Back to categories
Category

Agent Skills in category: Uncategorized

83217 skills match this category. Browse curated collections and explore related Agent Skills.

nvidia-megatron-bridge-verl-e2e-testing

External verl end-to-end validation workflow for Megatron-Bridge model/provider

NVIDIA
NVIDIA
103

nvidia-megatron-core-build-and-dependency

Container-based dev environment setup and dependency management for Megatron-LM.

NVIDIA
NVIDIA
103

nvidia-megatron-core-bump-base-image

Bump the NVIDIA PyTorch base image using the nvcr.io/nvidia/pytorch YY.MM py3 tag

NVIDIA
NVIDIA
103

nvidia-megatron-core-cicd

CI/CD reference for Megatron-LM. Covers CI pipeline structure, PR scope

NVIDIA
NVIDIA
103

nvidia-megatron-core-create-issue

Investigate a failing GitHub Actions run or job and create a GitHub issue

NVIDIA
NVIDIA
103

nvidia-megatron-core-linting-and-formatting

Linting and formatting for Megatron-LM. Covers running autoformat.sh,

NVIDIA
NVIDIA
103

nvidia-megatron-core-nightly-sync

Domain knowledge for the nightly main-to-dev sync workflow. Covers merge

NVIDIA
NVIDIA
103

nvidia-megatron-core-onboard-gb200-1node-tests

Onboard 1-node GitHub MR functional tests for GB200 from existing mr-scoped

NVIDIA
NVIDIA
103

nvidia-megatron-core-respond-to-issue

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

NVIDIA
NVIDIA
103

nvidia-megatron-core-run-on-slurm

How to launch distributed Megatron-LM training jobs on a SLURM cluster.

NVIDIA
NVIDIA
103

nvidia-megatron-core-split-pr

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

NVIDIA
NVIDIA
103

nvidia-megatron-core-testing

Test system for Megatron-LM. Covers test layout, recipe YAML structure,

NVIDIA
NVIDIA
103

nvidia-megatron-core-update-golden-values

Refresh golden values from a GitHub Actions workflow run (failing-only

NVIDIA
NVIDIA
103

nvidia-model-optimizer-accessing-mlflow

Query and browse evaluation results stored in MLflow. Use when the user

NVIDIA
NVIDIA
103

nvidia-model-optimizer-debug

Run commands inside a remote Docker container via the file-based command

NVIDIA
NVIDIA
103

nvidia-model-optimizer-deployment

Serve a quantized or unquantized LLM checkpoint as an OpenAI-compatible

NVIDIA
NVIDIA
103

nvidia-model-optimizer-evaluation

Evaluates accuracy of quantized or unquantized LLMs using NeMo Evaluator

NVIDIA
NVIDIA
103

nvidia-model-optimizer-launching-evals

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher.

NVIDIA
NVIDIA
103

nvidia-model-optimizer-monitor

Monitor submitted jobs (PTQ, evaluation, deployment) on SLURM clusters.

NVIDIA
NVIDIA
103

nvidia-model-optimizer-ptq

This skill should be used when the user asks to "quantize a model", "run

NVIDIA
NVIDIA
103

nvidia-model-optimizer-release-cherry-pick

Cherry-pick merged PRs labeled for a release branch into that branch,

NVIDIA
NVIDIA
103

nvidia-nemo-evaluator-byob

Create custom LLM evaluation benchmarks using the BYOB decorator framework.

NVIDIA
NVIDIA
103

nvidia-nemo-evaluator-launcher-accessing-mlflow

Query and browse evaluation results stored in MLflow. Use when the user

NVIDIA
NVIDIA
103

nvidia-nemo-evaluator-launcher-launching-evals

Run, monitor, analyze, and debug LLM evaluations via nemo-evaluator-launcher.

NVIDIA
NVIDIA
103

nvidia-nemo-evaluator-launcher-nel-assistant

Interactive config wizard for NeMo Evaluator Launcher (NEL). Use when

NVIDIA
NVIDIA
103

nvidia-nemo-gym-add-benchmark

'Guide for adding a new benchmark or training environment to NeMo-Gym.

