Kubeflow
Use when working with Kubeflow — route to the correct sub-skill based on what the user needs: TrainJob CRDs, Kubeflow Pipelines v2, or legacy Training Operator v1.
Stakater Reloader
Use when working with Stakater Reloader — watching ConfigMaps/Secrets and triggering workload rollouts on changes. Covers annotations, Helm values, patterns, and troubleshooting. NOT for CRD-based operators (no CRDs).
Harbor Helm
Use when deploying, configuring, or upgrading Harbor on Kubernetes via Helm chart — values configuration, external database, TLS/certificates, storage, ingress, authentication, and production patterns.
Kserve Operator
Create and manage KServe CRDs — InferenceService, ServingRuntime, InferenceGraph, LLMInferenceService, LocalModel, ClusterServingRuntime, and 22 CRDs under serving.kserve.io.
Netbird Operator
NetBird Kubernetes operator (netbirdio/kubernetes-operator) — CRDs for exposing cluster services on the NetBird mesh, managing peers/routes/groups from inside K8s. Covers SetupKey, Group, NetworkRouter, NetworkResource, NetworkEgress, SidecarProfile, ClusterProxy.
Higress
Use when working with Higress — AI Gateway, Wasm plugins, Ingress, Helm deployment, or operator CRDs. Triggers: higress, AI Gateway, WasmPlugin, McpBridge.
Rook Ceph
Use when working with Rook-Ceph on Kubernetes — deploying/managing Ceph clusters (operator) or running diagnostic/CLI commands (toolbox). Routes to sub-skills based on task.
Netbird
Use when working with NetBird — route to the correct sub-skill based on what you need: client CLI, Terraform provider, or the Kubernetes operator.
Gitea
Use when working with Gitea — route to the correct sub-skill based on what the user needs: API automation, runner management, container registry, webhooks, or tea CLI.
Flux
Use when working with Flux CD — debugging live clusters, writing/auditing Flux resources, or asking Flux CD questions. Routes to 3 sub-skills depending on the task.
Nextcloud Helm
Use when deploying, configuring, or upgrading Nextcloud on Kubernetes via Helm. Covers HelmRelease values, database (external PostgreSQL/MySQL or bundled MariaDB), Gateway API/Ingress routing, Redis cache, S3/Swift primary storage, Collabora Online, Imaginary previews, cron jobs, and metrics. NOT for API-level user/group operations.
Nextcloud
Use when working with Nextcloud — deploying on Kubernetes via Helm (nextcloud-helm) or managing users/groups/apps via the Provisioning API (nextcloud-api). Triggers: nextcloud deploy, nextcloud OCC, NC user provisioning, nextcloud-helm.
Cilium Network
Use when configuring Cilium CNI networking, writing network policies, debugging pod connectivity issues, setting up LB IPAM or L2 announcements for Service LoadBalancer IPs, enabling BGP route advertisement, configuring transparent encryption or Hubble observability, or managing Cilium security features (host firewall, Local Redirect Policy, CiliumCIDRGroup). Not for Gateway API (use cilium-gatew…
Nextcloud Api
Use when managing Nextcloud users, groups, and apps via the Provisioning API (OCS). Covers user CRUD, group management, app enable/disable, and curl examples. NOT for Helm deployment — use nextcloud-helm.
Netbird Server
Self-hosted NetBird control plane on Kubernetes — the netbirdio/netbird-server combined management/signal/relay/STUN server + dashboard. Covers the helmforge/netbird chart, config.yaml, PostgreSQL store, embedded Dex IdP, gRPC/HTTP routing, STUN, and ESO secret delivery.
Kubeflow Trainer
Kubeflow Trainer v2.2 — TrainJob, TrainingRuntime, ClusterTrainingRuntime CRDs for framework-agnostic distributed training on Kubernetes. Covers PyTorch, TensorFlow, JAX, XGBoost, MPI, and Flux workloads.
Gitea Tea
Work with Gitea using tea CLI for auth, repo, issue, pull request, release, actions, webhook, and notification workflows. Use when user references Gitea, self-hosted git forges, or asks for tea commands.
External Dns
Use when working with ExternalDNS — synchronizing Kubernetes resources with DNS providers (Cloudflare). Covers providers, sources, registry, RBAC, Gateway API integration, Helm values. No CRDs.
External Secrets
Use when working with External Secrets Operator (ESO) — syncing K8s Secrets from external providers (HashiCorp Vault, AWS, GCP, Azure). Covers SecretStore, ExternalSecret, PushSecret, template engine, Helm values, Vault provider auth.
Mariadb Operator
Create and manage MariaDB operator CRDs — 12 CRDs under k8s.mariadb.com, Galera HA, MaxScale, backups, PITR, monitoring, and connection pooling.
Gitea Registry
Use when working with the Gitea container registry — OCI/Docker v2 API, push/pull images, multi-arch builds, package management via API, and configuration for supported package types.
Atlas
Use when working with Atlas Operator on Kubernetes — creating or troubleshooting AtlasSchema or AtlasMigration resources; configuring DevDB, migration policies, credential patterns, or schema diff/lint rules.
Nvidia Device Plugin
Use when working with NVIDIA GPU support on Kubernetes — device plugin, GPU Feature Discovery, Node Feature Discovery, CDI, MIG, time-slicing. Covers Helm chart, values, configuration. No CRDs (ConfigMap-based).
Cert Manager
Use when creating or managing cert-manager CRDs — Certificate, Issuer, ClusterIssuer, CertificateRequest. Covers ACME DNS-01/HTTP-01, self-signed, CA issuers, Gateway API integration, and common patterns.
