Skip to content
Get packs

Cloud Monitoring Metric Finder

Lets an agent look up and pick the right Google Cloud Monitoring metrics for a service from live API data.

Source Download skill
Repository
google/skills
Stars
21,782
Licence
Apache-2.0
Files
2 files

What it does

When you ask about monitoring a Google Cloud service (for example Cloud Run, BigQuery or Cloud SQL), the agent queries Google Cloud Monitoring for the list of metrics that service exposes, then filters that list by keywords such as CPU, latency or connections to suggest the most relevant ones. It is designed to use live data from your project rather than guessing metric names from memory. If the needed query tool is not set up, it can add a Google Cloud Monitoring server entry to your MCP configuration file and asks you to restart the chat.

Great for

  • Engineers building dashboards or alerts who need the exact metric names for a Google Cloud service
  • SRE or operations staff exploring what telemetry is available for a resource
  • Developers writing monitoring-as-code who want to confirm metric type strings before using them

Skip it if

  • Projects where you cannot share a real Google Cloud project ID with the agent, since the skill requires one before querying
  • Environments where you do not want the agent editing MCP configuration files, because the skill may modify files such as claude_desktop_config.json to add a server
  • Questions about interpreting metric values or setting up alerting policies, which this skill does not cover

Try asking

  • “Find the Cloud Run metrics related to request latency in project my-project-123”
  • “What Compute Engine metrics track CPU and memory utilization?”
  • “List BigQuery metrics about bytes scanned and query count for my analytics project”
  • “Which Cloud SQL metrics show connection counts?”
Step-by-step guide: how to use Cloud Monitoring Metric FinderInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 2 original files, the Apache-2.0 licence and an attribution note.

    cloud-monitoring-metric-selection.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip cloud-monitoring-metric-selection.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip cloud-monitoring-metric-selection.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Give the agent your real Google Cloud project ID up front; it will refuse to query placeholder names like my-project-id.
  • Name the specific metric you care about (for example memory or latency) so the keyword filter returns a shorter, more useful list.
  • Expect a restart of your chat session if the agent has to add the MCP server to your configuration the first time.

What's inside

  • references/attribution.md
  • SKILL.md

Redistributed unmodified from google/skills under the Apache-2.0 licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.