2. DevOps & Infrastructure

Diagnostic tool for validating SpecWeave reflection system health, checking configuration, permissions, and system state to resolve issues with learnings capture and MEMORY.md updates.

Provides SRE expertise for incident response, root cause analysis, and post-mortem documentation during production outages and performance issues.

Architects observability systems using OpenTelemetry, Prometheus, and Grafana for metrics, logs, traces, SLIs/SLOs, and alert management.

Architects and troubleshoots cloud network infrastructure including VPC, service mesh, zero-trust, load balancers, and CDN.

Deploys software agents from YAML configuration files, enabling consistent and automated infrastructure provisioning.

Command-line tool for orchestrating Letta AI agent fleets with Kubernetes-inspired management capabilities.

Manages system resources including memory blocks, tools, folders, files, and MCP servers for efficient infrastructure operations.

Provides real-time monitoring of server health, context window usage, and asynchronous operations for infrastructure visibility and management.

Validates Jenkinsfile pipelines for syntax, best practices, and debugging in CI/CD workflows.

Generates best-practice Ansible playbooks, roles, tasks, and inventory files for infrastructure automation.

Generates production-ready Fluent Bit configurations for log collection pipelines, including INPUT, FILTER, and OUTPUT sections.

Validates and secures GitLab CI/CD pipeline configurations through linting, testing, and best practice enforcement.

Generates best-practice GitHub Actions workflows and configurations for CI/CD, ensuring adherence to current standards and conventions.

Validates, lints, and tests GitHub Actions workflow files, custom actions, and public actions for syntax and execution correctness in CI/CD pipelines.

Validates, lints, and secures Azure DevOps pipeline configurations to ensure reliable and secure CI/CD workflows.

Validates Helm charts and Kubernetes resources for correctness, best practices, and CRD compatibility.

Generates best-practice Jenkinsfiles for Declarative and Scripted pipelines to streamline CI/CD implementation.

Generates production-ready bash scripts following best practices for shell automation, text processing, and command-line tool development.

Generates best-practice PromQL queries for monitoring, alerting, and observability dashboards in Prometheus.

Validates, lints, and tests Kubernetes YAML manifests for syntax, correctness, and CRD documentation compatibility.

Generates optimized, production-ready Dockerfiles adhering to best practices for containerization and build efficiency.

Provides tools for diagnosing and resolving Kubernetes cluster issues, including pod failures, network problems, and resource usage.

Generates best-practice Azure Pipelines for CI/CD workflows following current standards.

Validates and optimizes Prometheus Query Language (PromQL) queries to ensure correctness and efficiency in infrastructure monitoring systems.