Claude Skills for a DevOps / SRE — Page 29
Dynamo Recipe Runner
Select, validate, minimally patch, and deploy existing NVIDIA Dynamo inference recipes on Kubernetes.
Earth2Studio Forecast Wrapper Builder
Build and validate Earth2Studio time-stepping forecast wrappers.
Holoscan Python Wheel Installer
Install Holoscan SDK Python bindings in a virtual environment and verify them on a Linux NVIDIA GPU system.
Jetson CSI Camera Customization
Generate and validate kernel device-tree overlays for MIPI and GMSL cameras on custom Jetson Thor or Orin carriers.
Jetson UPHY Lane Allocation
Configure UPHY lane allocation for Orin and Thor custom carriers.
Jetson Inference Memory Tuning
Choose a Jetson serving runtime and generate memory flags from the device snapshot and workload.
Jetson BSP Image Validator
Validate a flashed Jetson BSP image on disk and on the target device.
NeMo-RL Brev Runbook
Helps NeMo-RL agents manage storage, caches, logs, and authentication safely on Brev instances.
AWS Context Discovery
Resolve the active AWS environment before any account operation.
SageMaker Deployment Planner
Choose a practical Amazon SageMaker deployment path for your model, traffic pattern, and latency needs.
Hugging Face Spaces Builder
Build, deploy, debug, and maintain machine-learning apps on Hugging Face Spaces.
Agent Platform Endpoint Management
Manage Agent Platform serving endpoints and troubleshoot common endpoint failures.
Google Cloud Performance Advisor
Assess and improve workload performance using the Google Cloud WAF.
Expo EAS Workflow Assistant
Write and validate EAS CI/CD workflows for Expo projects.
Expo SDK Upgrade Assistant
Guides Expo SDK upgrades, dependency fixes, and compatibility cleanup.
n8n AI Agent Architecture Guide
Design n8n AI agents with the right nodes, tool connections, memory, structured output, and human approval.
n8n MCP Workflow Router
Routes n8n-mcp tasks to the right skills and reduces production workflow failures.
React Native Library Builder
Scaffold publishable React Native libraries or local native modules with a guided workflow.
Stable Interface Design
A practical guide to designing stable, clear, and hard-to-misuse APIs and module interfaces.
Context Compression Strategies
Compress long-running agent sessions while preserving files, decisions, risks, and next actions.
Project Development Methodology
Decide whether an LLM fits the job, then design a staged agent pipeline with predictable parsing, iteration, and cost control.
GKE GPU/TPU Disruption Diagnosis
Diagnose and mitigate GKE GPU/TPU node disruptions caused by host maintenance.
GKE Cost Intelligence
Analyze GKE costs across clusters and workloads by combining BigQuery billing exports with live utilization metrics.
AI Workload Migration to GKE Inference
Move existing AI inference workloads to self-hosted inference on Google Kubernetes Engine.