Skill directory
Agent skills
Focused instruction packs that teach a coding agent one job well. Browse the catalog and use any of them inside a RiverX project.
18,175Skills
1,902Publishers
249Official
Hsb Testnvidia/skillsExecute 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.06Jetson Build Sourcenvidia/skills>-010Jetson Customize Cameranvidia/skills>-011Jetson Customize Clocksnvidia/skillsUse 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.09Jetson Customize Fannvidia/skills>-05Jetson Customize Mgbenvidia/skills>-08Jetson Customize Nvpmodelnvidia/skills>-05Jetson Customize Pcienvidia/skills>-07Jetson Customize Pinmuxnvidia/skills>-011Jetson Customize Uphynvidia/skillsConfigure Jetson UPHY lane allocation (uphy0/uphy1-config) on Orin/Thor custom carriers. Do NOT use for pinmux or PCIe-only edits.08Jetson Customize Usbnvidia/skillsEnable/disable Jetson USB2/USB3 SS ports via kernel-DT overlay. Do NOT use for UPHY lane allocation or ODMDATA edits.011Jetson Derive Carriernvidia/skills>-05Jetson Diagnosticnvidia/skillsRead-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.012Jetson Download Bspnvidia/skills>-05Jetson Flash Imagenvidia/skillsUse 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.08Jetson Generate Kbnvidia/skills>-05Jetson Headless Modenvidia/skillsPlan and apply safe Jetson headless-mode changes to reclaim GUI and daemon memory.07Jetson Inference Mem Tunenvidia/skillsPick the serving stack and per-runtime memory flags (vLLM, SGLang, llama.cpp, TensorRT Edge-LLM) for an LLM/VLM workload on any NVIDIA Jetson.06Jetson Init Imagenvidia/skills>-05Jetson Init Sourcenvidia/skills>-06Jetson Init Targetnvidia/skills>-07Jetson Link Docsnvidia/skills>-05Jetson LLM Benchmarknvidia/skillsBenchmark Jetson LLM/VLM serving performance across vLLM, llama.cpp, and Ollama with structured JSON output.08Jetson LLM Servenvidia/skillsStand 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.05Jetson Memory Auditnvidia/skillsMeasure Jetson DRAM/NvMap usage and verify before/after memory reclamation with live audit data.08Jetson Optimize Memorynvidia/skills>-05Jetson Packagenvidia/skillsPick 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.08Jetson Print Bsp Infonvidia/skillsUse 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.05Jetson Print Device Infonvidia/skillsUse 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.05Jetson Promote Imagenvidia/skills>-08Jetson Quick Startnvidia/skills>-05Jetson Set Targetnvidia/skills>-05Jetson Speculative Decodingnvidia/skillsAdd EAGLE-3 or draft-model speculative decoding to a Jetson vLLM server when TPOT is the bottleneck.05Jetson Validate Imagenvidia/skills>-07Launch Nemo Rlnvidia/skillsPlaybook 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.05Mcore Create Issuenvidia/skillsInvestigate a failing GitHub Actions run or job and create a GitHub issue for the failure.05Mcore Linting And Formattingnvidia/skillsLinting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.05Mcore Run On Slurmnvidia/skillsHow 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.05Mcore Split PRnvidia/skillsSplit a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.05Mcore Testingnvidia/skillsTest system for Megatron-LM. Covers test layout, recipe YAML structure, adding and running unit and functional tests, golden values, marker filters, and CI parity.05Nemo Automodel Distributed Trainingnvidia/skillsGuide for selecting and configuring distributed training strategies in NeMo AutoModel, including FSDP2, Megatron FSDP, DDP, and parallelism settings.05Nemo Automodel Launcher Confignvidia/skillsConfigure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.05Nemo Automodel Model Onboardingnvidia/skillsGuide for onboarding new model architectures into NeMo AutoModel, including architecture discovery, implementation patterns, registration, and validation.09Nemo Automodel Recipe Developmentnvidia/skillsCreate and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.05Nemo Mbridge Mlm Bridge Trainingnvidia/skillsRun Megatron-LM (MLM) and Megatron Bridge training with mock or real data. Covers correlation testing, available recipes, and multi-GPU examples.06Nemo Mbridge Multi Node Slurmnvidia/skillsConvert 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.06Nemo Mbridge Perf Activation Recomputenvidia/skills>-06Nemo Mbridge Perf Cpu Offloadingnvidia/skillsValidate and use CPU offloading in Megatron Bridge, including layer-level activation offloading and fractional optimizer state offloading with HybridDeviceOptimizer.06
Skills, installed in one click
Start building freePut a skill to work
Open any project, search the Skills panel in the chat, and the agent picks it up from there.