superpowers-devops

Use before any DevOps build, change, or new feature — refine requirements through dialogue before touching infrastructure or code

Use when working with Docker — building images, writing Dockerfiles, debugging container issues

Use to execute a written implementation plan via subagents with review checkpoints

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup

Use when working with Kubernetes or Helm — authoring, reviewing, hardening, or debugging manifests, Deployments, Services, Ingress, RBAC, NetworkPolicy, or cluster operations

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Use when executing implementation plans with independent tasks in the current session

Use when encountering any bug, error, crash, or unexpected behavior — before proposing any fix

Use when implementing any infrastructure change, IaC module, CI pipeline, or DevOps automation — before writing any configuration, manifest, or script

Use before starting infrastructure or feature work that needs isolation from the current workspace — ensures an isolated workspace exists via native tools or git worktree fallback

Use at session start — orients the agent to the full DevOps skill set and when to invoke each skill automatically. If there is even a 1% chance a skill applies, check it before acting.

Use after brainstorming to create a detailed, step-by-step implementation plan for a DevOps task

Use when creating new skills, editing existing skills, or verifying skills work before deployment — especially when adding DevOps domain skills

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Use before declaring any work complete — run verification commands and confirm output before making any success claims

Use when designing, debugging, or fixing CI/CD pipelines — GitHub Actions, GitLab CI, Jenkins

Use when working with AWS, GCP, or Azure resource management, permissions, or deployments

Use when reviewing code or a codebase for DevOps readiness, security issues, and missing best practices

Use when analyzing code for performance issues, memory leaks, inefficient loops, blocking calls, and resource waste

Use when working with DNS records, propagation debugging, or domain routing

Use when the user pastes any error output, stack trace, log, or failure message — structured interpretation before diagnosis

Use when working with Terraform, Ansible, Pulumi, or any IaC tool — enforces plan-before-apply discipline

Use when working with load balancer configuration, upstream health checks, or traffic distribution

Use when setting up or debugging Prometheus, Grafana, logging, or alerting

Use when working with IPs, ports, firewall rules, routing, or diagnosing network connectivity issues

Use when working with Nginx, Traefik, or HAProxy — setup, config debugging, SSL termination, routing

Use when working with Vault, SOPS, secret scanning, or managing credentials safely