations, documentation, manifests, or repository code from NeMo Flow to NeMo Relay across Python, Rust, Node.js, Go, C FFI, CLI, configuration, and observability surfaces.
skillmarket install greatsage_sh/nemo-relay-migrate-from-flowUse this skill when baseline NeMo Relay instrumentation exists and the user wants to configure or evaluate adaptive plugin behavior, including telemetry, state, adaptive_hints, tool_parallelism, ACG, hint consumption, or measured rollout.
skillmarket install greatsage_sh/nemo-relay-plugin-adaptive-tuningUse this skill when building or packaging reusable NeMo Relay runtime behavior as a configuration-activated plugin with deterministic validation and rollback-safe registration.
skillmarket install greatsage_sh/nemo-relay-plugin-buildUse this skill when choosing or configuring NeMo Relay observability through the built-in plugin, subscribers, or exporters, including raw ATOF events, ATIF trajectories, OpenTelemetry traces, OpenInference export, or custom event handling.
skillmarket install greatsage_sh/nemo-relay-plugin-observabilityUse when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg` `.png` `.tiff`), Office (`.docx` `.pptx`), text (`.html` `.txt`), audio (`.mp3` `.wav` `.m4a`), or video (`.mp4` `.mov`). Prefer this over native Read / Grep for multi-file or non-PDF corpora. Not for: editing files, web browsing, single-file plain-text lookups, fine-tuning.
skillmarket install greatsage_sh/nemo-retrieverAutonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.
skillmarket install greatsage_sh/nemo-rl-auto-researchBrev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.
skillmarket install greatsage_sh/nemo-rl-brev-etiquetteDocumentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.
skillmarket install greatsage_sh/nemo-rl-docsManage durable working-session memory for coding agents. Use when a user asks to preserve or recover agent context across disconnects, VS Code restarts, long-running work, handoffs, or any session where important state should be written periodically under the repo's session directory. Do NOT use for: simple questions, short tasks, one-off commands, linting, or code review.
skillmarket install greatsage_sh/nemo-rl-session-memoryGuides 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, operate, troubleshoot, secure, or learn NemoClaw with an AI coding assistant. Trigger keywords - nemoclaw docs, use nemoclaw with ai agent, nemoclaw mcp docs, nemoclaw install help, nemoclaw quickstart, nemoclaw markdown docs, llms.txt, agent skills.
skillmarket install greatsage_sh/nemoclaw-user-guideOrchestration skill for NVIDIA Nemotron Speech (Riva) / NeMo ASR domain and language adaptation. Given a goal like "improve/fine-tune ASR for my domain or language", it scopes the task, picks the cheapest sufficient path (word boosting → n-gram LM → fine-tuning), delegates each stage to the right sub-skill (data generation, training, evaluation, deployment), and answers cost/time/data questions along the way.
skillmarket install greatsage_sh/nemotron-asr-finetunePlan, configure, and chain repo-native Nemotron customization steps into single-step or multi-step pipelines: curation, translation, SFT/PEFT (AutoModel or Megatron-Bridge), pretraining/CPT, RL alignment (DPO/RLVR/GRPO/RLHF), BYOB/MCQ benchmarks, checkpoint conversion, ModelOpt optimization, env profiles, and evaluation of trained checkpoints or existing/hosted endpoints. Use when a request names a Nemotron step or workflow, or asks to clean, translate, train, fine-tune, align, convert, optimize
skillmarket install greatsage_sh/nemotron-customizeGenerates BYO custom safety policies for NVIDIA Nemotron content-safety guardrails — Nemotron-Content-Safety-Reasoning-4B (text) and multimodal Nemotron-3-Content-Safety. Produces a Markdown policy, JSON taxonomy, and drop-in inference prompts. Maps rough words or an existing policy to V2 categories, adding custom categories or topic-following rules.
skillmarket install greatsage_sh/nemotron-policy-generatorUse when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.
skillmarket install greatsage_sh/nemotron-retrieval-recipesRoutes NVIDIA Nemotron Speech (Riva) NIM tasks — deploys, runs, and tests ASR, TTS, and NMT NIMs on build.nvidia.com or self-hosted.
skillmarket install greatsage_sh/nemotron-speechUsed for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data without review.
skillmarket install greatsage_sh/nv-generate-ct-rflowUsed for generating synthetic body MRI volumes with NV-Generate-CTMR rflow-mr. Not for paired masks or production training data.
