NVIDIA/Megatron-Bridge/resiliency A Agent Skill Active
NVIDIA/skills/skills/Megatron-Bridge/resiliency
Resiliency features in Megatron Bridge including fault tolerance, straggler detection, in-process restart, preemption, and re-run state machine.
Home › Agent Skills
Agent Skills
Browse SKILL.md-based agent skills for Claude Code, Codex, Cursor, Gemini CLI and more.
Filters
Status
Official17Category
Development and Testing65Product Management Skills by Pawel Huryn65Product Manager Skills by Dean Peters46Marketing Skills by Corey Haines32Specialized Domains32Productivity and Collaboration31Megatron-Bridge29TensorRT-LLM25NemoClaw23Marketing22Security Skills by Trail of Bits Team21Context Engineering19NeMo-RL14Megatron-Core12cuopt12Advertising Skills by Kim Barrett12video-search-and-summarization10Model-Optimizer8n8n Automation7TileGym7NeMo-Gym5NeMo-Evaluator-Launcher3deepstream2CUDA-Q1Install method
SKILL.md967Results
NVIDIA/Megatron-Bridge/testing A Agent Skill Active
NVIDIA/skills/skills/Megatron-Bridge/testing
Testing reference for Megatron Bridge — unit and functional test layout, tier semantics (L0/L1/L2/flaky), script conventions, running tests locally, adding/moving/disabling tests,...
NVIDIA/Megatron-Bridge/verl-e2e-testing A Agent Skill Active
NVIDIA/skills/skills/Megatron-Bridge/verl-e2e-testing
External verl end-to-end validation workflow for Megatron-Bridge model/provider changes.
NVIDIA/Megatron-Core/build-and-dependency A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/build-and-dependency
Container-based dev environment setup and dependency management for Megatron-LM.
NVIDIA/Megatron-Core/bump-base-image A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/bump-base-image
Bump the NVIDIA PyTorch base image (`nvcr.io/nvidia/pytorch:-py3`) used by Megatron-LM CI.
NVIDIA/Megatron-Core/cicd A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/cicd
CI/CD reference for Megatron-LM.
NVIDIA/Megatron-Core/create-issue A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/create-issue
Investigate a failing GitHub Actions run or job and create a GitHub issue for the failure.
NVIDIA/Megatron-Core/linting-and-formatting A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/linting-and-formatting
Linting and formatting for Megatron-LM.
NVIDIA/Megatron-Core/nightly-sync A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/nightly-sync
Domain knowledge for the nightly main-to-dev sync workflow.
NVIDIA/Megatron-Core/onboard-gb200-1node-tests A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/onboard-gb200-1node-tests
Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped 2-node tests.
NVIDIA/Megatron-Core/respond-to-issue A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/respond-to-issue
Research and draft a response to a GitHub issue or question from an external contributor.
NVIDIA/Megatron-Core/run-on-slurm A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/run-on-slurm
How to launch distributed Megatron-LM training jobs on a SLURM cluster.
NVIDIA/Megatron-Core/split-pr A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
NVIDIA/Megatron-Core/testing A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/testing
Test system for Megatron-LM.
NVIDIA/Megatron-Core/update-golden-values A Agent Skill Active
NVIDIA/skills/skills/Megatron-Core/update-golden-values
Refresh golden values from a GitHub Actions workflow run (failing-only or all jobs), score the change with average normalized relative differences, and produce a PR-ready summary.
NVIDIA/Model-Optimizer/accessing-mlflow A Agent Skill Active
NVIDIA/skills/skills/Model-Optimizer/accessing-mlflow
Query and browse evaluation results stored in MLflow.
NVIDIA/Model-Optimizer/debug A Agent Skill Active
NVIDIA/skills/skills/Model-Optimizer/debug
Run commands inside a remote Docker container via the file-based command relay (tools/debugger).
NVIDIA/Model-Optimizer/deployment A Agent Skill Active
NVIDIA/skills/skills/Model-Optimizer/deployment
Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible API endpoint using vLLM, SGLang, or TRT-LLM.
NVIDIA/Model-Optimizer/evaluation A Agent Skill Active
NVIDIA/skills/skills/Model-Optimizer/evaluation
Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator Launcher (NEL).
NVIDIA/Model-Optimizer/launching-evals A Agent Skill Active
NVIDIA/skills/skills/Model-Optimizer/launching-evals
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher.
NVIDIA/Model-Optimizer/monitor A Agent Skill Active
NVIDIA/skills/skills/Model-Optimizer/monitor
Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters.
NVIDIA/Model-Optimizer/ptq A Agent Skill Active
NVIDIA/skills/skills/Model-Optimizer/ptq
This skill should be used when the user asks to "quantize a model", "run PTQ", "post-training quantization", "NVFP4 quantization", "FP8 quantization", "INT8 quantization", "INT4 AW...
