[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6CXQ469EAD5692B8B5QDDAV":3,"skill-same:01M6CXQ469EAD5692B8B5QDDAV":55},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":26,"linkOnly":27,"markdownContent":28,"markdownBody":29,"frontMatter":30,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":40,"install":41,"resources":54},"01M6CXQ469EAD5692B8B5QDDAV","monitoring",null,"System monitoring and observability implementation using Prometheus, Grafana, and related tools","ffsshhttiikk\u002Fopencode-agents-skills","ffsshhttiikk","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F226346827?v=4","01M6CWD9RR3Y7VRQX3MXYC8FYH","01M6CWD9WVPYAZW0J82G1VKGHY",3,"MIT","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fsystems-administration\u002Fmonitoring\u002FSKILL.md",[],[5,18,19,20,21,22,23,24,25],"observability","prometheus","grafana","Tools","system","devops","opencode","implementation","2026-11-10 10:12:30",false,"---\nname: monitoring\ndescription: System monitoring and observability implementation using Prometheus, Grafana, and related tools\nlicense: MIT\ncompatibility: opencode\nmetadata:\n  audience: devops-engineers\n  category: systems-administration\n---\n\n## What I do\n- Configure Prometheus metrics collection\n- Create Grafana dashboards\n- Set up alerting rules and notifications\n- Monitor application and infrastructure metrics\n- Implement distributed tracing\n- Configure log aggregation\n- Design observability strategies\n- Create SLOs and SLIs\n- Analyze performance bottlenecks\n- Debug production issues using metrics\n\n## When to use me\nWhen setting up monitoring systems, creating dashboards, configuring alerts, or troubleshooting performance issues.\n\n## Core Concepts\n- Prometheus metrics types (counter, gauge, histogram, summary)\n- Service discovery and scraping configurations\n- PromQL query language\n- Grafana visualization and alerting\n- Alertmanager routing and silencing\n- Kubernetes metrics (kube-state-metrics, node-exporter)\n- Application performance monitoring (APM)\n- Distributed tracing (Jaeger, Zipkin)\n- Log aggregation (ELK, Loki)\n- SLO\u002FSLI\u002FError budget design\n\n## Code Examples\n\n### Prometheus Configuration\n```yaml\n# prometheus.yml\nglobal:\n  scrape_interval: 15s\n  evaluation_interval: 15s\n  external_labels:\n    cluster: 'prod-us-east-1'\n    env: 'production'\n\nalerting:\n  alertmanagers:\n    - static_configs:\n        - targets:\n            - alertmanager:9093\n      timeout: 10s\n      api_version: v2\n\nrule_files:\n  - \u002Fetc\u002Fprometheus\u002Frules\u002F*.yml\n\nscrape_configs:\n  # Prometheus self-monitoring\n  - job_name: 'prometheus'\n    static_configs:\n      - targets: ['localhost:9090']\n\n  # Node Exporter for hardware\u002FOS metrics\n  - job_name: 'node'\n    static_configs:\n      - targets: ['node-exporter:9100']\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: instance\n        regex: '(.+):\\\\d+'\n        replacement: '${1}'\n\n  # Kubernetes service discovery\n  - job_name: 'kubernetes-service-endpoints'\n    kubernetes_sd_configs:\n      - role: endpoints\n    relabel_configs:\n      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]\n        action: keep\n        regex: true\n      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]\n        action: replace\n        target_label: __metrics_path__\n        regex: (.+)\n      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]\n        action: replace\n        target_label: __address__\n        regex: ([^:]+)(?::\\\\d+)?;(\\\\d+)\n        replacement: ${1}:${2}\n\n  # Kubernetes pods\n  - job_name: 'kubernetes-pods'\n    kubernetes_sd_configs:\n      - role: pod\n    relabel_configs:\n      - action: keep\n        source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]\n```\n\n```yaml\n# prometheus-rules.yml\ngroups:\n  - name: default-alerts\n    rules:\n      # High CPU usage\n      - alert: HighCPUUsage\n        expr: |\n          sum(rate(container_cpu_usage_seconds_total{namespace!