skillmarket install greatsage_sh/nv-generate-mrUsed for generating synthetic brain MRI volumes with NV-Generate-CTMR rflow-mr-brain. Not for production training data.
skillmarket install greatsage_sh/nv-generate-mr-brainUsed for finetuning NV-Generate-CTMR MR-brain diffusion UNet from a NIfTI datalist. Not for clinical or production data approval.
skillmarket install greatsage_sh/nv-generate-mr-brain-finetuneUsed for finetuning the NV-Generate-CTMR MAISI VAE from CT/MRI NIfTI datalists. Not for clinical or production data approval.
skillmarket install greatsage_sh/nv-generate-vae-finetuneUsed for command-shape or live NV-Reason-CXR chest X-ray reasoning smoke tests. Not for diagnosis or clinical reporting.
skillmarket install greatsage_sh/nv-reason-cxrUsed for running NV-Segment-CT VISTA3D on CT NIfTI volumes and recording label-map evidence.
skillmarket install greatsage_sh/nv-segment-ctUsed for smoke or dataset finetuning of NV-Segment-CT VISTA3D on CT NIfTI labels. Not for clinical validation.
skillmarket install greatsage_sh/nv-segment-ct-finetuneUsed for running NV-Segment-CTMR on CT or MRI NIfTI volumes and recording label-map evidence. Not for clinical interpretation.
skillmarket install greatsage_sh/nv-segment-ctmr>-
skillmarket install greatsage_sh/nvidia-skill-finder>-
skillmarket install greatsage_sh/nvidia-skills-nvidia-skill-finderUse as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.
skillmarket install greatsage_sh/omniverse-realtime-viewer>-
skillmarket install greatsage_sh/physical-ai-defect-image-generationRouter for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, PhysicalAI HF datasets. Do NOT use for SimReady or infra setup.
skillmarket install greatsage_sh/physical-ai-neural-reconstruction>-
skillmarket install greatsage_sh/physical-ai-people-attribute-search>-
skillmarket install greatsage_sh/physical-ai-video-data-augmentationOfficial NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment setup, training-loop or other code authoring/scaffolding, contributor/CI/packaging questions, repo-specific questions in physicsnemo-sym/-cfd/-curator, or general (non-physics) ML/Py
skillmarket install greatsage_sh/physicsnemo-discoverNVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).
skillmarket install greatsage_sh/rag-blueprint>-
skillmarket install greatsage_sh/rag-eval>-
skillmarket install greatsage_sh/rag-perfPerforms deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with
skillmarket install greatsage_sh/tao-analyze-changenet-rcaPerforms gap analysis on NVIDIA TAO VCN Classify (Visual Component Net) experiments by invoking the data-services container (`tao_toolkit.data_services` from `versions.yaml`) directly via `docker run … gap_analysis vcn_aoi …` — picks the optimal decision threshold, ranks per-sample weakness, and emits a top-K weakest parquet expanded per-lighting for downstream augmentation. Use when analyzing VCN classification failures, picking SDA augmentation targets, or auditing PASS/NO_PASS boundary
skillmarket install greatsage_sh/tao-analyze-gaps-visual-changenetExtract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions.
skillmarket install greatsage_sh/tao-analyze-gaps-vlm-bcqRun `tao-daft convert` to convert NVIDIA TAO DAFT datasets between supported formats. Do not use for non-DAFT data.
skillmarket install greatsage_sh/tao-convert-dataset-formatCLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX
skillmarket install greatsage_sh/tao-finetune-clip>-
skillmarket install greatsage_sh/tao-finetune-cosmos-embedCosmos3-Nano video QA supervised fine-tuning with FSDP parallelism. Use when training or evaluating video
skillmarket install greatsage_sh/tao-finetune-cosmos-reason>
skillmarket install greatsage_sh/tao-finetune-huggingface-modelTwo-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them
skillmarket install greatsage_sh/tao-generate-image-groundingFour-step image referring-expression pipeline: turns images plus KITTI bounding-box labels into region
skillmarket install greatsage_sh/tao-generate-referring-expressions>-
skillmarket install greatsage_sh/tao-generate-video-reasoning-annotations>-
skillmarket install greatsage_sh/tao-launch-workflow>-
skillmarket install greatsage_sh/tao-list-capabilitiesRuns the DEFT embed-then-mine workflow for VCN AOI iterations — embeds the gap-analysis target parquet, embeds a source pool, and mines nearest-neighbour source images for downstream augmentation. Use as the immediate next step after `tao-route-visual-changenet-samples` when expanding a real-image augmentation queue from the mining subset.