NVIDIA/Model-Optimizer/release-cherry-pick A Agent Skill Active
NVIDIA/skills/skills/Model-Optimizer/release-cherry-pick
Cherry-pick merged PRs labeled for a release branch into that branch, then open a PR and apply the cherry-pick-done label.
NVIDIA/NeMo-Evaluator/byob A Agent Skill Active
NVIDIA/skills/skills/NeMo-Evaluator/byob
Create custom LLM evaluation benchmarks using the BYOB decorator framework.
NVIDIA/NeMo-Evaluator-Launcher/accessing-mlflow A Agent Skill Active
NVIDIA/skills/skills/NeMo-Evaluator-Launcher/accessing-mlflow
Query and browse evaluation results stored in MLflow.
NVIDIA/NeMo-Evaluator-Launcher/launching-evals A Agent Skill Active
NVIDIA/skills/skills/NeMo-Evaluator-Launcher/launching-evals
Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher.
NVIDIA/NeMo-Evaluator-Launcher/nel-assistant A Agent Skill Active
NVIDIA/skills/skills/NeMo-Evaluator-Launcher/nel-assistant
Interactive config wizard for NeMo Evaluator Launcher (NEL).
NVIDIA/NeMo-Gym/add-benchmark A Agent Skill Active
NVIDIA/skills/skills/NeMo-Gym/add-benchmark
Guide for adding a new benchmark or training environment to NeMo-Gym.
NVIDIA/NeMo-Gym/nemo-gym-debugging A Agent Skill Active
NVIDIA/skills/skills/NeMo-Gym/nemo-gym-debugging
Use when debugging a Nemo Gym run or reward profiling job.
NVIDIA/NeMo-Gym/nemo-gym-docs A Agent Skill Active
NVIDIA/skills/skills/NeMo-Gym/nemo-gym-docs
Maintain the NeMo Gym Fern docs site — add, update, move, or remove pages under fern/.
NVIDIA/NeMo-Gym/nemo-gym-pivot-datasets A Agent Skill Active
NVIDIA/skills/skills/NeMo-Gym/nemo-gym-pivot-datasets
Use when creating, validating, or documenting Nemo Gym pivot datasets from rollout, trajectory, chat-completion, Responses API, or tool-call artifacts.
NVIDIA/NeMo-Gym/nemo-gym-reward-profiling A Agent Skill Active
NVIDIA/skills/skills/NeMo-Gym/nemo-gym-reward-profiling
Use to help users get started with Nemo Gym reward profiling.
NVIDIA/NeMo-RL/auto-research A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/auto-research
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery.
NVIDIA/NeMo-RL/brev-etiquette A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/brev-etiquette
Brev 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.
NVIDIA/NeMo-RL/build-and-dependency A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/build-and-dependency
Build and dependency management for NeMo-RL.
NVIDIA/NeMo-RL/cicd A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/cicd
CI/CD reference for NeMo-RL.
NVIDIA/NeMo-RL/config-conventions A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/config-conventions
Configuration conventions for NeMo-RL.
NVIDIA/NeMo-RL/contributing A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/contributing
Contribution conventions for NeMo-RL.
NVIDIA/NeMo-RL/copyright A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/copyright
NVIDIA copyright header requirements for NeMo-RL.
NVIDIA/NeMo-RL/docs A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/docs
Documentation conventions for NeMo-RL.
NVIDIA/NeMo-RL/error-handling A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/error-handling
Error handling guidelines for NeMo-RL.
NVIDIA/NeMo-RL/launch-nemo-rl A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/launch-nemo-rl
Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI.
NVIDIA/NeMo-RL/linting-and-formatting A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/linting-and-formatting
Code style guidelines for NeMo-RL (Python and shell).
NVIDIA/NeMo-RL/review-pr A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/review-pr
Interactive code review for NVIDIA-NeMo/RL pull requests.
NVIDIA/NeMo-RL/session-memory A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/session-memory
Manage durable working-session memory for coding agents.
NVIDIA/NeMo-RL/testing A Agent Skill Active
NVIDIA/skills/skills/NeMo-RL/testing
Testing conventions for NeMo-RL.
NVIDIA/NemoClaw/nemoclaw-contributor-create-pr A Agent Skill Active
NVIDIA/skills/skills/NemoClaw/nemoclaw-contributor-create-pr
Create GitHub pull requests that follow the NemoClaw PR template.
NVIDIA/NemoClaw/nemoclaw-contributor-update-docs A Agent Skill Active
NVIDIA/skills/skills/NemoClaw/nemoclaw-contributor-update-docs
Scan recent git commits for changes that affect user-facing behavior, then draft or update the corresponding documentation pages and refresh generated user skills for release prep.