cloud-monitoring — Claude Code skill: what it does, how to install
Interacts with Google Cloud Monitoring through MCP, rendering ASCII sparklines and concise CSV summaries to prevent context bloat.
Apache-2.0 ★ 151 updated 2026-10-12
/plugin marketplace add gemini-cli-extensions/sre
/plugin install sre-extension@sreWhat cloud-monitoring does
The skill connects AI agents to Google Cloud Monitoring endpoints using MCP server tools like mcp_google-monitoring_query_range, alert checkers, and dashboard fetchers. Standard monitoring responses return massive JSON payloads. To protect agent memory limits, the skill guides the model to route queries through sub-agents and condense time-series points into compact formats.
It bundles scripts/export_timeseries_to_csv.py, which pulls historical numbers into a structured CSV file containing execution timestamps, summary statistics (AVG, Min, Max), and visual ASCII art sparklines. The helper script handles correlated metric pairs, such as network ingress versus egress, Cloud Run hit volume against response latencies, and GKE container memory alongside CPU core usage. It also includes scripts/setup-frontend-slo.sh to configure a 99.9% availability SLO based on application logs.
The skill strictly requires an operational google-monitoring MCP server instance. The assistant cannot query any telemetry if those external tools are missing.
What it helps with
- fetch Google Cloud Monitoring telemetry without exhausting agent context budgets
- compare correlated metric pairs like container CPU usage and memory consumption in GKE
- export time-series records to CSV complete with ASCII sparkline visualisations
- deploy a 99.9% availability SLO configuration for web frontends via bash script
Example prompts for the agent
- Pull Cloud Run request volume and response latencies for the last hour using export_timeseries_to_csv.py
- Show me the current alert policies registered in Google Cloud Monitoring
- Generate an ASCII sparkline comparing container memory and CPU usage on GKE
How to install cloud-monitoring
1Plugin marketplace
/plugin marketplace add gemini-cli-extensions/sre/plugin install sre-extension@sreThis installs the whole sre-extension plugin with all its skills
2Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill cloud-monitoring -a claude-code3Manually: put the files in place
~/.claude/skills/cloud-monitoring/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/cloud-monitoring/
1Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill cloud-monitoring -a codex2Manually: put the files in place
.agents/skills/cloud-monitoring/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill cloud-monitoring -a cursor2Manually: put the files in place
.cursor/skills/cloud-monitoring/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install gemini-cli-extensions/sre skills/cloud-monitoring2Manually: put the files in place
.github/skills/cloud-monitoring/SKILL.md1Skills CLI (Vercel)
npx skills add gemini-cli-extensions/sre --skill cloud-monitoring -a gemini-cli2Platform CLI
gemini skills install https://github.com/gemini-cli-extensions/sre --path skills/cloud-monitoringManually: put the files in place
.devin/skills/cloud-monitoring/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about cloud-monitoring
How to install cloud-monitoring in Claude Code?
Run npx skills add gemini-cli-extensions/sre --skill cloud-monitoring -a claude-code. Alternatively, add it via the marketplace with /plugin marketplace add gemini-cli-extensions/sre followed by /plugin install sre-extension@sre.
What prerequisite must be met before using this skill?
The google-monitoring MCP server must be installed and active in your client. If MCP tools like mcp_google-monitoring_query_range are unavailable, the skill halts and asks you to enable them.
How does the skill handle large monitoring datasets?
Instead of loading raw API JSON into prompt context, it converts time-series points into CSV with header stats and compact text sparklines to preserve memory.
Source text
SKILL.md · Apache-2.0
---
name: cloud-monitoring
description: 🐉 Skill for interacting with Google Cloud Monitoring (CM) via APIs to avoid large context bloat. Produces nice short synoptic "gists" of graphs
metadata:
author: Riccardo Carlesso
version: 0.2.17
tools:
- mcp_google-monitoring_get_alert
- mcp_google-monitoring_get_alert_policy
- mcp_google-monitoring_get_dashboard
- mcp_google-monitoring_list_alert_policies
- mcp_google-monitoring_list_alerts
- mcp_google-monitoring_list_dashboards
- mcp_google-monitoring_list_metric_descriptors
- mcp_google-monitoring_list_timeseries
- mcp_google-monitoring_query_range
---
# Cloud Monitoring
> **⚠️ PREREQUISITE: `google-monitoring` MCP Server**
> This skill relies on the `google-monitoring` MCP server being installed and active. Before proceeding with monitoring tasks, assert that the required MCP tools (e.g., `mcp_google-monitoring_query_range`) are available. If they are missing, immediately inform the user and recommend they enable the MCP server (they can use the `gcp-mcp-setup` skill if available).
This skill provides utilities for analyzing and extracting data from Google Cloud Monitoring (CM).
## Best Practices
* **Avoid Context Bloat:** Cloud Monitoring API responses can be massive. Do not try to read raw JSON responses directly into the LLM context. Try to delegate to a SubAgent anything which pulls monitoring data as they tend to bloat the context.
* **Use Export Scripts:** If you pull monitoring data, make sure to surface this final data (in CSV format) using the `scripts/export_timeseries_to_csv.py` Python script to surface important stats like AVG, Max, Min and a simplified text-graph of the system (see `references/sample_output_dual_metrics.csv`) . Also report back that stats header to the main agent, together with any interesting insights you might have found.
* **Metadata Headers:** Exported data should contain metadata (time ranges, metric names) at the top of the file so that the context of "when" the data was pulled is never lost, as `now()` changes over time.
* **Target Workloads:** Focus your monitoring extractions primarily on GKE and Cloud Run environments. Generic time-series extractions should still allow filtering by specific resources.
* **Paired Metrics Comparison:** The extraction script supports querying multiple metrics simultaneously. For apples-to-apples comparisons, try these recommended pairs:
* **Network I/O:** `compute.googleapis.com/instance/network/received_bytes_count` vs `compute.googleapis.com/instance/network/sent_bytes_count`
* **Disk I/O:** `compute.googleapis.com/instance/disk/read_bytes_count` vs `compute.googleapis.com/instance/disk/write_bytes_count`
* **Cloud Run Traffic:** `run.googleapis.com/request_count` vs `run.googleapis.com/response_latencies`
* **GKE Memory vs CPU:** `kubernetes.io/container/memory/used_bytes` vs `kubernetes.io/container/cpu/core_usage_time`
## Available Tools
* `scripts/export_timeseries_to_csv.py`: Fetches time-series data for specified metric(s) and time range, outputting a CSV file with metadata headers. Supports extracting two or more variables for direct correlation and comparison. This is an amazing synoptic you can surface to the user
* It's very effective particularly to share the "**Sparkline**" / **ASCII Art** part showing in TEXT the graphical shape of the curve (e.g., `|█▇▆▇ ▂▃ ▂ ▂|`). This is very useful for humans for rapid visual feedback! Use `csv_to_sparkline.py` from `monitoring-graphs` to recreate it for arbitrary CSVs.
* `scripts/setup-frontend-slo.sh`: A bash script to automatically set up a 99.9% availability SLO using Log-based Metrics for a 'frontend' service. (See `scripts/README.md` for full manual).
© Riccardo Carlesso · Apache-2.0 · gemini-cli-extensions/sre