skillmarket install greatsage_sh/tao-mine-aoi-images>
skillmarket install greatsage_sh/tao-port-huggingface-modelRoutes the weakest VCN samples (output of `tao-analyze-gaps-visual-changenet`) into per-augmentation-module
skillmarket install greatsage_sh/tao-route-visual-changenet-samplesRun AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm
skillmarket install greatsage_sh/tao-run-automl>
skillmarket install greatsage_sh/tao-run-automl-deft-pipeline>
skillmarket install greatsage_sh/tao-run-deft-aoi>
skillmarket install greatsage_sh/tao-run-inference-serviceBrev managed GPU instances with Docker support. Use when running TAO training, evaluation, or inference on
skillmarket install greatsage_sh/tao-run-on-brevKubernetes execution platform — submits TAO container jobs as single-pod k8s Jobs with NVIDIA GPU scheduling.
skillmarket install greatsage_sh/tao-run-on-kubernetesLocal or remote Docker execution for TAO SDK job containers using a Docker daemon with NVIDIA GPU runtime. Use
skillmarket install greatsage_sh/tao-run-on-local-dockerRemote SLURM GPU cluster execution over SSH with sbatch/srun, Pyxis/Enroot containers, and Lustre-backed
skillmarket install greatsage_sh/tao-run-on-slurmTAO Execution SDK for submitting and monitoring GPU training jobs on supported platforms (Brev, SLURM,
skillmarket install greatsage_sh/tao-run-platform>-
skillmarket install greatsage_sh/tao-setup-nvidia-gpu-hostAction recognition from video sequences. Supports RGB, optical flow, and joint (multi-stream) input types for
skillmarket install greatsage_sh/tao-train-action-recognitionBEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view
skillmarket install greatsage_sh/tao-train-bevfusionCenterPose for keypoint / pose estimation. Detects object centers and regresses keypoint locations for 6-DoF
skillmarket install greatsage_sh/tao-train-centerposeDeformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing,
skillmarket install greatsage_sh/tao-train-deformable-detrMonocular depth estimation using Metric Depth Anything v2 or Relative Depth Anything architectures. Predicts
skillmarket install greatsage_sh/tao-train-depth-anything-v2DINO (DETR with Improved DeNoising Anchor Boxes) for 2D object detection. Transformer-based detector with
skillmarket install greatsage_sh/tao-train-dinoReal-time stereo depth estimation using FastFoundationStereo (FFS), the distilled bp2 commercial variant of
skillmarket install greatsage_sh/tao-train-fast-foundation-stereoStereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D
skillmarket install greatsage_sh/tao-train-foundation-stereoGrounding DINO for open-set object detection. Combines DINO-style detection with a BERT text encoder for
skillmarket install greatsage_sh/tao-train-grounding-dinoPyTorch-based TAO image classification. Supports a wide range of backbones (FAN, EfficientNet, ResNet, etc.)
skillmarket install greatsage_sh/tao-train-image-classificationMasked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs
skillmarket install greatsage_sh/tao-train-mask-auto-encoderMAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations
skillmarket install greatsage_sh/tao-train-mask-auto-labelMask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with a mask-prediction head for
skillmarket install greatsage_sh/tao-train-mask-grounding-dinoMask2Former for universal image segmentation (panoptic, instance, and semantic). Transformer-based with
skillmarket install greatsage_sh/tao-train-mask2formerMetric-learning recognition (ml-recog) for fine-grained visual recognition. Learns embeddings for
skillmarket install greatsage_sh/tao-train-metric-learning-recognitionNVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation
skillmarket install greatsage_sh/tao-train-nvdinov2NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation
skillmarket install greatsage_sh/tao-train-nvpanoptix3dOCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a
skillmarket install greatsage_sh/tao-train-ocdnetOCRNet for scene text recognition. Recognizes text content from cropped text-region images and supports CTC
skillmarket install greatsage_sh/tao-train-ocrnetOneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a
skillmarket install greatsage_sh/tao-train-oneformerOptical Inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing
skillmarket install greatsage_sh/tao-train-optical-inspectionPointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a
skillmarket install greatsage_sh/tao-train-pointpillarsPose classification using ST-GCN (Spatial Temporal Graph Convolutional Network). Classifies skeleton sequences
skillmarket install greatsage_sh/tao-train-pose-classificationPerson re-identification (ReID). Learns discriminative embeddings to match the same person across different
skillmarket install greatsage_sh/tao-train-reidRT-DETR (Real-Time DEtection TRansformer) for 2D object detection. Designed for real-time inference with
skillmarket install greatsage_sh/tao-train-rtdetrSegFormer for semantic segmentation. Lightweight transformer-based architecture with hierarchical feature
skillmarket install greatsage_sh/tao-train-segformerStandard single-step train/eval/export workflow for any TAO model. Use when training a TAO model on a dataset
skillmarket install greatsage_sh/tao-train-single-stepSparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable
skillmarket install greatsage_sh/tao-train-sparse4dVisual ChangeNet for binary image classification and segmentation in AOI defect detection. Use when training,
skillmarket install greatsage_sh/tao-train-visual-changenetRun `tao-daft validate` to check NVIDIA TAO DAFT datasets for structure, schema, and cross-reference errors. Do
skillmarket install greatsage_sh/tao-validate-dataset-formatAdd a new cuTile GPU kernel operator to TileGym. Covers dispatch registration in ops.py, cuTile backend implementation, __init__.py exports, test creation, and benchmark in tests/benchmark. Use when adding, creating, or implementing a new cuTile operator/kernel in TileGym, or when asking how to register a new cuTile op.
