google-agents-cli-scaffold
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
infrastructure-monitoring
Set up comprehensive infrastructure monitoring with Prometheus, Grafana, and alerting systems for metrics, health checks, and performance tracking.
Full skill instructions
Implement comprehensive infrastructure monitoring to track system health, performance metrics, and resource utilization with alerting and visualization across your entire stack.
# prometheus.yml
global:
scrape_interval: 15s
evaluation_interval: 15s
external_labels:
monitor: 'infrastructure-monitor'
environment: 'production'
# Alertmanager configuration
alerting:
alertmanagers:
- static_configs:
- targets:
- localhost:9093
# Rule files
rule_files:
- 'alerts.yml'
- 'rules.yml'
scrape_configs:
# Prometheus itself
- job_name: 'prometheus'
static_configs:
- targets: ['localhost:9090']
# Node Exporter for system metrics
- job_name: 'node'
static_configs:
- targets:
- 'node1.internal:9100'
- 'node2.internal:9100'
- 'node3.internal:9100'
relabel_configs:
- source_labels: [__address__]
target_label: instance
# Docker container metrics
- job_name: 'docker'
static_configs:
- targets: ['localhost:9323']
metrics_path: '/metrics'
# Kubernetes metrics
- job_name: 'kubernetes-apiservers'
kubernetes_sd_configs:
- role: endpoints
scheme: https
tls_config:
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
relabel_configs:
- source_labels: [__meta_kubernetes_namespace, __meta_kubernetes_service_name, __meta_kubernetes_endpoint_port_name]
action: keep
regex: default;kubernetes;https
# Application metrics
- job_name: 'application'
metrics_path: '/metrics'
static_configs:
- targets:
- 'app1.internal:8080'
- 'app2.internal:8080'
- 'app3.internal:8080'
scrape_interval: 10s
scrape_timeout: 5s
# PostgreSQL metrics
- job_name: 'postgres'
static_configs:
- targets: ['postgres-exporter.internal:9187']
# Redis metrics
- job_name: 'redis'
static_configs:
- targets: ['redis-exporter.internal:9121']
# RabbitMQ metrics
- job_name: 'rabbitmq'
static_configs:
- targets: ['rabbitmq.internal:15692']
# alerts.yml
groups:
- name: application_alerts
interval: 30s
rules:
- alert: HighErrorRate
expr: rate(http_requests_total{status=~"5.."}[5m]) > 0.05
for: 5m
labels:
severity: critical
annotations:
summary: "High error rate detected"
description: "Error rate is {{ $value | humanizePercentage }}"
- alert: HighLatency
expr: histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m])) > 1
for: 10m
labels:
severity: warning
annotations:
summary: "High request latency"
description: "P95 latency is {{ $value }}s"
- alert: ServiceDown
expr: up{job="application"} == 0
for: 1m
labels:
severity: critical
annotations:
summary: "Service {{ $labels.instance }} is down"
description: "Service has been unreachable for 1 minute"
- name: infrastructure_alerts
interval: 30s
rules:
- alert: HighCPUUsage
expr: (100 - (avg by (instance) (rate(node_cpu_seconds_total{mode="idle"}[5m])) * 100)) > 80
for: 5m
labels:
severity: warning
annotations:
summary: "High CPU usage on {{ $labels.instance }}"
description: "CPU usage is {{ $value }}%"
- alert: HighMemoryUsage
expr: (1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100 > 85
for: 5m
labels:
severity: warning
annotations:
summary: "High memory usage on {{ $labels.instance }}"
description: "Memory usage is {{ $value }}%"
- alert: LowDiskSpace
expr: (node_filesystem_avail_bytes{fstype!~"tmpfs|fuse.lxcfs|squashfs|vfat"} / node_filesystem_size_bytes) * 100 < 10
for: 5m
labels:
severity: critical
annotations:
summary: "Low disk space on {{ $labels.instance }}"
description: "Available disk space is {{ $value }}%"
- alert: NodeNotReady
expr: kube_node_status_condition{condition="Ready",status="true"} == 0
for: 5m
labels:
severity: critical
annotations:
summary: "Kubernetes node {{ $labels.node }} is not ready"
description: "Node has been unready for 5 minutes"
- alert: PodCrashLooping
expr: rate(kube_pod_container_status_restarts_total[15m]) > 0.1
for: 5m
labels:
severity: warning
annotations:
summary: "Pod {{ $labels.pod }} is crash looping"
description: "Pod has restarted {{ $value }} times in 15 minutes"
# alertmanager.yml
global:
resolve_timeout: 5m
slack_api_url: 'YOUR_SLACK_WEBHOOK_URL'
# Template files
templates:
- '/etc/alertmanager/templates/*.tmpl'
# Routing tree
route:
receiver: 'default'
group_by: ['alertname', 'cluster', 'service']
group_wait: 30s
group_interval: 5m
repeat_interval: 4h
routes:
# Critical alerts
- match:
severity: critical
receiver: 'critical-team'
continue: true
group_wait: 10s
repeat_interval: 1h
# Warning alerts
- match:
severity: warning
receiver: 'warning-channel'
group_wait: 1m
# Receivers
receivers:
- name: 'default'
slack_configs:
- channel: '#alerts'
title: 'Alert: {{ .GroupLabels.alertname }}'