=\"kube-system\"}[5m]))\n          \u002F\n          sum(machine_cpu_cores) > 0.85\n        for: 5m\n        labels:\n          severity: warning\n        annotations:\n          summary: \"High CPU usage on {{ $labels.node }}\"\n          description: \"CPU usage is above 85% for more than 5 minutes\"\n      \n      # High memory usage\n      - alert: HighMemoryUsage\n        expr: |\n          (1 - (node_memory_MemAvailable_bytes \u002F node_memory_MemTotal_bytes)) > 0.90\n        for: 5m\n        labels:\n          severity: warning\n        annotations:\n          summary: \"High memory usage on {{ $labels.instance }}\"\n          description: \"Memory usage is above 90% for more than 5 minutes\"\n      \n      # Disk space low\n      - alert: LowDiskSpace\n        expr: |\n          (1 - (node_filesystem_avail_bytes{mountpoint=\"\u002F\"} \u002F node_filesystem_size_bytes{mountpoint=\"\u002F\"})) > 0.85\n        for: 10m\n        labels:\n          severity: warning\n        annotations:\n          summary: \"Low disk space on {{ $labels.instance }}\"\n          description: \"Disk usage is above 85% on {{ $labels.mountpoint }}\"\n      \n      # Pod not ready\n      - alert: PodNotReady\n        expr: |\n          kube_pod_status_ready{namespace!=\"kube-system\",condition=\"true\"} == 0\n        for: 3m\n        labels:\n          severity: warning\n        annotations:\n          summary: \"Pod {{ $labels.namespace }}\u002F{{ $labels.pod }} not ready\"\n          description: \"Pod has been not ready for more than 3 minutes\"\n      \n      # Pod crashing\n      - alert: PodCrashing\n        expr: |\n          increase(kube_pod_container_status_restarts_total[1h]) > 3\n        labels:\n          severity: critical\n        annotations:\n          summary: \"Pod {{ $labels.namespace }}\u002F{{ $labels.pod }} is crashing\"\n          description: \"Container restarted more than 3 times in the last hour\"\n      \n      # High error rate\n      - alert: HighErrorRate\n        expr: |\n          sum(rate(http_requests_total{status=~\"5..\"}[5m])) \n          \u002F \n          sum(rate(http_requests_total[5m])) > 0.05\n        for: 5m\n        labels:\n          severity: critical\n        annotations:\n          summary: \"High HTTP error rate\"\n          description: \"More than 5% of requests are returning 5xx errors\"\n\n  - name: sli-metrics\n    rules:\n      # Availability SLI (99.9%)\n      - record: service:http_requests:ratio5m\n        expr: |\n          sum(rate(http_requests_total{handler!~\"\u002Fhealth|\u002Fmetrics\"}[5m])) \n          \u002F \n          sum(rate(http_requests_total{handler!~\"\u002Fhealth|\u002Fmetrics\"}[5m]))\n      \n      # Latency SLI (p99 \u003C 500ms)\n      - record: service:http_request_duration_seconds:p99\n        expr: |\n          histogram_quantile(0.99, \n            sum(rate(http_request_duration_seconds_bucket{handler!~\"\u002Fhealth|\u002Fmetrics\"}[5m])) by (le))\n```\n\n### AlertManager Configuration\n```yaml\n# alertmanager.yml\nglobal:\n  resolve_timeout: 5m\n  smtp_smarthost: 'smtp.example.com:587'\n  smtp_from: 'alertmanager@example.com'\n  smtp_auth_username: 'alertmanager'\n  smtp_auth_password: '${SMTP_PASSWORD}'\n\nroute:\n  group_by: ['alertname', 'severity']\n  group_wait: 30s\n  group_interval: 5m\n  repeat_interval: 4h\n  receiver: 'default'\n  routes:\n    - match:\n        severity: critical\n      receiver: 'critical-pager'\n      continue: true\n    - match:\n        severity: warning\n      receiver: 'warning-slack'\n      continue: true\n    - match_re:\n        alertname: '.