2. DevOps & Infrastructure

Orchestrates long-running build workflows with token-capped logging and failure diagnosis for ROCm and similar builds, minimizing changes and providing evidence-based reports.

Provides end-to-end DevOps guidance for infrastructure, CI/CD, containerization, cloud platforms, and SRE best practices across the full engineering lifecycle.

Provides self-maintenance guidance for Claude Dash infrastructure, covering system health, memory management, index optimization, and cleanup operations.

Reviews production operational readiness by validating permissions, observability, and failure handling to prevent on-call incidents during critical system failures.

Guides setup of monitoring systems (Prometheus, Grafana), incident response workflows, and SLO/SLI management to reduce MTTR and improve system reliability.

Provides Kubernetes cluster troubleshooting, diagnostics, and incident response for pod failures, networking, and resource management issues.

Assists in implementing GitOps workflows with Flux and ArgoCD for declarative infrastructure management, including Helm releases and drift detection.

Guides cloud cost optimization for AWS, Azure, and GCP through bill analysis, resource rightsizing, and Reserved Instances/Savings Plans strategies.

Provides configuration guidelines for AWS cloud infrastructure services including S3, EC2, and Lambda for deployment and management.

Designs, optimizes, and secures CI/CD pipelines for GitHub Actions, GitLab CI, and Jenkins, covering build, test, and deployment workflows.

Monitors long-running tasks with terminal interface and HTTP API, featuring scheduler integration and automatic restarts for reliability.

Expert assistance for writing, debugging, and optimizing safe, portable Bash and POSIX shell scripts on macOS/Linux systems.

Generates markdown reports analyzing batch job manifests, timings, and failures for DevOps monitoring and cross-project communication.

Provides step-by-step instructions for setting up CI/CD pipelines with GitHub Actions, including testing and deployment automation.

Manages Readarr e-book library operations, including book searches, download monitoring, and service health checks via API interactions.

Provides a Docker-based environment for converting markdown files, ensuring isolated execution when alternative tools are unavailable.

Assists in creating, refactoring, and linting Bash scripts with shellcheck, adhering to strict conventions.

Deploys the Baume MCP server to Fly.io with correct build context for seamless cloud deployment.

Runs all quality gates (code, security, performance) and reports detailed status for pipeline verification.

Builds and configures Grafana dashboards for infrastructure monitoring, observability, and metrics visualization using Prometheus and InfluxDB data sources.

Provides expert guidance for Kubernetes cluster management, including deployment, troubleshooting, and configuration of Helm, ArgoCD, and ingress controllers.

Diagnoses Kubernetes cluster issues by analyzing pods, logs, events, and cluster state.

Automates Azure infrastructure deployment (Cosmos DB, Managed Identity, Container Apps) via Bicep templates in specified region and environment.

Automates CI/CD pipeline creation and management in Azure DevOps, including build, release, and deployment configurations for seamless software delivery.