Initial commit

skills/auto-scaling-configurator/assets/README.md

@@ -0,0 +1,7 @@
+# Assets
+
+Bundled resources for auto-scaling-configurator skill
+
+- [ ] config_template.yaml: YAML template for auto-scaling configuration files, providing a starting point for users.
+- [ ] example_hpa.yaml: Example Kubernetes Horizontal Pod Autoscaler (HPA) configuration file.
+- [ ] example_aws_scaling_policy.json: Example AWS auto-scaling policy configuration file.

skills/auto-scaling-configurator/assets/config_template.yaml

@@ -0,0 +1,79 @@
+# Auto-Scaling Configuration Template
+
+# --- Global Settings ---
+global:
+  # Enable or disable auto-scaling globally
+  enabled: true
+
+  # Default cooldown period (in seconds) after a scaling event
+  cooldown: 300 # seconds (5 minutes)
+
+# --- Application Configuration ---
+application:
+  name: REPLACE_ME # Application Name (e.g., web-app, api-server)
+  type: web  # Application type (e.g., web, api, worker)
+
+  # Resource limits (CPU, Memory)
+  resources:
+    cpu:
+      min: 0.5  # Minimum CPU units
+      max: 4    # Maximum CPU units
+    memory:
+      min: 512  # Minimum memory in MB
+      max: 4096 # Maximum memory in MB
+
+# --- Scaling Policies ---
+scaling_policies:
+  # --- CPU Utilization Scaling ---
+  cpu_utilization:
+    enabled: true
+    target_utilization: 70 # Target CPU utilization percentage
+    scale_up_threshold: 80  # CPU usage percentage to trigger scale-up
+    scale_down_threshold: 40 # CPU usage percentage to trigger scale-down
+    scale_up_increment: 1    # Number of instances to add during scale-up
+    scale_down_decrement: 1  # Number of instances to remove during scale-down
+
+  # --- Memory Utilization Scaling ---
+  memory_utilization:
+    enabled: true
+    target_utilization: 75 # Target Memory utilization percentage
+    scale_up_threshold: 85  # Memory usage percentage to trigger scale-up
+    scale_down_threshold: 50 # Memory usage percentage to trigger scale-down
+    scale_up_increment: 1    # Number of instances to add during scale-up
+    scale_down_decrement: 1  # Number of instances to remove during scale-down
+
+  # --- Request Latency Scaling ---
+  request_latency:
+    enabled: false # Enable only if latency metrics are available
+    target_latency: 200 # Target request latency in milliseconds
+    scale_up_threshold: 500 # Latency in milliseconds to trigger scale-up
+    scale_down_threshold: 100 # Latency in milliseconds to trigger scale-down
+    scale_up_increment: 1    # Number of instances to add during scale-up
+    scale_down_decrement: 1  # Number of instances to remove during scale-down
+
+  # --- Custom Metric Scaling ---
+  custom_metric:
+    enabled: false # Enable only if a custom metric is available
+    metric_name: YOUR_VALUE_HERE # Name of the custom metric
+    target_value: YOUR_VALUE_HERE # Target value for the custom metric
+    scale_up_threshold: YOUR_VALUE_HERE # Threshold to trigger scale-up
+    scale_down_threshold: YOUR_VALUE_HERE # Threshold to trigger scale-down
+    scale_up_increment: 1    # Number of instances to add during scale-up
+    scale_down_decrement: 1  # Number of instances to remove during scale-down
+
+# --- Infrastructure Configuration ---
+infrastructure:
+  platform: aws # Cloud platform (e.g., aws, azure, gcp, on-prem)
+  region: us-east-1 # Cloud region
+  instance_type: t3.medium # Instance type for new instances
+  min_instances: 1    # Minimum number of instances
+  max_instances: 5    # Maximum number of instances
+
+# --- Monitoring Configuration ---
+monitoring:
+  # Integration with monitoring tools (e.g., CloudWatch, Prometheus)
+  # Configure details for your monitoring system here
+  # Example:
+  type: cloudwatch # Monitoring system type
+  namespace: MyApp # Monitoring namespace
+  metric_prefix: MyAppInstance # Metric prefix

