AI & LLM Engineering · For devops and sre engineers

Step-by-step guide for adding a new observability/tracing provider to Agent Kernel.

yaalalabs/agent-kernel

Diagnose and remediate per-node issues on a HyperPod cluster (EKS or Slurm) — a specific node is unhealthy, unresponsive, stuck, or needs replacing.

awslabs/agent-plugins

Validate that a Dynamo deployment's NIXL/UCX/NCCL interconnect is ready for disaggregated serving over RDMA/NVLink.

NVIDIA/skills

A skill your agent uses for MolMIM, NVIDIA's BioNeMo NIM microservice for small-molecule latent-space generation and optimization.

NVIDIA/skills

Deploy ML models on Kubernetes with KServe (formerly KFServing) and NVIDIA Triton Inference Server.

sickn33/agentic-awesome-skills

Deploy, monitor, and debug long GPU jobs on RENTED/remote instances (AutoDL, RunPod, vast.ai, Lambda, Slurm, K8s): teardown/billing safety, spot resilience, resumable checkpointing, OOM/NaN triage.

sickn33/agentic-awesome-skills

Deploys a baseline landing zone foundation for a Google Cloud Organization, establishing security guardrails using Organization Policies, resource hierarchy folders and projects, billing…

google/skills

Sync Agent Kernel documentation from branch changes before a feature or bugfix is merged.

yaalalabs/agent-kernel

Analyze the most expensive users in AI observability and explain why they cost so much.

PostHog/posthog

Route requests across models in FastLLM — create, inspect or change frontend models, their default targets, weighted splits, and routing rules (by caller, prompt size, streaming, headers, budget…

azrtydxb/Fastllm-proxy

Adds Arize AX tracing to an LLM application for the first time.

github/awesome-copilot

Port a published computer vision paper's official code and training recipe onto a customer's own dataset, or diagnose why such a transfer produced bad numbers.

NVIDIA/skills

Take a working agent prototype to a scalable, observable production deployment on Microsoft Foundry.

microsoft/ai-agents-for-beginners

Take one working agent prototype go scalable, observable production deployment for Microsoft Foundry.

microsoft/ai-agents-for-beginners

Use during planning, implementation, PR review, or /qv-qip-triage when a change may affect public SDK API, native dependency, plugin contract, model registry contract, runtime, transport, storage…

tetherto/qvac

Apply Karpathy-style minimalism and anti-dependency principles to code and system design.

LearnPrompt/andrej-karpathy-skills

Resolve a non-trivial implementation or architecture decision before coding.

rapidaai/voice-ai

Add or modify telemetry/metrics instrumentation for assistant-api and integration-api flows while preserving metric schema compatibility and audit behavior.

rapidaai/voice-ai

Create or update repository documentation, runbooks, configuration references, and developer guidance.

rapidaai/voice-ai

Deploy AI and NLP-powered detection systems to identify business email compromise attacks by analyzing writing style, behavioral patterns, and contextual anomalies that evade traditional rule-based…

mukul975/Anthropic-Cybersecurity-Skills

Investigate AI observability evaluations — hog (deterministic code-based), llmjudge (LLM-prompt-based), and sentiment (user-message sentiment).

PostHog/posthog

Work with the Ambient Quality Agent (AQuA) added to this agents-cli project: augment the agents-cli agent with AQuA or attach the agent to an AQuA deployed elsewhere, read the quality insights it…

google/adk-recipes

Create, refactor, evaluate, and package agent skills from workflows, prompts, transcripts, docs, or notes.

aiskillstore/marketplace

Turn on AI + ML features in Grafana Cloud — Grafana Assistant (NL → PromQL/LogQL/TraceQL, dashboard build, incident investigation, MCP integration), Dynamic Alerting (Prophet forecasting + DBSCAN…

grafana/skills

Speed up long-sequence transformer training and inference. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Constrain LLM output with grammars; guarantee valid JSON. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Train sparse autoencoders to interpret model features. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Reference-free preference alignment, simpler than DPO. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

RL post-training for LLMs with Megatron and SGLang. An agent skill from Luciole-Studio/Misaka-Agent.

Luciole-Studio/Misaka-Agent

Review the configured cost alert rules and the alerts currently fired on the Agent Monitor dashboard, then explain exactly what tripped and why.

hoangsonww/Claude-Code-Agent-Monitor

A skill your agent uses when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.

sharpdeveye/maestro

Debug live Azure Kubernetes Service (AKS) incidents with a read-only, evidence-first investigation.

microsoft/GitHub-Copilot-for-Azure

Plan and coordinate a model deployment to Amazon SageMaker, including serving stack and real-time versus async inference.

waybarrios/opencode-power-pack

Check progress for a detached KERMT run (pretrain, finetune, or any kermtrundetached invocation).

NVIDIA/skills

Build AI applications on Microsoft Foundry using the azure-ai-projects SDK.

aiskillstore/marketplace

Workflow specifically for creating a new resource, supporting both autogen and manual generation.

GoogleCloudPlatform/magic-modules

Operate and troubleshoot the UAV Mission Compute SDK for PX4 telemetry, camera streaming, missions, computer vision, and edge AI demonstrations.

open-edge-platform/edge-ai-suites

A skill your agent uses when adding logging, metrics, or instrumentation — structured Logger usage, telemetry handler attachment, Ecto/Phoenix telemetry events.

j-morgan6/elixir-phoenix-guide

Inspect GitHub Actions self-hosted runner queues when a developer provides a run URL, job URL, runner label, or reports a blocked CI job, or invokes /qv-devops-runner-queue.

tetherto/qvac

Self-healing China mirror source resolver. An agent skill from LeoYeAI/openclaw-master-skills.

LeoYeAI/openclaw-master-skills

A Principal ML Engineer interviewer that simulates a FAANG-style ML system design interview covering the full lifecycle from data to production.

PrepLabsAI/InterviewMentor

Migrate workloads from Google Cloud Platform to AWS — plus AI and agentic workloads from any provider.

aws/agent-toolkit-for-aws

Analyze & debug GenAI/LLM apps: token cost & caching by prompt, model & provider; latency/errors; agent & tool loops/failures; conversations; guardrails; evaluations; OpenTelemetry/dt-evals setup.

Dynatrace/dynatrace-for-ai

Guides tenant isolation architecture in Qdrant for multi-tenant or multi-user applications.

qdrant/skills

Zero token cost. An agent skill from LeoYeAI/openclaw-master-skills.

LeoYeAI/openclaw-master-skills

Sync Agent Kernel skills and documentation from a specific commit hash.

yaalalabs/agent-kernel

Sync Agent Kernel skills from branch changes before a feature or bugfix is merged.

yaalalabs/agent-kernel

How to swap the DeepStream CV detection model in the VSS Alerts Blueprint verification (2dcv) mode - covers ONNX export, custom bbox parsers, compose mount gotchas, nvinfer config, runtime TRT…

NVIDIA/skills