Skip to content
Skill

Cloud monitoring metric selection

Finds relevant Google Cloud Monitoring metric descriptors for a service or resource

Install
Scripts
None
Platforms
Claude Code, Codex, Cursor
GitHub stars
24.4K
Last commit
2 days ago
License
Apache-2.0
Listing updated
1 day ago

Similar skills

About Cloud monitoring metric selection

Cloud monitoring metric selection is an open-source agent skill for databases. It is available on Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose.

This skill helps an agent locate the Cloud Monitoring metric types that matter for a given Google Cloud service, such as Compute Engine, Spanner, BigQuery or Cloud Run. It pulls the live descriptor list through the Cloud Monitoring MCP tool, paging through results per service prefix, then narrows them with keyword matching on type, display name and description.

The workflow checks that the MCP tool is available and points to the Cloud Monitoring endpoint, and it requires a real project ID before any API query runs. For each service it builds a metric prefix filter (including Ops Agent, GKE, Istio, Knative and custom metric namespaces) and returns a short set of key metrics as Markdown tables with kind, value type, unit and monitored resource columns. If API calls fail, the skill falls back to public documentation and must state the error and the risk of non-live data.

It expects a Google Cloud project with the Cloud Monitoring MCP server configured, and it can add that server entry to an existing MCP config file when it is missing.

When your agent uses it

Retrieve, query, and identify relevant Cloud Monitoring metric descriptors on Google Cloud for a service or resource (such as Compute Engine, Spanner, BigQuery, Cloud Run, Cloud SQL, Pub/Sub, Cloud Storage, etc.). Use when asked to find, list, search, or discover GCP metric types, names, kind/value schemas, or descriptors.

From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.

What it can access

From a static check of its 2 files (12 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.

Check another skill before you install it.

Install

Copy the skill folder to ~/.claude/skills/cloud-monitoring-metric-selection to use it in all your projects:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/cloud-monitoring-metric-selection &&
cp -R "$tmp/skills/cloud/cloud-monitoring-metric-selection" ~/.claude/skills/cloud-monitoring-metric-selection &&
rm -rf "$tmp"

For one project only, put the folder in .claude/skills/cloud-monitoring-metric-selection inside it instead.

Claude Code docs on skills

Copy the skill folder to ~/.agents/skills/cloud-monitoring-metric-selection to use it in every repository:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/cloud-monitoring-metric-selection &&
cp -R "$tmp/skills/cloud/cloud-monitoring-metric-selection" ~/.agents/skills/cloud-monitoring-metric-selection &&
rm -rf "$tmp"

For one repository only, put the folder in .agents/skills/cloud-monitoring-metric-selection inside it instead.

Codex docs on skills

Copy the skill folder to ~/.cursor/skills/cloud-monitoring-metric-selection to use it in every project:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/cloud-monitoring-metric-selection &&
cp -R "$tmp/skills/cloud/cloud-monitoring-metric-selection" ~/.cursor/skills/cloud-monitoring-metric-selection &&
rm -rf "$tmp"

For one project only, put the folder in .cursor/skills/cloud-monitoring-metric-selection inside it instead.

Cursor docs on skills

Run in a terminal (add --scope workspace to install it for the current workspace only):

gemini skills install https://github.com/google/skills.git --path skills/cloud/cloud-monitoring-metric-selection

Or copy the folder to ~/.gemini/skills/cloud-monitoring-metric-selection yourself.

Gemini CLI docs on skills

For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/cloud-monitoring-metric-selection:

tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/google/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/cloud-monitoring-metric-selection &&
cp -R "$tmp/skills/cloud/cloud-monitoring-metric-selection" ~/.copilot/skills/cloud-monitoring-metric-selection &&
rm -rf "$tmp"

For one project only, put the folder in .github/skills/cloud-monitoring-metric-selection inside it instead.

VS Code docs on skills

Get the folder:

git clone --depth 1 https://github.com/google/skills.git

Then copy skills/skills/cloud/cloud-monitoring-metric-selection into your agent's skills folder as cloud-monitoring-metric-selection. Agents that support SKILL.md read one folder per skill.

The SKILL.md format

What it does

Live descriptor retrieval
Queries current Cloud Monitoring metric descriptors through the MCP tool rather than relying on cached lists.
Service prefix filtering
Builds per-service metric prefix filters and pages through all results for each service.
Keyword narrowing
Matches user terms like CPU or latency against metric type, display name and description.
Project ID safeguard
Refuses to run queries until a real project ID is confirmed, avoiding placeholder names.
Structured metric tables
Presents selected metrics grouped by service with kind, value type, unit and resource columns.
Documented fallback path
Uses public docs when API calls fail and reports the error and staleness risk.

Good for

  • Find which Spanner metrics track instance CPU utilization
  • List BigQuery metrics for bytes scanned and query latency
  • Discover Cloud Run request count and latency metric types
  • Look up Pub/Sub metric names for backlog and throughput monitoring
  • Identify Cloud SQL metrics for connections and disk usage

Cloud monitoring metric selection FAQ

What does the skill need to run?

It needs a Google Cloud project ID and the Cloud Monitoring MCP server at the monitoring.googleapis.com/mcp endpoint. If the tool is missing, the skill adds the server to the MCP config and asks you to restart the session.

Does it change my Google Cloud resources?

The skill only lists metric descriptors through the list_metric_descriptors tool. Its instructions do not describe creating or modifying cloud resources.

Will it query a placeholder project?

No. The skill instructs the agent to stop and ask for a confirmed project ID before calling any API, and it names placeholder values such as my-project-id to avoid.

What happens if the API call fails?

The skill retries with a smaller page size for timeouts, corrects filter syntax errors, and as a last resort checks whether the service is enabled and consults public documentation, reporting the error and the risk of stale data.

How do I install Cloud monitoring metric selection in Claude Code?

Copy the skill folder from GitHub to ~/.claude/skills/cloud-monitoring-metric-selection to use it in all your projects, or to .claude/skills/cloud-monitoring-metric-selection in one project.

Does Cloud monitoring metric selection run scripts?

No. It is instructions only, with no scripts. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.

Which AI agents can use Cloud monitoring metric selection?

Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.

What are the best alternatives to Cloud monitoring metric selection?

The closest alternatives to Cloud monitoring metric selection are Cloud monitoring promql query, Finding google skills, Cloud monitoring list time series request, Bigquery observability and Cloud monitoring alert configuration.

Where this comes from

  • Description: from the skill's own SKILL.md.

More from google/skills

  1. Route platform choices to Google's own skills by fetching and filtering its skill catalog

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  2. Guardrails for gcloud commands: validate syntax with help, scope projects, dry-run first

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  3. Authenticate to Google Cloud: ADC, impersonation, service accounts and IAM roles

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  4. First-time Google Cloud setup: sign in, pick a project, link billing, with consent gates

    • Open source
    • 24.4K GitHub stars
    • Cloud and infrastructure
  5. Look up Google developer docs through the Developer Knowledge MCP server or REST fallback

    • Open source
    • 24.4K GitHub stars
    • Developer tools