Netbird Terraform
NetBird Terraform provider (netbirdio/netbird) — groups, peers, routes, networks, network resources/routers, policies, setup keys, DNS zones/records, posture checks, users, tokens, SCIM, identity providers, reverse proxy services. Declarative NetBird management via public API.
Helm
Use when working with Helm — route to the correct sub-skill based on what you need: writing Helm charts or production operations (GitOps, release inspection, OCI, hooks). **Manual helm CLI for prod deploys is NOT recommended — prefer GitOps (Flux, ArgoCD).**
Dragonfly
Use when working with DragonflyDB operator on Kubernetes — creating or troubleshooting Dragonfly resources, configuring replication, snapshots, TLS, authentication, or affinity/scheduling for Dragonfly instances.
Rook Ceph Operator
Use when deploying or managing Rook-Ceph CRDs — CephCluster, CephBlockPool, CephFilesystem, CephObjectStore, CephNFS, CephRBDMirror, and supporting resources. Covers operator chart config, cluster spec, CSI settings, storage classes.
Rook Ceph Toolbox
Use when running ceph CLI commands from the Rook toolbox pod — cluster health, OSD management, pool operations, RBD commands, CephFS management, RGW admin, and common diagnostic operations.
Flagger
Use when working with Flagger — progressive delivery, canary deployments, A/B testing, blue/green on Kubernetes. Covers Canary CRD, analysis/meshes/metrics/webhooks, Helm values. CRDs: Canary, MetricTemplate, AlertProvider.
Cnpg
Use when working with CloudNativePG (CNPG) for PostgreSQL on Kubernetes — creating or troubleshooting Cluster, Backup, ScheduledBackup, Pooler, or ImageCatalog resources; defining bootstrap, storage, backup, or affinity settings.
Netbird Cli
NetBird client CLI — install, connect (up/down), status, networks, reverse proxy (expose), SSH, Kubernetes access, and debugging. Commands verified against v0.76.x.
Harbor Terraform
Use when managing Harbor infrastructure as code with Terraform — projects, robot accounts, registries, replication rules, retention policies, webhooks, users, groups, system config, and the goharbor/terraform-provider-harbor.
Gitea Runner
Use when configuring Gitea Actions runners — registration, deployment modes, Docker vs host mode, Talos/Kubernetes host-mode, ephemeral runners, and v1.26 Actions features.
Kubeflow Pipelines
Kubeflow Pipelines v2 — Python DSL, IR YAML compilation, @dsl.component, @dsl.pipeline, control flow, Kubernetes Native API, and artifact management.
Sealed Secrets
Use when working with Sealed Secrets — encrypting Kubernetes Secrets for safe Git storage. Covers SealedSecret CRD, kubeseal, key management, encryption flow, Helm values, controller config, key rotation.
Helm Ops
Helm production operations — CLI usage for development/debug/emergency, release inspection, troubleshooting, OCI registry, hooks, values management, and GitOps integration (Flux HelmRelease, ArgoCD). **For production deploys, prefer GitOps over manual helm CLI.**
Gitea Api
Use when working with the Gitea REST API — authentication, token management, repository/issue/PR CRUD, package management, admin operations, and general API automation with curl.
Harbor Api
Use when working with the Harbor REST API v2 — project management, artifact operations, robot accounts, replication, vulnerability scanning, OIDC/LDAP config, garbage collection, and general API automation with curl.
Higress Operator
Create and manage Higress CRDs — WasmPlugin, Http2Rpc, McpBridge, AI Gateway, 41 Wasm plugins, 16 AI provider integrations, and Gateway configuration.
Gitea Webhooks
Use when managing Gitea webhooks — creating webhooks via API, understanding event types, system vs repo vs org webhooks, payload verification with HMAC-SHA256, and supported webhook formats.
Cilium Gateway
Use when creating Gateway API resources for ingress, configuring TLS termination or passthrough, setting up HTTP-to-HTTPS redirect or traffic splitting, integrating oauth2-proxy or ExternalDNS with Cilium, or debugging Cilium Gateway controller issues including the Programmed=False cosmetic bug.
Mariadb Helm
Deploy MariaDB operator on Kubernetes via Helm — 3 charts, production HA values, Galera, MaxScale, backups, PITR configuration.
Helm Chart
Writing Helm charts — chart anatomy, templates, Go template syntax, helpers, values design, schema validation, library charts, testing, and common chart-writing mistakes.
Kserve
Use when working with KServe — model inference, ServingRuntime, InferenceService, Helm deployment, or operator CRDs. Triggers: kserve, InferenceService, model serving, ModelMesh.
Harbor
Use when working with Harbor container registry — route to the correct sub-skill based on what the user needs: API calls, Helm deployment, or Terraform management.
Kubeflow Training Operator
Legacy Kubeflow Training Operator v1 — PyTorchJob, TFJob, MPIJob, XGBoostJob, ModelMesh CRDs for distributed training on Kubernetes (deprecated in favor of Trainer v2).
Mariadb
Use when working with MariaDB operator — Helm deployment, operator CRDs, Galera HA, MaxScale, or backups. Triggers: mariadb, Galera, MaxScale, PITR.
Higress Helm
Deploy, configure, or upgrade Higress AI Gateway on Kubernetes via Helm chart. Covers Gateways, plugins, Ingress/CRD routing, observability, and production patterns.
Kserve Helm
Deploy KServe on Kubernetes via Helm — 10 charts, Serverless/RawDeployment/ModelMesh modes, KServe/ModelMesh/annotator/router configurations.