2. DevOps & Infrastructure

Configures access permissions for Claude Code projects, resolves permission errors, and manages Git worktree permissions for team collaboration.

Configures and optimizes MCP servers in Claude Code, including token usage, connection troubleshooting, and tool selection for efficiency.

Generates infrastructure code based on defined architecture using Terraform, Bicep, and Kubernetes manifests for automated cloud deployment.

Guides effective usage of FleetFlow, a Kubernetes-based container orchestration tool for managing containerized applications.

Enforces pure pipeline by prohibiting runtime code, using only specs, SEA™, and generators.

Enables debugging and troubleshooting of SEA-Forge™ services through OpenTelemetry-based observability, including traces, metrics, and logs for performance and incident response.

Enables read-only command-line operations for inspecting GitHub repositories, including code, commits, and issues without modifications.

Explains the required sequence and success signals for each stage in a pipeline specification.

Guides recording of terminal demonstrations for CLI tools and DevOps workflows using asciinema format.

Guides developers in creating interactive demo scripts using Playwright within Kubernetes, executed via screenenv Jobs for recording.

Coordinates YAML-defined workflows, handling step execution, gate decisions, and evaluation for automated pipeline management.

Provides guidelines for writing, reviewing, and refactoring Pulumi code to ensure optimal infrastructure deployment performance and reliability.

Provides guidance on application versioning strategies and deployment release processes for consistent software delivery.

Expertly models APM observability layers for Documentation Robotics documentation.

Enables security scanning, compliance validation, deployment automation, and infrastructure management for operational workflows.

Enforces safe, portable, and maintainable shell scripting best practices with POSIX compliance, error handling, and quoting standards.

Manages Kubernetes clusters using kubectl, Helm, and kustomize for deployments, services, and troubleshooting operations.

Manages ephemeral Neon databases for testing, CI/CD pipelines, and isolated development environments with rapid setup and teardown capabilities.

Terminates an active Ralph Loop process, halting ongoing automation or service operations in infrastructure environments.

Provides health monitoring procedures for infrastructure platforms, enabling system health assessment, health audits, and monitoring setup.

Analyzes and parses logs from any platform to troubleshoot infrastructure issues efficiently.

Provides deep expertise for troubleshooting, configuring, and optimizing GitHub Actions, Railway, Supabase, and Postgres platforms.

Guides terminal session management with tmux for persistent shells, multiple windows, and background process monitoring in shell environments.

Identifies, categorizes, and resolves infrastructure errors across platforms using recognized diagnostic patterns.