*Info'\n      receiver: 'informational'\n      group_interval: 15m\n\nreceivers:\n  - name: 'default'\n    email_configs:\n      - to: 'team@example.com'\n        send_resolved: true\n        html: |\n          {{ define \"email.default.html\" }}\n          \u003C!DOCTYPE html>\n          \u003Chtml>\n          \u003Cbody>\n            \u003Ch2>{{ .Status }} - {{ .GroupLabels.alertname }}\u003C\u002Fh2>\n            {{ range .Alerts }}\n              \u003Cp>\u003Cstrong>{{ .Labels.severity | upper }}\u003C\u002Fstrong>\u003C\u002Fp>\n              \u003Cp>{{ .Annotations.summary }}\u003C\u002Fp>\n              \u003Cpre>{{ .Annotations.description }}\u003C\u002Fpre>\n            {{ end }}\n          \u003C\u002Fbody>\n          \u003C\u002Fhtml>\n          {{ end }}\n          {{ template \"email.default.html\" . }}\n    \n  - name: 'critical-pager'\n    pagerduty_configs:\n      - service_key: '${PAGERDUTY_SERVICE_KEY}'\n        severity: critical\n    \n  - name: 'warning-slack'\n    slack_configs:\n      - channel: '#alerts-warning'\n        api_url: '${SLACK_WEBHOOK_URL}'\n        title: '{{ range .Alerts }}{{ .Labels.alertname }} {{ end }}'\n        text: '{{ range .Alerts }}{{ .Annotations.summary }} {{ end }}'\n        severity: '{{ .Labels.severity }}'\n        color: '{{ if eq .Labels.severity \"critical\" }}danger{{ else }}warning{{ end }}'\n\ninhibit_rules:\n  - source_match:\n      severity: 'critical'\n    target_match:\n      severity: 'warning'\n    equal: ['alertname', 'instance']\n```\n\n### Grafana Dashboard\n```json\n{\n  \"dashboard\": {\n    \"title\": \"Application Overview\",\n    \"uid\": \"app-overview\",\n    \"tags\": [\"application\", \"overview\"],\n    \"timezone\": \"browser\",\n    \"refresh\": \"30s\",\n    \"panels\": [\n      {\n        \"title\": \"Request Rate\",\n        \"type\": \"graph\",\n        \"gridPos\": {\"x\": 0, \"y\": 0, \"w\": 12, \"h\": 8},\n        \"targets\": [\n          {\n            \"expr\": \"sum(rate(http_requests_total[5m])) by (method, status)\",\n            \"legendFormat\": \"{{method}} {{status}}\"\n          }\n        ]\n      },\n      {\n        \"title\": \"Error Rate\",\n        \"type\": \"stat\",\n        \"gridPos\": {\"x\": 12, \"y\": 0, \"w\": 12, \"h\": 4},\n        \"targets\": [\n          {\n            \"expr\": \"sum(rate(http_requests_total{status=~\\\"5..\\\"}[5m])) \u002F sum(rate(http_requests_total[5m])) * 100\",\n            \"legendFormat\": \"Error Rate %\"\n          }\n        ],\n        \"fieldConfig\": {\n          \"defaults\": {\n            \"unit\": \"percent\",\n            \"thresholds\": {\n              \"mode\": \"absolute\",\n              \"steps\": [\n                {\"color\": \"green\", \"value\": null},\n                {\"color\": \"yellow\", \"value\": 1},\n                {\"color\": \"red\", \"value\": 5}\n              ]\n            }\n          }\n        }\n      },\n      {\n        \"title\": \"P99 Latency\",\n        \"type\": \"graph\",\n        \"gridPos\": {\"x\": 0, \"y\": 8, \"w\": 12, \"h\": 8},\n        \"targets\": [\n          {\n            \"expr\": \"histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))\",\n            \"legendFormat\": \"p99\"\n          },\n          {\n            \"expr\": \"histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))\",\n            \"legendFormat\": \"p95\"\n          }\n        ]\n      },\n      {\n        \"title\": \"Active Pods\",\n        \"type\": \"timeseries\",\n        \"gridPos\": {\"x\": 12, \"y\": 8, \"w\": 12, \"h\": 8},\n        \"targets\": [\n          {\n            \"expr\": \"count(kube_pod_container_status_ready{namespace=\\\"$namespace\\\"})\",\n            \"legendFormat\": \"Ready\"\n          },\n          {\n            \"expr\": \"count(kube_pod_container_status_ready{namespace=\\\"$namespace\\\"} == 0)\",\n            \"legendFormat\": \"Not Ready\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n## Best Practices\n- Use histograms for values with many distinct values (latency, sizes)\n- Set appropriate recording rules for complex queries\n- Implement labels consistently across metrics\n- Use appropriate alert thresholds based on SLOs\n- Avoid alert fatigue with proper grouping and routing\n- Use service discovery instead of static configurations\n- Monitor not just infrastructure but business metrics too\n- Implement proper error budget policies\n- Use annotations for rich alert information\n- Test alerting rules before deploying to production\n","## What I do\n- Configure Prometheus metrics collection\n- Create Grafana dashboards\n- Set up alerting rules and notifications\n- Monitor application and infrastructure metrics\n- Implement distributed tracing\n- Configure log aggregation\n- Design observability strategies\n- Create SLOs and SLIs\n- Analyze performance bottlenecks\n- Debug production issues using metrics\n\n## When to use me\nWhen setting up monitoring systems, creating dashboards, configuring alerts, or troubleshooting performance issues.\n\n## Core Concepts\n- Prometheus metrics types (counter, gauge, histogram, summary)\n- Service discovery and scraping configurations\n- PromQL query language\n- Grafana visualization and alerting\n- Alertmanager routing and silencing\n- Kubernetes metrics (kube-state-metrics, node-exporter)\n- Application performance monitoring (APM)\n- Distributed tracing (Jaeger, Zipkin)\n- Log aggregation (ELK, Loki)\n- SLO\u002FSLI\u002FError budget design\n\n## Code Examples\n\n### Prometheus Configuration\n```yaml\n# prometheus.yml\nglobal:\n  scrape_interval: 15s\n  evaluation_interval: 15s\n  external_labels:\n    cluster: 'prod-us-east-1'\n    env: 'production'\n\nalerting:\n  alertmanagers:\n    - static_configs:\n        - targets:\n            - alertmanager:9093\n      timeout: 10s\n      api_version: v2\n\nrule_files:\n  - \u002Fetc\u002Fprometheus\u002Frules\u002F*.yml\n\nscrape_configs:\n  # Prometheus self-monitoring\n  - job_name: 'prometheus'\n    static_configs:\n      - targets: ['localhost:9090']\n\n  # Node Exporter for hardware\u002FOS metrics\n  - job_name: 'node'\n    static_configs:\n      - targets: ['node-exporter:9100']\n    relabel_configs:\n      - source_labels: [__address__]\n        target_label: instance\n        regex: '(.+):\\\\d+'\n        replacement: '${1}'\n\n  # Kubernetes service discovery\n  - job_name: 'kubernetes-service-endpoints'\n    kubernetes_sd_configs:\n      - role: endpoints\n    relabel_configs:\n      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]\n        action: keep\n        regex: true\n      - source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]\n        action: replace\n        target_label: __metrics_path__\n        regex: (.+)\n      - source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]\n        action: replace\n        target_label: __address__\n        regex: ([^:]+)(?::\\\\d+)?;(\\\\d+)\n        replacement: ${1}:${2}\n\n  # Kubernetes pods\n  - job_name: 'kubernetes-pods'\n    kubernetes_sd_configs:\n      - role: pod\n    relabel_configs:\n      - action: keep\n        source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]\n```\n\n```yaml\n# prometheus-rules.yml\ngroups:\n  - name: default-alerts\n    rules:\n      # High CPU usage\n      - alert: HighCPUUsage\n        expr: |\n          sum(rate(container_cpu_usage_seconds_total{namespace!