Initial skills documentation — 25 categories, all SKILL.md + references + scripts

2026-07-15 17:42:20 -04:00
commit 1b4fcd4427
976 changed files with 188344 additions and 0 deletions
@@ -0,0 +1,56 @@
+version: '3.8'
+
+services:
+  prometheus:
+    image: prom/prometheus:latest
+    container_name: prometheus
+    restart: unless-stopped
+    volumes:
+      - ./prometheus.yml:/etc/prometheus/prometheus.yml
+      - prometheus_data:/prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yml'
+      - '--storage.tsdb.path=/prometheus'
+      - '--storage.tsdb.retention.time=90d'
+    ports:
+      - "127.0.0.1:9090:9090"
+    deploy:
+      resources:
+        limits:
+          cpus: '1'
+          memory: 1G
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+  grafana:
+    image: grafana/grafana:latest
+    container_name: grafana
+    restart: unless-stopped
+    depends_on:
+      - prometheus
+    volumes:
+      - grafana_data:/var/lib/grafana
+      - ./grafana-provisioning:/etc/grafana/provisioning
+    environment:
+      - GF_SECURITY_ADMIN_USER=admin
+      - GF_SECURITY_ADMIN_PASSWORD=ITProPartnerMonitor!
+      - GF_INSTALL_PLUGINS=
+    ports:
+      - "127.0.0.1:3002:3000"
+    deploy:
+      resources:
+        limits:
+          cpus: '1'
+          memory: 512M
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "3"
+
+volumes:
+  prometheus_data:
+  grafana_data:
@@ -0,0 +1,16 @@
+# Grafana provisioning — Prometheus datasource
+# Mount this file to /etc/grafana/provisioning/datasources/prometheus.yml
+apiVersion: 1
+
+datasources:
+  - name: Prometheus
+    type: prometheus
+    access: proxy
+    url: http://prometheus:9090
+    isDefault: true
+    editable: false
+    uid: prometheus
+    jsonData:
+      timeInterval: "60s"
+      queryTimeout: "30s"
+      httpMethod: POST
@@ -0,0 +1,46 @@
+# Prometheus configuration for IT Pro Partner infrastructure
+# Scrapes:
+#   1. Ops Portal backend (FastAPI /metrics)
+#   2. Node Exporter on Core server
+#   3. Node Exporter on each Hetzner server
+#   4. (Optional) Prometheus self-monitoring
+global:
+  scrape_interval: 60s      # Every 60s for all targets
+  evaluation_interval: 60s
+  scrape_timeout: 10s
+
+rule_files:
+  - "alerts.yml"
+
+scrape_configs:
+  # Self-monitoring
+  - job_name: 'prometheus'
+    static_configs:
+      - targets: ['localhost:9090']
+
+  # Ops Portal backend metrics
+  - job_name: 'ops-portal'
+    static_configs:
+      - targets: ['127.0.0.1:8090']
+    metrics_path: /metrics
+
+  # Core server (netcup) — node exporter on port 9100
+  - job_name: 'node-core'
+    static_configs:
+      - targets: ['127.0.0.1:9100']
+    metrics_path: /metrics
+
+  # Hetzner servers — node exporter on each
+  - job_name: 'node-hetzner'
+    static_configs:
+      - targets:
+        - '5.161.62.38:9100'     # wphost02
+        - '5.161.225.131:9100'   # unms
+        - '178.156.131.57:9100'  # unifi
+        - '178.156.130.130:9100' # hudu
+        - '178.156.149.32:9100'  # fleettracker360
+        - '178.156.168.35:9100'  # docker
+        - '178.156.167.181:9100' # ai
+        - '5.161.114.8:9100'     # app1-bu
+        - '87.99.144.163:9100'   # app1 (n8n)
+        - '87.99.159.142:9100'   # tony-vps