What specific performance metrics can I track?

The skill provides access to time-series data for CU computation, storage usage, search QPS, latency, and entity counts over various time periods.

How are monitoring results presented?

Results are typically formatted into clean, readable summary tables that include cluster info, row counts, and load states for quick analysis.

Can I monitor multiple databases within a single cluster?

Yes, the skill allows you to list all databases and iterate through them to gather statistics and collection data for each.

How do I check if my Zilliz collection is loaded?

You can use this skill to retrieve the load-state of any collection, which confirms if the data is currently resident in memory and available for search.

Does this skill work with suspended clusters?

The skill will identify and report if a cluster is suspended, informing you that data-plane operations are currently unavailable until the cluster is resumed.

Zilliz Cloud Monitoring

Name: Zilliz Cloud Monitoring
Author: zilliztech

byzilliztech

•

Analíticas y Monitorización

Monitors Zilliz Cloud cluster health, collection statistics, and performance metrics through natural language commands.

This skill empowers developers to maintain high-performance vector databases by providing comprehensive visibility into Zilliz Cloud resources. It enables real-time tracking of cluster statuses, collection load states, and granular performance metrics such as QPS and latency directly within Claude Code. By automating the retrieval of system statistics and resource usage, it helps identify bottlenecks, verify deployment readiness, and ensure that vector search infrastructure is operating at peak efficiency.

Características Principales

01Detailed collection statistics including row counts and entity data

023 GitHub stars

03Real-time cluster status and resource health tracking

04Performance metrics for CU computation, QPS, and search latency

05Comprehensive monitoring of vector collection load states

06Automated summary reporting for multi-database environments

Casos de Uso

01Verifying if a vector collection is fully loaded and ready for search operations

02Generating status reports for Zilliz Cloud clusters and resource distribution

03Identifying performance bottlenecks using time-series QPS and latency metrics

Características Principales

01Detailed collection statistics including row counts and entity data

023 GitHub stars

03Real-time cluster status and resource health tracking

04Performance metrics for CU computation, QPS, and search latency

05Comprehensive monitoring of vector collection load states

06Automated summary reporting for multi-database environments

Casos de Uso

01Verifying if a vector collection is fully loaded and ready for search operations

02Generating status reports for Zilliz Cloud clusters and resource distribution

03Identifying performance bottlenecks using time-series QPS and latency metrics