Update to Zilliz

{
  "description": "Use when the user wants to check cluster status, collection statistics, load states, or get an overview of their Zilliz Cloud resources.",
  "included_files": [],
  "name": "monitoring",
  "skill_md_contents": "---\nname: monitoring\ndescription: Use when the user wants to check cluster status, collection statistics, load states, or get an overview of their Zilliz Cloud resources.\n---\n\n## Prerequisites\n\n1. CLI installed and logged in (see setup skill).\n2. Cluster context set for collection-level monitoring (see setup skill).\n\n## Commands Reference\n\nAll monitoring commands that target collections accept an optional `--database <db-name>` flag. If omitted, the database from the current context is used.\n\n### Cluster Status\n\n```bash\n# Current context\nzilliz context current\n\n# Cluster details (status, plan, region, endpoints)\nzilliz cluster describe --cluster-id <cluster-id>\n```\n\n### Collection Overview\n\nList all collections with their stats:\n\n```bash\n# List collections\nzilliz collection list\nzilliz collection list --database <db-name>\n\n# For each collection, get stats and load state:\nzilliz collection get-stats --name <collection-name>\nzilliz collection get-load-state --name <collection-name>\n```\n\nIf the cluster has multiple databases, iterate through each database by running `zilliz database list` first, then `zilliz collection list --database <db-name>` for each.\n\n### Database Overview\n\n```bash\nzilliz database list\n```\n\n### All Clusters\n\n```bash\nzilliz cluster list --all\n```\n\n### Time-series Metrics\n\nFor cluster-wide time series (CU sizing, storage, serverless VCU, slow queries) use `zilliz cluster metrics`:\n\n```bash\nzilliz cluster metrics --cluster-id <cluster-id> -m CU_COMPUTATION --period 1h\n```\n\nFor per-collection time series (QPS, latency, entity counts, hybrid-search aliases) use `zilliz collection metrics` -- see the collection skill for metric scope rules and the full alias list:\n\n```bash\nzilliz collection metrics -c <collection-name> -m SEARCH_QPS --period 1h\n```\n\nBoth commands render an inline Braille line chart by default (one block per metric with a `min / max / avg / last` summary). Pass an explicit `-o table` (or `--output table`) for the pivot-table layout, or use `-o json` / `--query` to get raw data for scripting.\n\n## Presenting Results\n\nWhen the user asks for a status overview, collect and present information as a summary table:\n\n**Cluster Info:**\n- Cluster ID, name, status (RUNNING/SUSPENDED/etc.)\n- Plan type, region, create time\n\n**Collections Summary:**\nPresent as a table with columns:\n| Collection | Rows | Load State |\n|---|---|---|\n\nGather this by running `collection list`, then `get-stats` and `get-load-state` for each collection.\n\n## Guidance\n\n- When presenting status, use `--output json` to get machine-readable data, then format it into a readable summary for the user.\n- If the cluster is suspended, note this prominently and inform the user that data-plane operations are unavailable.\n- For multiple clusters, show a summary table of all clusters first, then drill into the selected one.\n"
}