NVIDIA
NVIDIA
103

nvidia-nemo-gym-debugging

Use when debugging a Nemo Gym run or reward profiling job. Covers rollout

NVIDIA
NVIDIA
103

nvidia-nemo-gym-docs

'Maintain the NeMo Gym Fern docs site — add, update, move, or remove

NVIDIA
NVIDIA
103

nvidia-nemo-gym-pivot-datasets

Use when creating, validating, or documenting Nemo Gym pivot datasets

NVIDIA
NVIDIA
103

nvidia-nemo-gym-reward-profiling

Use to help users get started with Nemo Gym reward profiling. Covers

NVIDIA
NVIDIA
103

nvidia-nemo-rl-auto-research

'Autonomous NeMo-RL research agent workflow for directed hypothesis testing

NVIDIA
NVIDIA
103

nvidia-nemo-rl-brev-etiquette

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL

NVIDIA
NVIDIA
103

nvidia-nemo-rl-build-and-dependency

Build and dependency management for NeMo-RL. Covers Docker image building

NVIDIA
NVIDIA
103

nvidia-nemo-rl-cicd

CI/CD reference for NeMo-RL. Covers GitHub Actions pipeline structure,

NVIDIA
NVIDIA
103

detecting-fileless-malware-techniques

>

autohandai
autohandai
103

dotnet-msbuild

Comprehensive MSBuild and .NET build skills: failure diagnosis, performance optimization, code quality, and modernization.

dotnet
dotnet
103

dotnet-nuget

NuGet and .NET package management: dependency management and modernization.

dotnet
dotnet
103

detecting-container-escape-attempts

Container escape is a critical attack technique where an adversary breaks out of container isolation to access the host system or other containers. Detection involves monitoring for escape indicators

autohandai
autohandai
103

detecting-container-escape-with-falco-rules

Detect container escape attempts in real-time using Falco runtime security rules that monitor syscalls, file access, and privilege escalation.

autohandai
autohandai
103

detecting-credential-dumping-techniques

Detect LSASS credential dumping, SAM database extraction, and NTDS.dit theft using Sysmon Event ID 10, Windows Security logs, and SIEM correlation rules

autohandai
autohandai
103

detecting-credential-dumping-with-edr

Detect OS credential dumping techniques including LSASS access, SAM extraction, and DCSync using EDR telemetry and Sysmon logs.

autohandai
autohandai
103

detecting-cryptomining-in-cloud

>

autohandai
autohandai
103

detecting-dcsync-attack-in-active-directory

Detect DCSync attacks where adversaries abuse Active Directory replication privileges to extract password hashes by monitoring for non-domain-controller accounts requesting directory replication via DsGetNCChanges.

autohandai
autohandai
103

detecting-dll-sideloading-attacks

Detect DLL side-loading attacks where adversaries place malicious DLLs alongside legitimate applications to hijack execution flow for defense evasion.

autohandai
autohandai
103

detecting-dnp3-protocol-anomalies

>

autohandai
autohandai
103

detecting-dns-exfiltration-with-dns-query-analysis

Detect data exfiltration through DNS tunneling by analyzing query entropy, subdomain length, query volume, TXT record abuse, and response payload sizes using passive DNS monitoring.

autohandai
autohandai
103

detecting-email-account-compromise

Detect compromised O365 and Google Workspace email accounts by analyzing inbox rule creation, suspicious sign-in locations, mail forwarding rules, and unusual API access patterns via Microsoft Graph and audit logs.

autohandai
autohandai
103

detecting-email-forwarding-rules-attack

Detect malicious email forwarding rules created by adversaries to maintain persistent access to email communications for intelligence collection and BEC attacks.

autohandai
autohandai
103

detecting-evasion-techniques-in-endpoint-logs

>

autohandai
autohandai
103

detecting-exfiltration-over-dns-with-zeek

Detect DNS-based data exfiltration by analyzing Zeek dns.log for high-entropy subdomains and anomalous query patterns

autohandai
autohandai
103

Page 1178 of 1665 · 83217 results