Grafana Prometheus Alerting

This skill should be used when a Prometheus + Grafana stack has metrics being scraped but no real alerting configured, when adding a new Grafana alert rule via provisioning-as-code (not the UI), when checking whether Prometheus alert rules actually exist versus assuming a monitoring stack alerts on its own, when detecting individual systemd service failures across a fleet without building a custom OnFailure-to-webhook mechanism, or when a Grafana alert rule needs testing end-to-end before trusting it. Also use it when a disk/filesystem alert rule is green over something that is actually filling up, when a mounted volume has no `node_filesystem_*` series at all, or when a scrape target goes DOWN after a host changes address. Trigger phrases include "prometheus has no alert rules", "grafana provisioning alert rules", "node_systemd_unit_state", "grafana rules.yaml", "alert on systemd unit failure", "grafana noDataState", "test grafana alert rule firing", "prometheus /api/v1/rules empty", "node_exporter systemd collector", "node_exporter not showing /mnt", "no metrics for mounted volume", "mount-points-exclude", "collector.filesystem.mount-points-exclude", "datastore has no disk metrics", "alert green but disk full", "filesystem collector skipping mount", "disk space rule never fires", "scrape target DOWN after IP change", "pin scrape target to hostname not IP".

mkdir -p ~/.claude/skills/grafana-prometheus-alerting
curl -L https://claudskills.com/skills/grafana-prometheus-alerting/SKILL.md \
  -o ~/.claude/skills/grafana-prometheus-alerting/SKILL.md

@misc{grafana-prometheus-alerting-2026,
  author    = {jackson2w},
  title     = {Grafana Prometheus Alerting [Claude Code skill]},
  year      = {2026},
  publisher = {ClaudSkills},
  url       = {https://claudskills.com/skills/grafana-prometheus-alerting/}
}