npx claudepluginhub frank-luongt/faos-skills-marketplace --plugin faos-sreThis skill uses the workspace's default tool permissions.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Create and manage production-ready Grafana dashboards for comprehensive system observability.
Design effective Grafana dashboards for monitoring applications, infrastructure, and business metrics.
┌─────────────────────────────────────┐
│ Critical Metrics (Big Numbers) │
├─────────────────────────────────────┤
│ Key Trends (Time Series) │
├─────────────────────────────────────┤
│ Detailed Metrics (Tables/Heatmaps) │
└─────────────────────────────────────┘
{
"dashboard": {
"title": "API Monitoring",
"tags": ["api", "production"],
"timezone": "browser",
"refresh": "30s",
"panels": [
{
"title": "Request Rate",
"type": "graph",
"targets": [
{
"expr": "sum(rate(http_requests_total[5m])) by (service)",
"legendFormat": "{{service}}"
}
],
"gridPos": {"x": 0, "y": 0, "w": 12, "h": 8}
},
{
"title": "Error Rate %",
"type": "graph",
"targets": [
{
"expr": "(sum(rate(http_requests_total{status=~\"5..\"}[5m])) / sum(rate(http_requests_total[5m]))) * 100",
"legendFormat": "Error Rate"
}
],
"alert": {
"conditions": [
{
"evaluator": {"params": [5], "type": "gt"},
"operator": {"type": "and"},
"query": {"params": ["A", "5m", "now"]},
"type": "query"
}
]
},
"gridPos": {"x": 12, "y": 0, "w": 12, "h": 8}
},
{
"title": "P95 Latency",
"type": "graph",
"targets": [
{
"expr": "histogram_quantile(0.95, sum(rate(http_request_duration_seconds_bucket[5m])) by (le, service))",
"legendFormat": "{{service}}"
}
],
"gridPos": {"x": 0, "y": 8, "w": 24, "h": 8}
}
]
}
}
Reference: See assets/api-dashboard.json
{
"type": "stat",
"title": "Total Requests",
"targets": [{
"expr": "sum(http_requests_total)"
}],
"options": {
"reduceOptions": {
"values": false,
"calcs": ["lastNotNull"]
},
"orientation": "auto",
"textMode": "auto",
"colorMode": "value"
},
"fieldConfig": {
"defaults": {
"thresholds": {
"mode": "absolute",
"steps": [
{"value": 0, "color": "green"},
{"value": 80, "color": "yellow"},
{"value": 90, "color": "red"}
]
}
}
}
}
{
"type": "graph",
"title": "CPU Usage",
"targets": [{
"expr": "100 - (avg by (instance) (rate(node_cpu_seconds_total{mode=\"idle\"}[5m])) * 100)"
}],
"yaxes": [
{"format": "percent", "max": 100, "min": 0},
{"format": "short"}
]
}
{
"type": "table",
"title": "Service Status",
"targets": [{
"expr": "up",
"format": "table",
"instant": true
}],
"transformations": [
{
"id": "organize",
"options": {
"excludeByName": {"Time": true},
"indexByName": {},
"renameByName": {
"instance": "Instance",
"job": "Service",
"Value": "Status"
}
}
}
]
}
{
"type": "heatmap",
"title": "Latency Heatmap",
"targets": [{
"expr": "sum(rate(http_request_duration_seconds_bucket[5m])) by (le)",
"format": "heatmap"
}],
"dataFormat": "tsbuckets",
"yAxis": {
"format": "s"
}
}
{
"templating": {
"list": [
{
"name": "namespace",
"type": "query",
"datasource": "Prometheus",
"query": "label_values(kube_pod_info, namespace)",
"refresh": 1,
"multi": false
},
{
"name": "service",
"type": "query",
"datasource": "Prometheus",
"query": "label_values(kube_service_info{namespace=\"$namespace\"}, service)",
"refresh": 1,
"multi": true
}
]
}
}
sum(rate(http_requests_total{namespace="$namespace", service=~"$service"}[5m]))
{
"alert": {
"name": "High Error Rate",
"conditions": [
{
"evaluator": {
"params": [5],
"type": "gt"
},
"operator": {"type": "and"},
"query": {
"params": ["A", "5m", "now"]
},
"reducer": {"type": "avg"},
"type": "query"
}
],
"executionErrorState": "alerting",
"for": "5m",
"frequency": "1m",
"message": "Error rate is above 5%",
"noDataState": "no_data",
"notifications": [
{"uid": "slack-channel"}
]
}
}
dashboards.yml:
apiVersion: 1
providers:
- name: 'default'
orgId: 1
folder: 'General'
type: file
disableDeletion: false
updateIntervalSeconds: 10
allowUiUpdates: true
options:
path: /etc/grafana/dashboards
Key Panels:
Reference: See assets/infrastructure-dashboard.json
Key Panels:
Reference: See assets/database-dashboard.json
Key Panels:
resource "grafana_dashboard" "api_monitoring" {
config_json = file("${path.module}/dashboards/api-monitoring.json")
folder = grafana_folder.monitoring.id
}
resource "grafana_folder" "monitoring" {
title = "Production Monitoring"
}
- name: Deploy Grafana dashboards
copy:
src: "{{ item }}"
dest: /etc/grafana/dashboards/
with_fileglob:
- "dashboards/*.json"
notify: restart grafana
assets/api-dashboard.json - API monitoring dashboardassets/infrastructure-dashboard.json - Infrastructure dashboardassets/database-dashboard.json - Database monitoring dashboardreferences/dashboard-design.md - Dashboard design guideprometheus-configuration - For metric collectionslo-implementation - For SLO dashboards