k8s-agent-stack

Implement Agent-to-Agent (A2A) protocol for inter-agent communication. Use for agent discovery, agent cards, task delegation, and multi-agent orchestration. Triggers on "A2A protocol", "agent-to-agent", "agent discovery", "agent card", "multi-agent", "agent delegation", "agent communication", or when implementing spec/api/017-a2a-protocol.md.

Implement CI/CD pipelines for AI agent deployment with evaluation gates. Use for GitHub Actions workflows, GitOps with ArgoCD, container image building, and automated testing. Triggers on "CI/CD", "pipeline", "GitHub Actions", "GitOps", "ArgoCD", "deployment automation", "continuous deployment", or when implementing safe agent release workflows.

Implement agent evaluation and safety gates using MLflow 3.x. Use for creating LLM-as-Judge scorers, evaluation datasets, quality gates, tracing, and continuous evaluation. Triggers on "evaluate agent", "MLflow scorer", "LLM judge", "safety evaluation", "quality gate", "agent testing", "hallucination detection", or when implementing spec/010-agent-evaluation.md requirements.

Build CLI tools using Go with Cobra and Viper. Use for implementing agentctl commands, interactive prompts, configuration management, and output formatting. Triggers on "CLI", "agentctl", "command line", "cobra", "terminal application", "interactive prompt", or when implementing spec/009-developer-experience.md CLI section.

Build the AgentStack API Gateway in Go with Fiber/Chi. Use for creating REST API endpoints, HTTP handlers, middleware, request validation, and API routing. Triggers on "build API", "create endpoint", "HTTP handler", "REST API", "API gateway", "Fiber handler", "Chi router", or when implementing spec/004-api-design.md endpoints.

Deploy serverless workloads with Knative Serving for scale-to-zero and autoscaling. Use for creating Knative Services, configuring autoscaling, traffic splitting, and revisions. Triggers on "knative service", "scale-to-zero", "serverless deployment", "ksvc", "knative autoscaling", "traffic splitting", or when deploying agents as serverless workloads.

Generate production-ready Kubernetes manifests for AgentStack. Use for creating Deployments, Services, ConfigMaps, Secrets, RBAC, and other K8s resources. Triggers on "create deployment", "k8s manifest", "kubernetes yaml", "pod spec", "service definition", "configmap", "RBAC", or when deploying components to Kubernetes.

Implement multi-tenant PostgreSQL database layer with row-level security. Use for database schema design, tenant isolation, migrations, connection pooling, and data access patterns. Triggers on "database schema", "PostgreSQL", "multi-tenant", "row-level security", "RLS", "database migration", "sqlc", or when implementing the data layer for AgentStack.

Implement OpenTelemetry-based observability for traces, metrics, and logs. Use for distributed tracing, Prometheus metrics, structured logging, and agent monitoring. Triggers on "OpenTelemetry", "OTEL", "tracing", "metrics", "observability", "Prometheus", "Grafana", "distributed tracing", or when implementing spec/007-observability.md.

Implement authentication, authorization, and security controls. Use for JWT handling, API key management, RBAC, OAuth integration, and security policies. Triggers on "authentication", "authorization", "JWT", "API key", "RBAC", "OAuth", "security", "permissions", or when implementing spec/006-security-governance.md.

Guide for creating effective Claude Skills for the AgentStack Sovereign Platform. Use this skill when creating new skills, updating existing skills, or learning skill design patterns. Triggers on requests like "create a new skill", "build a skill for X", "skill design", "skill template", or "extend Claude's capabilities".