Skip to main content
NeVibeCode · 17,648 items

Everything for Gemini CLI

What installs into Gemini CLI: skills, MCP servers and plugins. Each card has an install command and example prompts.

holoscan-install-conda Holoscan Team skill Checks Conda package availability for Holoscan SDK 5.x releases, flags missing 5.0 builds, and routes to supported installation alternatives. CX Codex +1 1,800installs holoscan-install-container Holoscan Team skill Checks a host and installs the Holoscan SDK 5.x CUDA 13 development container. Use it before running the SDK in Docker with GPU access. CX Codex +1 1,800installs holoscan-setup Holoscan Team skill Checks a Linux host and picks a Holoscan SDK 5.x install path: container, Debian packages, wheels or a source build. CX Codex +1 1,800installs tilegym-adding-cutile-kernel TileGym Team skill Guides AI coding agents through adding cuTile GPU kernel operators to TileGym. Useful when implementing custom kernels, tests, and benchmarks. CX Codex +1 1,800installs mcore-split-pr Philip Petrakian skill This skill maps a pull request’s files to CODEOWNERS groups and proposes smaller PRs with fewer reviewer groups. Use it when a large change brings in too many reviewers. CX Codex +1 1,800installs mcore-testing Philip Petrakian skill A skill that maps out the Megatron-LM test system: test layout, recipe YAML, golden values, and how to run unit tests locally. CX Codex +1 1,800installs mcore-create-issue Philip Petrakian skill Investigates failing GitHub Actions runs for NVIDIA/Megatron-LM, extracts the error cause, and files a structured bug report. CX Codex +1 1,800installs mcore-run-on-slurm Philip Petrakian skill Prepare a SLURM launch for distributed Megatron-LM training, from an sbatch skeleton to rank-level failure checks. Useful when configuring or debugging a multi-node job. CX Codex +1 1,800installs nemo-rl-brev-etiquette NVIDIA skill A skill that tells the agent where files belong on a Brev box: code stays in the repo, heavy run output goes to /ephemeral. CX Codex +1 1,800installs mcore-linting-and-formatting Philip Petrakian skill Sets up linting and code formatting for Megatron-LM projects. It helps fix ruff and mypy violations and sort imports before opening a pull request. CX Codex +1 1,800installs nemo-mbridge-perf-tp-dp-comm-overlap NVIDIA skill A skill that walks through enabling TP, DP and PP communication overlap in Megatron-Bridge: which knobs to turn, where the code gates it, how to verify. CX Codex +1 1,800installs nemo-mbridge-perf-moe-dispatcher-selection NVIDIA skill Picks between alltoall, DeepEP and HybridEP for MoE token dispatch based on your hardware, EP degree and optimization stage. CX Codex +1 1,800installs nemo-mbridge-perf-megatron-fsdp NVIDIA skill Configures Megatron FSDP in Megatron-Bridge to replace standard DDP, helping resolve out-of-memory errors and verify training checkpoints. CX Codex +1 1,800installs nemo-rl-docs NVIDIA skill This skill hands your agent the documentation rules for NeMo-RL: keeping docs/index.md current and writing docstrings in Google style. Useful when you touch the docs. CX Codex +1 1,800installs nemo-mbridge-resiliency NVIDIA skill A skill covering resiliency setup in Megatron Bridge: fault tolerance, straggler detection, preemption and re-run state machine. CX Codex +1 1,800installs nemo-mbridge-perf-hierarchical-context-parallel NVIDIA skill Configures hierarchical context parallelism in Megatron-Bridge. Useful for scaling long-sequence model training when context length exceeds KV head counts. CX Codex +1 1,800installs nemo-mbridge-perf-moe-hardware-configs NVIDIA skill A reference of MoE training starting configurations for H100, B200, GB200, and GB300. Use it when selecting a dispatcher, parallelism layout, or planning throughput checks. CX Codex +1 1,800installs nemo-mbridge-perf-moe-comm-overlap NVIDIA skill A skill for MoE expert-parallel communication overlap in Megatron Bridge: dispatch/combine, flex dispatcher backends, expert wgrad scheduling. CX Codex +1 1,800installs nemo-mbridge-perf-moe-long-context NVIDIA skill Guides context parallelism sizing and selective recompute for long-context MoE training in Megatron Bridge. CX Codex +1 1,800installs nemo-mbridge-perf-expert-parallel-overlap NVIDIA skill A skill for enabling and validating MoE expert-parallel communication overlap in Megatron-Bridge, covering alltoall and flex dispatchers with DeepEP and HybridEP. CX