cb-analytics-adminlisted

Use this skill when the user wants to inspect or manage the Analytics service's runtime — checking ingestion health, killing runaway queries, restarting nodes, or diagnosing performance. Trigger when they mention "ingestion status", "active queries", "completed requests", "restart service", "cancel request", "service status", or "Analytics health".
celticht32/Couchbase-Skills-for-Claude.ai · ★ 1 · AI & Automation · score 75

Install: claude install-skill celticht32/Couchbase-Skills-for-Claude.ai

# Analytics service admin You have 7 tools for runtime management. ## Status snapshot (read-only, safe) - `get_service_status(cluster)` — overall service state, replica lag, authorised node list - `get_ingestion_status(cluster)` — per-link ingestion state, pending ops - `get_active_requests(cluster)` — what's running right now - `get_completed_requests(client_context_id=None, cluster)` — recent history; pass `client_context_id` to filter to one request ## Diagnostic workflow When a user says "queries are slow" or "ingestion looks stuck": 1. `get_service_status` — is the service even healthy? Watch `ccRevLag` (replication lag). 2. `get_ingestion_status` — for each link, look at `pendingOperations`. A non-zero pending count after a quiet period usually means a stuck link. 3. `get_active_requests` — long-running queries appear here with `elapsedTime`. Anything over a few seconds is suspect. 4. `get_completed_requests` — look for a pattern of errors or unusually long durations. ## Destructive operations (use with care) - `cancel_request(client_context_id, cluster)` — abort one in-flight query. Get the id from `get_active_requests`. - `restart_node(cluster)` — restart only the Analytics process on the local node. May briefly disrupt queries routed to that node. - `restart_service(cluster)` — **cluster-wide** Analytics restart. All active queries fail. Don't suggest this lightly; warn the user. ## Confirmation patterns When the user asks to cancel or