=\"kube-system\"}[5m]))\n          \u002F\n          sum(machine_cpu_cores) > 0.85\n        for: 5m\n        labels:\n          severity: warning\n        annotations:\n          summary: \"High CPU usage on {{ $labels.node }}\"\n          description: \"CPU usage is above 85% for more than 5 minutes\"\n      \n      # High memory usage\n      - alert: HighMemoryUsage\n        expr: |\n          (1 - (node_memory_MemAvailable_bytes \u002F node_memory_MemTotal_bytes)) > 0.90\n        for: 5m\n        labels:\n          severity: warning\n        annotations:\n          summary: \"High memory usage on {{ $labels.instance }}\"\n          description: \"Memory usage is above 90% for more than 5 minutes\"\n      \n      # Disk space low\n      - alert: LowDiskSpace\n        expr: |\n          (1 - (node_filesystem_avail_bytes{mountpoint=\"\u002F\"} \u002F node_filesystem_size_bytes{mountpoint=\"\u002F\"})) > 0.85\n        for: 10m\n        labels:\n          severity: warning\n        annotations:\n          summary: \"Low disk space on {{ $labels.instance }}\"\n          description: \"Disk usage is above 85% on {{ $labels.mountpoint }}\"\n      \n      # Pod not ready\n      - alert: PodNotReady\n        expr: |\n          kube_pod_status_ready{namespace!=\"kube-system\",condition=\"true\"} == 0\n        for: 3m\n        labels:\n          severity: warning\n        annotations:\n          summary: \"Pod {{ $labels.namespace }}\u002F{{ $labels.pod }} not ready\"\n          description: \"Pod has been not ready for more than 3 minutes\"\n      \n      # Pod crashing\n      - alert: PodCrashing\n        expr: |\n          increase(kube_pod_container_status_restarts_total[1h]) > 3\n        labels:\n          severity: critical\n        annotations:\n          summary: \"Pod {{ $labels.namespace }}\u002F{{ $labels.pod }} is crashing\"\n          description: \"Container restarted more than 3 times in the last hour\"\n      \n      # High error rate\n      - alert: HighErrorRate\n        expr: |\n          sum(rate(http_requests_total{status=~\"5..\"}[5m])) \n          \u002F \n          sum(rate(http_requests_total[5m])) > 0.05\n        for: 5m\n        labels:\n          severity: critical\n        annotations:\n          summary: \"High HTTP error rate\"\n          description: \"More than 5% of requests are returning 5xx errors\"\n\n  - name: sli-metrics\n    rules:\n      # Availability SLI (99.9%)\n      - record: service:http_requests:ratio5m\n        expr: |\n          sum(rate(http_requests_total{handler!~\"\u002Fhealth|\u002Fmetrics\"}[5m])) \n          \u002F \n          sum(rate(http_requests_total{handler!~\"\u002Fhealth|\u002Fmetrics\"}[5m]))\n      \n      # Latency SLI (p99 \u003C 500ms)\n      - record: service:http_request_duration_seconds:p99\n        expr: |\n          histogram_quantile(0.99, \n            sum(rate(http_request_duration_seconds_bucket{handler!~\"\u002Fhealth|\u002Fmetrics\"}[5m])) by (le))\n```\n\n### AlertManager Configuration\n```yaml\n# alertmanager.yml\nglobal:\n  resolve_timeout: 5m\n  smtp_smarthost: 'smtp.example.com:587'\n  smtp_from: 'alertmanager@example.com'\n  smtp_auth_username: 'alertmanager'\n  smtp_auth_password: '${SMTP_PASSWORD}'\n\nroute:\n  group_by: ['alertname', 'severity']\n  group_wait: 30s\n  group_interval: 5m\n  repeat_interval: 4h\n  receiver: 'default'\n  routes:\n    - match:\n        severity: critical\n      receiver: 'critical-pager'\n      continue: true\n    - match:\n        severity: warning\n      receiver: 'warning-slack'\n      continue: true\n    - match_re:\n        alertname: '.