Codex +1 1,800installs nemo-mbridge-perf-cpu-offloading NVIDIA skill A skill that validates and enables CPU offloading in Megatron Bridge: layer-level activation offloading and optimizer state offloading via HybridDeviceOptimizer. CX Codex +1 1,800installs nemo-mbridge-perf-moe-optimization-workflow NVIDIA skill Guides MoE throughput tuning and regression diagnosis in Megatron Bridge. Useful when diagnosing speed drops after commit or configuration changes. CX Codex +1 1,800installs nemo-mbridge-multi-node-slurm NVIDIA skill Converts single-node launches into multi-node Slurm jobs and helps investigate NCCL, launch, and memory failures. CX Codex +1 1,800installs nemo-mbridge-perf-sequence-packing NVIDIA skill A skill for configuring packed sequences and long-context training in Megatron-Bridge: offline LLM packing, collate-time VLM packing, Energon online packing. CX Codex +1 1,800installs nemo-mbridge-perf-moe-vlm-training NVIDIA skill Practical guidance for training MoE VLMs in Megatron Bridge. It helps configure FSDP or 3D parallelism and debug OOM failures during multimodal training runs. CX Codex +1 1,800installs nemo-mbridge-mlm-bridge-training NVIDIA skill This skill runs Megatron-LM and Megatron Bridge training, compares loss curves, and helps investigate divergence after code changes. CX Codex +1 1,800installs nemo-mbridge-perf-parallelism-strategies NVIDIA skill Picks TP, PP, CP, EP and DP degrees for Megatron Bridge training runs, and traces an OOM or slowdown back to a parallelism config change. CX Codex +1 1,800installs nemo-mbridge-perf-activation-recompute NVIDIA skill Guides activation recomputation setup in Megatron Bridge to resolve GPU memory OOMs during LLM training. Balances memory savings against extra recomputed operations. CX Codex +1 1,800installs nv-generate-vae-finetune NVIDIA MedTech Team skill Stages and runs NV-Generate-CTMR MAISI VAE finetuning from CT or MRI NIfTI datalists. Use it to validate a dataset before starting GPU training. CX Codex +1 1,800installs nv-segment-ct-finetune NVIDIA MedTech skill Finetunes NV-Segment-CT VISTA3D on CT NIfTI image and label datasets, with a fixed-channel softmax path and optional MLflow tracking. CX Codex +1 1,800installs nv-reason-cxr NVIDIA MedTech Team skill Runs NV-Reason-CXR-3B smoke tests on chest X-ray images. Useful for verifying pipeline command shapes and parsing JSON reasoning outputs. CX Codex +1 1,800installs nv-generate-ct-rflow NVIDIA MedTech Team skill This skill runs rflow-ct to create synthetic CT volumes and masks. Review the outputs independently before using them to train medical models. CX Codex +1 1,800installs nv-segment-ctmr NVIDIA MedTech Team skill Runs NV-Segment-CTMR on CT or MRI NIfTI volumes and writes a label map plus a JSON report. Not meant for clinical interpretation. CX Codex +1 1,800installs nv-generate-mr NVIDIA MedTech Team skill Generates synthetic body MRI volumes using NV-Generate-CTMR rflow-mr. Useful for staging T1 MRI volume synthesis without paired segmentations. CX Codex +1 1,800installs nv-segment-ct NVIDIA MedTech Team skill Runs VISTA3D on CT NIfTI volumes and writes a label map plus a JSON report. Built for research runs, not clinical use. CX Codex +1 1,800installs nv-generate-mr-brain-finetune NVIDIA MedTech Team skill Finetunes the NV-Generate-CTMR MR-Brain v1 diffusion model on your T1, T2, FLAIR, SWI or MRA NIfTI volumes. A preflight pass runs first, without a GPU. CX Codex +1 1,800installs nv-generate-mr-brain NVIDIA MedTech Team skill Generates synthetic T1, T2, FLAIR, SWI, or MRA brain MRI volumes with NV-Generate-CTMR MR-Brain v1. It provides test NIfTI volumes without clinical scans. CX Codex +1 1,800installs research-ideation Galaxy-Dawn skill Guides the research project kickoff by framing questions through 5W1H, mapping literature gaps, and organizing papers in Zotero. CX Codex +1 566installs compose-animations chrisbanes skill Helps write and review Jetpack Compose motion across common UI states. Useful when picking between AnimatedVisibility, AnimatedContent, animate*AsState, and rememberTransition. CX Codex +1 1,800installs restaurant-booking gooseworks-ai skill Automates restaurant reservations on OpenTable and Resy via Notte browser automation. Handles date selection, table sizing, and guest forms directly. CX Codex +1 488installs

5,961–6,000 of 17,648

Narrow it down

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor