Use when reviewing, auditing, or sanity-checking rook (github.com/rook/) code, tests, docs, or workflows — a working tree, branch, commit range, or PR; when checking a branch before opening a PR; when reviewing, critiquing, or stress-testing a rook design proposal, design doc, enhancement doc, or design/ change before…
Use when authoring or shepherding changes to rook (github.com/rook/) repos — committing, pushing branches, opening or updating PRs, weighing review feedback, backporting, regenerating CRDs or generated code, writing tests or GitHub Actions workflows, watching or retrying CI, or before ANY gh write (comment, label…
Use when triaging rook (github.com/rook/) issues or PRs — grooming or clearing the backlog, labeling or categorizing issues, finding duplicate issues, cross-linking an issue to a PR (or a PR to the issue it fixes), checking what info a bug report is missing, deciding who should review a PR or requesting reviewers, or…
This skill should be used when the user asks to deploy or install a Ceph cluster on bare-metal/VMs using cephadm — e.g. "deploy Ceph with cephadm", "cephadm bootstrap", "install Ceph without Kubernetes", "set up a Ceph cluster on bare-metal". No Kubernetes/Rook — plain cephadm + ceph orch, container-orchestrated Ceph…
This skill should be used when the user asks to deploy or install a Ceph cluster on Kubernetes using Rook — e.g. "deploy Ceph with Rook", "install rook-ceph operator", "bootstrap a CephCluster CRD", "set up Rook on Kubernetes". Platform-agnostic (works on any Kubernetes distribution, not tied to OpenShift/ODF).
This skill should be used when the user asks to set up RGW (RADOS Gateway) multisite replication between two Rook-managed Ceph clusters — e.g. "set up Rook RGW multisite", "CephObjectRealm/CephObjectZone multisite setup", "configure multisite replication with Rook CRDs", "primary/secondary RGW zone with Rook".…
Use this skill whenever the user needs to operate or diagnose a Ceph cluster via its ceph-mgr Dashboard REST API — decode a HEALTHWARN/ERR state into cause + action (clusterhealth), read the cluster status, inspect OSDs (tree/df/perf), placement groups (summary/stuck/scrub), pools (list/usable capacity), RBD images…