*Info'\n      receiver: 'informational'\n      group_interval: 15m\n\nreceivers:\n  - name: 'default'\n    email_configs:\n      - to: 'team@example.com'\n        send_resolved: true\n        html: |\n          {{ define \"email.default.html\" }}\n          \u003C!DOCTYPE html>\n          \u003Chtml>\n          \u003Cbody>\n            \u003Ch2>{{ .Status }} - {{ .GroupLabels.alertname }}\u003C\u002Fh2>\n            {{ range .Alerts }}\n              \u003Cp>\u003Cstrong>{{ .Labels.severity | upper }}\u003C\u002Fstrong>\u003C\u002Fp>\n              \u003Cp>{{ .Annotations.summary }}\u003C\u002Fp>\n              \u003Cpre>{{ .Annotations.description }}\u003C\u002Fpre>\n            {{ end }}\n          \u003C\u002Fbody>\n          \u003C\u002Fhtml>\n          {{ end }}\n          {{ template \"email.default.html\" . }}\n    \n  - name: 'critical-pager'\n    pagerduty_configs:\n      - service_key: '${PAGERDUTY_SERVICE_KEY}'\n        severity: critical\n    \n  - name: 'warning-slack'\n    slack_configs:\n      - channel: '#alerts-warning'\n        api_url: '${SLACK_WEBHOOK_URL}'\n        title: '{{ range .Alerts }}{{ .Labels.alertname }} {{ end }}'\n        text: '{{ range .Alerts }}{{ .Annotations.summary }} {{ end }}'\n        severity: '{{ .Labels.severity }}'\n        color: '{{ if eq .Labels.severity \"critical\" }}danger{{ else }}warning{{ end }}'\n\ninhibit_rules:\n  - source_match:\n      severity: 'critical'\n    target_match:\n      severity: 'warning'\n    equal: ['alertname', 'instance']\n```\n\n### Grafana Dashboard\n```json\n{\n  \"dashboard\": {\n    \"title\": \"Application Overview\",\n    \"uid\": \"app-overview\",\n    \"tags\": [\"application\", \"overview\"],\n    \"timezone\": \"browser\",\n    \"refresh\": \"30s\",\n    \"panels\": [\n      {\n        \"title\": \"Request Rate\",\n        \"type\": \"graph\",\n        \"gridPos\": {\"x\": 0, \"y\": 0, \"w\": 12, \"h\": 8},\n        \"targets\": [\n          {\n            \"expr\": \"sum(rate(http_requests_total[5m])) by (method, status)\",\n            \"legendFormat\": \"{{method}} {{status}}\"\n          }\n        ]\n      },\n      {\n        \"title\": \"Error Rate\",\n        \"type\": \"stat\",\n        \"gridPos\": {\"x\": 12, \"y\": 0, \"w\": 12, \"h\": 4},\n        \"targets\": [\n          {\n            \"expr\": \"sum(rate(http_requests_total{status=~\\\"5..\\\"}[5m])) \u002F sum(rate(http_requests_total[5m])) * 100\",\n            \"legendFormat\": \"Error Rate %\"\n          }\n        ],\n        \"fieldConfig\": {\n          \"defaults\": {\n            \"unit\": \"percent\",\n            \"thresholds\": {\n              \"mode\": \"absolute\",\n              \"steps\": [\n                {\"color\": \"green\", \"value\": null},\n                {\"color\": \"yellow\", \"value\": 1},\n                {\"color\": \"red\", \"value\": 5}\n              ]\n            }\n          }\n        }\n      },\n      {\n        \"title\": \"P99 Latency\",\n        \"type\": \"graph\",\n        \"gridPos\": {\"x\": 0, \"y\": 8, \"w\": 12, \"h\": 8},\n        \"targets\": [\n          {\n            \"expr\": \"histogram_quantile(0.99, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))\",\n            \"legendFormat\": \"p99\"\n          },\n          {\n            \"expr\": \"histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (le))\",\n            \"legendFormat\": \"p95\"\n          }\n        ]\n      },\n      {\n        \"title\": \"Active Pods\",\n        \"type\": \"timeseries\",\n        \"gridPos\": {\"x\": 12, \"y\": 8, \"w\": 12, \"h\": 8},\n        \"targets\": [\n          {\n            \"expr\": \"count(kube_pod_container_status_ready{namespace=\\\"$namespace\\\"})\",\n            \"legendFormat\": \"Ready\"\n          },\n          {\n            \"expr\": \"count(kube_pod_container_status_ready{namespace=\\\"$namespace\\\"} == 0)\",\n            \"legendFormat\": \"Not Ready\"\n          }\n        ]\n      }\n    ]\n  }\n}\n```\n\n## Best Practices\n- Use histograms for values with many distinct values (latency, sizes)\n- Set appropriate recording rules for complex queries\n- Implement labels consistently across metrics\n- Use appropriate alert thresholds based on SLOs\n- Avoid alert fatigue with proper grouping and routing\n- Use service discovery instead of static configurations\n- Monitor not just infrastructure but business metrics too\n- Implement proper error budget policies\n- Use annotations for rich alert information\n- Test alerting rules before deploying to production\n",{"name":5,"license":14,"metadata":31,"description":7,"compatibility":24},{"audience":32,"category":33},"devops-engineers","systems-administration","main","5f7a3e453c98261f93d19a6a7de44ad8f7b72d41","systems-administration\u002Fmonitoring",2,"https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk","2026-03-01 06:55:40",{"source":8,"skillName":5,"commands":42,"prompt":52,"zipAvailable":53},[43,46,49],{"tool":44,"command":45},"npx","npx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill monitoring",{"tool":47,"command":48},"bunx","bunx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill monitoring",{"tool":50,"command":51},"pnpm","pnpm dlx skills add ffsshhttiikk\u002Fopencode-agents-skills --skill monitoring","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fsystems-administration\u002Fmonitoring\u002FSKILL.md",true,[],[56,67,77,85,95,104],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":26},"01M6CXT9TXDF79BWJTMQAPB49G","xamarin","Xamarin cross-platform development","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fxamarin\u002FSKILL.md",[],[58,63,64,65,24,66],"platform","cross-platform","mobile","development",{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":26},"01M6CXT8AD04MFYDA32VW3FKAG","wrangling","Data wrangling fundamentals","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwrangling\u002FSKILL.md",[],[69,74,24,75,76],"data wrangling","science","data",{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":26},"01M6CXT717GCN7SRRNPBDP4508","windows","Windows operating system administration and scripting","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwindows\u002FSKILL.md",[],[79,22,24,84],"scripting",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":26},"01M6CXT54K794NMEM3XAPZZDKT","wide-column","Wide-column data model","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwide-column\u002FSKILL.md",[],[92,93,24,94,76],"wide column","databases","model",{"skillNo":96,"name":97,"nameZh":6,"description":98,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":99,"categories":100,"keywords":101,"publishedAt":26},"01M6CXT28FMT2P4V9GZE67WA8E","wide-column-stores","Wide-column database stores","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwide-column-stores\u002FSKILL.md",[],[102,93,24,103],"wide column stores","database",{"skillNo":105,"name":106,"nameZh":6,"description":107,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":108,"categories":109,"keywords":110,"publishedAt":26},"01M6CXT0D0M0Q4T2N7C2RX7DSN","websockets","WebSocket implementation and best practices","https:\u002F\u002Fgithub.com\u002Fffsshhttiikk\u002Fopencode-agents-skills\u002Fblob\u002Fmain\u002Fwebsockets\u002FSKILL.md",[],[106,111,112,113,24,114,25],"websocket","real-time","time","best practices"]