mirror of
https://github.com/magnus919/agent-skills.git
synced 2026-09-20 08:06:35 +03:00
f83d48ba53
Adds one top-level telemetry skill covering the observability stack that deploys as one unit: Prometheus (scrape config, recording/alerting rules, relabeling, retention, HA), the OpenTelemetry Collector (pipelines, receivers/processors/exporters, sampling, trace/span correlation), and Loki (ingest, LogQL, retention, labels). Ships the read-only telemetry-check script (stdlib-only, --json): Prometheus rule sanity mirroring promtool check rules plus scrape-target reachability probes, fixture-tested with 16 unittest/pytest cases. Includes five dated references, a human-facing README, and six eval cases covering rule authoring, pipeline design, and retention. Routes up to platform-engineering and grafana without duplicating their content. Regenerates the llms.txt / marketplace / plugin catalogs and adds the README index entry. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com>
30 lines
1.0 KiB
YAML
30 lines
1.0 KiB
YAML
# Sample Prometheus recording and alerting rules used by telemetry-check.
|
|
# Mirrors the structure promtool check rules accepts: groups of recording and
|
|
# alerting rules with labels, annotations, and durations.
|
|
groups:
|
|
- name: api-slo
|
|
interval: 1m
|
|
rules:
|
|
- record: job:http_requests:rate5m
|
|
expr: sum by (job) (rate(http_requests_total{job="api"}[5m]))
|
|
- record: job:http_errors:rate5m
|
|
expr: sum by (job) (rate(http_requests_total{job="api",status=~"5.."}[5m]))
|
|
- alert: ApiHighErrorRate
|
|
expr: job:http_errors:rate5m / job:http_requests:rate5m > 0.05
|
|
for: 10m
|
|
labels:
|
|
severity: page
|
|
team: platform
|
|
annotations:
|
|
summary: "API error rate above 5% for 10 minutes"
|
|
runbook: "https://example.com/runbooks/api-high-error-rate"
|
|
- name: node-health
|
|
rules:
|
|
- alert: InstanceDown
|
|
expr: up == 0
|
|
for: 5m
|
|
labels:
|
|
severity: critical
|
|
annotations:
|
|
summary: "Instance {{ $labels.instance }} is down"
|