Development · NVIDIA AI Platform

Unified LLM torch-profiler triage skill for sglang, vllm, TensorRT-LLM, and TokenSpeed.

sgl-project/sglang

Walks an agent through working inside the Megatron-LM CI container and changing dependencies with uv, so lock files resolve the same locally and in CI.

NVIDIA/Megatron-LM

Remove bracketed NemoClaw tags from GitHub issue and PR titles.

NVIDIA/NemoClaw

Audit and implement a NemoClaw dependency version upgrade, including Hermes and base images.

NVIDIA/NemoClaw

Reviews recent code changes and checks if documentation needs updates.

NVlabs/alpasim

Find and safely apply per-operator refactoring / redundancy-reduction opportunities in a CV-CUDA operator (near-duplicate Tensor/VarShape kernels, reinvented shared utilities, dead code).

CVCUDA/CV-CUDA

Guides moving Megatron Core GPTModel checkpoints, configs, training commands and launch scripts to HybridModel, following the repository's migration document.

NVIDIA/Megatron-LM

Kaizen UI (KUI) component library and design-pattern advisor for NVIDIA applications.

NVIDIA/Personal-AI-Router

Analyzes Torch Profiler traces from SGLang, vLLM and TensorRT-LLM servers into kernel attribution, overlap and fusion tables.

BBuf/AI-Infra-Auto-Driven-SKILLS

Analyze retained NemoClaw CI timings for slow CLI tests, runner queues, or base-image publication.

NVIDIA/NemoClaw

Add a new step under src/nemotron/steps/<category/<stepid/ — manifest (step.toml), runner glue, configs, and per-step README.md.

NVIDIA-NeMo/Nemotron

Multi-agent PR review using Claude Code, Codex, and CodeRabbit.

NVIDIA/aicr

Analyze one NemoClaw PR lifetime to identify contributor, review, and automation delays or compare it with a latency target.

NVIDIA/NemoClaw

Query and write durable debugging memory recorded by MemoryWhale.

wuisabel-gif/MemWhale

Generates, validates, compares and explains HOLOLINK_def.svh macro files for the HSB IP, using bundled Python scripts and asking before it writes anything.

NVIDIA/skills

Write, debug, and optimize TileLang kernels from local upstream language, JIT, autotuning, profiling, compiler, test, and example source.

slowlyC/agent-gpu-skills

Draft a post-tag NemoClaw Announcement from the verified release range and shipped PRs.

NVIDIA/NemoClaw

Choose and run ACU-only, adaptive PPU in-kernel timeline, or optional bounded joint analysis for a PPU kernel.

alibaba/atrex-kernel-agent

Runs and validates an end-to-end Mission Control demo in a locally installed Isaac Sim, with a Nova Carter robot driven through a Python server.

NVIDIA/skills

Compare a Primus backend against an upstream repository or reference, verify git state, dependencies, directory changes, and integration coupling, then generate comparison reports, dashboard…

AMD-AGI/Primus

Explains where HOT-Step generation time goes (LM/DiT/VAE), how the TensorRT paths activate, how to benchmark from logs, and which knobs trade quality for speed.

scragnog/HOT-Step-CPP

Manage NVIDIA AI Workbench projects, contexts, builds, and environments via the nvwb CLI.

brevdev/workshop-build-an-agent

Runs the Megatron-LM autoformat script and its linting tools before a pull request, and keeps Python imports in order with isort.

NVIDIA/Megatron-LM

Use MemoryWhale debugging evidence when the user requests recall or a recurring failure may have relevant recorded history.

wuisabel-gif/MemWhale

Query current NVIDIA CUDA, PTX ISA, Runtime API, Driver API, Programming Guide, Best Practices, Nsight Compute, and Nsight Systems references.

slowlyC/agent-gpu-skills

A skill your agent uses when reviewing the weekly AICR component drift report — the Slack digest and drift-report.json artifact produced by Registry Drift Report (registry-drift.yaml) listing which…

NVIDIA/aicr

Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.

NVIDIA/Megatron-LM

MemoryWhale debugging; compiler failures; terminal diagnostics.

wuisabel-gif/MemWhale

Research and draft a response to a GitHub issue or question from an external contributor.

NVIDIA/Megatron-LM

Review rubric for the /review pull-request command. An agent skill from NVIDIA/Megatron-LM.

NVIDIA/Megatron-LM

Publish or update a NemoClaw pull request and follow its CI and automated reviews to completion.

NVIDIA/NemoClaw

Write, optimize, and debug high-performance AI compute kernels using TileLang (a Python DSL for GPU programming).

yzlnew/infra-skills

Execute a requested NeMo Relay code freeze by cutting a release branch, updating nightly alpha configuration, bumping main, and preparing the required PR.

NVIDIA/NeMo-Relay

Profile GPU kernels using NCU (NVIDIA) or rocprof (AMD) to collect performance metrics.

ZJLi2013/awesome-kernel-skills

Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation.

AI4Scientist/nano-scientist

A skill your agent uses when the user needs to locate authoritative information about NVIDIA DOCA without access to the source tree — finding the right docs.nvidia.com page for a…

NVIDIA/skills

A skill your agent uses for non-failing HoloHub app work with ./holohub: scaffold, build, run, test, visual evidence, lint, and flow benchmarking.

NVIDIA/skills

Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation.

NVIDIA/skills

A skill your agent uses when the user is doing hands-on DOCA Rivermax work on a BlueField DPU or ConnectX host — standing up docarmaxinstream (receive) sessions for timing-precise media-over-IP…

NVIDIA/skills

Discover and run Holoscan Sensor Bridge example applications on a connected devkit.

NVIDIA/skills

Evidence-gated workflow for MoE performance optimization in Megatron Bridge.

NVIDIA/skills

Linting and formatting for Megatron-LM. An agent skill from NVIDIA/skills.

NVIDIA/skills

CUDA debugging skill for GPU program correctness. An agent skill from mohitmishra786/low-level-dev-skills.

mohitmishra786/low-level-dev-skills

CUDA profiling skill for NVIDIA GPU performance analysis. An agent skill from mohitmishra786/low-level-dev-skills.

mohitmishra786/low-level-dev-skills