skillmarket install greatsage_sh/tilegym-adding-cutile-kernelConverts cuTile Python GPU kernels (@ct.kernel) to cuTile.jl Julia equivalents. Handles kernel syntax translation, 0-indexed to 1-indexed conversion, broadcasting differences, memory layout (row-major to column-major), type system mapping, and launch API differences. Use when converting, porting, or translating cuTile Python kernels to Julia cuTile.jl, or debugging/optimizing existing Julia cuTile translations.
skillmarket install greatsage_sh/tilegym-converting-cutile-to-juliaConverts cuTile GPU kernels (@ct.kernel) to Triton (@triton.jit). Handles standard in-repo conversion, debugging (cudaErrorIllegalAddress, shape mismatch, numerical mismatch), and mapping cuTile idioms (ct.load/ct.store, ct.Constant, ct.launch) to Triton equivalents. Covers dual-kernel layout flags (e.g. transpose=True/False + autotune grid via META) per translations/advanced-patterns.md. Use when converting, porting, or translating cuTile kernels to Triton, or debugging existing Triton translat
skillmarket install greatsage_sh/tilegym-converting-cutile-to-tritonUse when adding, modifying, optimizing, or debugging CuTile autotuning code. Trigger signals: `exhaustive_search` / `replace_hints` / `hints_fn` / `cuda.tile.tune` in code, `autotune` in filenames, or correctness/performance issues in autotuned CuTile kernels. Covers: tune-once/cache/launch pattern, per-architecture configs (sm80–sm120), parameter space design (tile sizes, occupancy, num_ctas), and 7 common pitfalls with solutions.
skillmarket install greatsage_sh/tilegym-cutile-autotuningExpert cuTile programming assistant. Write high-performance GPU kernels using cuTile's tile-based programming model with proper validation and optimization. Supports deep agent orchestration for complex multi-kernel tasks.
skillmarket install greatsage_sh/tilegym-cutile-pythonIteratively optimize cuTile kernel performance through systematic profiling, bottleneck analysis, IR comparison, and targeted tuning. Covers tile sizes, occupancy, autotune configs, TMA, latency hints, persistent scheduling, num_ctas, flush_to_zero, and IR-level debugging. Use when asked to "optimize cutile kernel", "improve kernel perf", "tune cutile performance", "make kernel faster", or iteratively benchmark and refine a cuTile GPU kernel in the TileGym project.
skillmarket install greatsage_sh/tilegym-improve-cutile-kernel-perfIntegrate TileGym kernels into Hugging Face `transformers` models by replacing the library's submodule(s) and certain class(es)' implementations, and patching certain class(es)' init/forward/load weight methods prior to instantiating models. Used when the user requires integrating TileGym kernels into `transformers` models.
skillmarket install greatsage_sh/tilegym-monkey-patch-kernels-to-transformersUse 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 metadata-answerable questions.
skillmarket install greatsage_sh/vss-ask-videoUse 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 user says things like 'deploy rtvi-cv', 'start warehouse 2d', 'add a stream', 'check rtvi-cv health', or 'stop the perception container'. Not for VLM, embedding, or analytics — use the matching vss-* skill.
skillmarket install greatsage_sh/vss-deploy-detection-tracking-2d>
skillmarket install greatsage_sh/vss-deploy-detection-tracking-3d