text: '{{ range .Alerts }}{{ .Annotations.description }}{{ end }}'
- name: 'critical-team'
slack_configs:
- channel: '#critical-alerts'
title: 'CRITICAL: {{ .GroupLabels.alertname }}'
email_configs:
- to: '[email protected]'
from: '[email protected]'
smarthost: 'smtp.mycompany.com:587'
auth_username: '[email protected]'
auth_password: 'secret'
- name: 'warning-channel'
slack_configs:
- channel: '#warnings'
title: 'Warning: {{ .GroupLabels.alertname }}'
{
"dashboard": {
"title": "Infrastructure Overview",
"panels": [
{
"title": "CPU Usage",
"targets": [
{
"expr": "100 - (avg(rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)"
}
],
"type": "graph",
"alert": {
"name": "CPU Usage Alert",
"conditions": [
{
"evaluator": {
"type": "gt",
"params": [80]
}
}
]
}
},
{
"title": "Memory Usage",
"targets": [
{
"expr": "(1 - (node_memory_MemAvailable_bytes / node_memory_MemTotal_bytes)) * 100"
}
],
"type": "graph"
},
{
"title": "Request Rate",
"targets": [
{
"expr": "rate(http_requests_total[5m])"
}
],
"type": "graph"
},
{
"title": "Error Rate",
"targets": [
{
"expr": "rate(http_requests_total{status=~\"5..\"}[5m])"
}
],
"type": "graph"
},
{
"title": "Response Time P95",
"targets": [
{
"expr": "histogram_quantile(0.95, rate(http_request_duration_seconds_bucket[5m]))"
}
],
"type": "graph"
},
{
"title": "Disk Usage",
"targets": [
{
"expr": "(1 - (node_filesystem_avail_bytes / node_filesystem_size_bytes)) * 100"
}
],
"type": "graph"
}
]
}
}
#!/bin/bash
# deploy-monitoring.sh - Deploy Prometheus and Grafana
set -euo pipefail
NAMESPACE="monitoring"
PROMETHEUS_VERSION="v2.40.0"
GRAFANA_VERSION="9.3.2"
echo "Creating monitoring namespace..."
kubectl create namespace "$NAMESPACE" --dry-run=client -o yaml | kubectl apply -f -
# Deploy Prometheus
echo "Deploying Prometheus..."
kubectl apply -f prometheus-configmap.yaml -n "$NAMESPACE"
kubectl apply -f prometheus-deployment.yaml -n "$NAMESPACE"
kubectl apply -f prometheus-service.yaml -n "$NAMESPACE"
# Deploy Alertmanager
echo "Deploying Alertmanager..."
kubectl apply -f alertmanager-configmap.yaml -n "$NAMESPACE"
kubectl apply -f alertmanager-deployment.yaml -n "$NAMESPACE"
kubectl apply -f alertmanager-service.yaml -n "$NAMESPACE"
# Deploy Grafana
echo "Deploying Grafana..."
kubectl apply -f grafana-deployment.yaml -n "$NAMESPACE"
kubectl apply -f grafana-service.yaml -n "$NAMESPACE"
# Wait for deployments
echo "Waiting for deployments to be ready..."
kubectl rollout status deployment/prometheus -n "$NAMESPACE" --timeout=5m
kubectl rollout status deployment/alertmanager -n "$NAMESPACE" --timeout=5m
kubectl rollout status deployment/grafana -n "$NAMESPACE" --timeout=5m
# Port forward for access
echo "Port forwarding to services..."
kubectl port-forward -n "$NAMESPACE" svc/prometheus 9090:9090 &
kubectl port-forward -n "$NAMESPACE" svc/grafana 3000:3000 &
echo "Monitoring stack deployed successfully!"
echo "Prometheus: http://localhost:9090"
echo "Grafana: http://localhost:3000"
Project scaffolding, deployment configuration, and CI/CD setup for Google ADK agents.
Set up tracing, logging, and monitoring for deployed ADK agents across Cloud Trace, BigQuery, and third-party platforms.
Enterprise Azure infrastructure architect generating Bicep or Terraform from workload descriptions.
Plan and configure production-ready Azure Kubernetes Service clusters with Day-0 and Day-1 best practices.
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Web search, scraping, extraction, crawling, and monitoring via ScrapeGraph AI CLI.
Skill for working with Firebase Hosting (Classic). Use this when you want to deploy static web apps, Single Page Apps (SPAs), or simple microservices. Do NOT use for Firebase App Hosting.
Deploy and manage web apps with Firebase App Hosting. Use this skill when deploying Next.js/Angular apps with backends.
Deploy applications and websites to Vercel. Use when the user requests deployment actions like "deploy my app", "deploy and give me the link", "push this live", or "create a preview deployment".
Build SEO-optimized pages at scale using templates, data, and proven playbook patterns.
Design and build isolated, reusable Convex backend components with clear boundaries and app-facing wrappers.
Deploy and manage projects on Vercel using token-based authentication. Use when working with Vercel CLI using access tokens rather than interactive login — e.g. "deploy to vercel", "set up vercel", "add environment variables to vercel".
Opus.ai: Revolutionize Your Web Experience
Build a no-code AI app in minutes.
An IDE for code migration from legacy to modern frameworks through coding agents.
Automate CGI animation in live-action scenes
Branded artistic QR-code concepts
Launch a website in seconds with AI.
Streamline Your Coding Experience with AI Code Helper
Convert any screenshot or design to clean code.