Reviews Terraform/OpenTofu plans, detects drift, performs state surgery (mv/rm/import), upgrades providers, and traces Terragrunt cache errors. Multi-cloud. Use when working with Terraform, OpenTofu, Terragrunt, terraform plan, drift, or provider upgrades.
Designs and debugs ArgoCD ApplicationSets, picks generators, templates per-tenant deploys, configures sync waves and hooks, and untangles syncPolicy.automated prune/selfHeal. Use when working with ArgoCD, ApplicationSet, sync wave, GitOps, or per-tenant Application deploys.
Reviews and hardens Dockerfiles and docker-compose files — multi-stage build conversion, base-image choice, layer caching, secret leakage, root-user containers, missing healthchecks. Use when reviewing a Dockerfile, optimizing image size or build time, writing a compose file, or auditing container security.
Debugs Kubernetes pods and controllers — FailedCreate, ImagePullBackOff, init-container failures, probe flapping, missing service endpoints, GKE NEG readiness. Use when a pod is not Running, a Deployment/StatefulSet shows FailedCreate, image pulls fail, or services lack endpoints.
Designs and audits Kubernetes Operators — CRD shape, reconcile-loop correctness, finalizer and status-subresource handling, OperatorHub capability levels, framework choice. Use when building a controller for a CRD, reviewing an operator for capability gaps, or designing the API surface of a Custom Resource. Not for…
Guides developers through mindfulness exercises and stress-reduction techniques during coding sessions. Based on Anthropic's Mindfulness Mentor prompt.
Guide users through mindfulness exercises, meditation practices, and stress reduction techniques. Use when users ask for help with relaxation, stress management, breathing exercises, or cultivating inner peace.
Inject and audit 1Password secrets via the op CLI: op:// references with op run/op inject, an always-ask permission gate, and an opt-in deny-capable PreToolUse audit hook. Use when handling API keys, tokens, credentials, .env secrets, OPSERVICEACCOUNTTOKEN, or 1Password.
Injects and audits 1Password secrets via the op CLI using op:// references, prefers op run/op inject over op read so values stay out of context, gates every op call behind an always-ask permission rule, and ships an opt-in deny-capable audit hook. Use when handling API keys, tokens, passwords, credentials, .env…
Installs skills from a user-curated manifest (/.claude/skill-manifest.json) into the current project's .claude/skills/ directory. Symlinks local skills, runs npx skills add for third-party ones, and advises /plugin install for native Claude plugins. Optionally scans the project for trigger files (Dockerfile, wrang.
Installs skills from a user-curated manifest (/.claude/skill-manifest.json) into the current project's .claude/skills/ — symlinks local skills, runs npx skills add for third-party ones, and advises /plugin install for native Claude plugins. Optionally scans the project for trigger files (Dockerfile, wrangler.jsonc…