Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →automateyournetwork/gcp-cloud-monitoring
Google Cloud Monitoring — time series metrics, alert policies, active alerts, metric discovery.
Passed 17 of 21 test cases with the skill, and 7 of 21 without it.
and 8 more in the full report
11 fixed7 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
When connecting to the Google Cloud Monitoring MCP server, what specific environment variable must be set to scope time series and alert queries to the correct project?
| Checked | Without skill | With skill |
|---|---|---|
| Specifies GCP_PROJECT_ID as the required environment variable name. | Missed | Passed |
The instructions your model reads when the skill loads.
https://monitoring.googleapis.com/mcp (Streamable HTTP)GOOGLE_APPLICATION_CREDENTIALS) or gcloud auth application-default loginGCP_PROJECT_ID environment variable| Tool | What It Does |
|---|---|
list_timeseries | Query time series data — CPU, memory, network, disk metrics for any GCP resource |
list_metric_descriptors | Discover available metric types in a project — find what you can monitor |
list_alert_policies | List all alerting policies — conditions, notification channels, thresholds |
get_alert_policy | Get details of a specific alerting policy |
list_alerts | List current and past alert violations — what's firing right now |
get_alert | Get details of a specific alert violation |
When a user asks "how is our GCP network performing?":
list_alerts to find any active alert violationslist_timeseries for compute.googleapis.com/instance/network/received_bytes_count and sent_bytes_countlist_timeseries for compute.googleapis.com/instance/network/received_packets_dropped_countlist_timeseries for compute.googleapis.com/firewall/dropped_packets_countlist_timeseries for loadbalancing.googleapis.com/https/request_count and total_latenciesWhen investigating GCP alerts:
list_alerts — find what's currently firingget_alert — condition, threshold, resource affectedget_alert_policy — what triggers this alert, notification channelslist_timeseries for the affected metric — see the spike/anomalygcp-cloud-logging for correlated log entriestest cases passed, vs 7 / 21 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.