skills/auto-scaling-configurator/assets/example_aws_scaling_policy.json

@@ -0,0 +1,70 @@
+{
+  "_comment": "Example AWS Auto Scaling Policy Configuration",
+  "PolicyName": "WebAppCPUPolicy",
+  "PolicyType": "TargetTrackingScaling",
+  "TargetTrackingConfiguration": {
+    "_comment": "Target utilization for CPU",
+    "TargetValue": 70.0,
+    "_comment": "Metric to track",
+    "PredefinedMetricSpecification": {
+      "PredefinedMetricType": "ASGAverageCPUUtilization"
+    },
+    "_comment": "Cooldown periods",
+    "ScaleOutCooldown": 300,
+    "ScaleInCooldown": 600
+  },
+  "_comment": "Resource ID - Auto Scaling Group ARN",
+  "ResourceId": "autoScalingGroupName/my-web-app-asg",
+  "ScalableDimension": "autoscaling:autoScalingGroup:DesiredCapacity",
+  "ServiceNamespace": "autoscaling",
+  "_comment": "Optional - Adjustments for more control",
+  "StepScalingPolicyConfiguration": {
+    "_comment": "Adjustment type (ChangeInCapacity, PercentChangeInCapacity, ExactCapacity)",
+    "AdjustmentType": "ChangeInCapacity",
+    "_comment": "Minimum number of instances to add/remove",
+    "MinAdjustmentMagnitude": 1,
+    "_comment": "Cooldown period",
+    "Cooldown": 300,
+    "_comment": "Scaling adjustments based on metric value",
+    "StepAdjustments": [
+      {
+        "MetricIntervalLowerBound": 0.0,
+        "MetricIntervalUpperBound": 10.0,
+        "ScalingAdjustment": -1
+      },
+      {
+        "MetricIntervalLowerBound": 70.0,
+        "ScalingAdjustment": 1
+      }
+    ]
+  },
+  "_comment": "Optional - Metric Alarms",
+  "Alarms": [
+    {
+      "AlarmName": "CPUHigh",
+      "MetricName": "CPUUtilization",
+      "Namespace": "AWS/EC2",
+      "Statistic": "Average",
+      "Period": 60,
+      "EvaluationPeriods": 5,
+      "Threshold": 80.0,
+      "ComparisonOperator": "GreaterThanThreshold",
+      "AlarmActions": [
+        "arn:aws:sns:us-east-1:123456789012:HighCPUAlarm"
+      ]
+    },
+    {
+      "AlarmName": "CPULow",
+      "MetricName": "CPUUtilization",
+      "Namespace": "AWS/EC2",
+      "Statistic": "Average",
+      "Period": 60,
+      "EvaluationPeriods": 5,
+      "Threshold": 20.0,
+      "ComparisonOperator": "LessThanThreshold",
+      "AlarmActions": [
+        "arn:aws:sns:us-east-1:123456789012:LowCPUAlarm"
+      ]
+    }
+  ]
+}

skills/auto-scaling-configurator/assets/example_hpa.yaml

@@ -0,0 +1,43 @@
+# example_hpa.yaml
+# This is an example Kubernetes Horizontal Pod Autoscaler (HPA) configuration file.
+# It defines how the number of pods in a deployment or replication controller
+# should be automatically scaled based on observed CPU utilization.
+
+apiVersion: autoscaling/v2 # Use autoscaling/v2 for more features (e.g., resource metrics)
+kind: HorizontalPodAutoscaler
+metadata:
+  name: example-hpa # The name of the HPA resource
+  namespace: default # The namespace where the HPA should be deployed (REPLACE_ME if needed)
+spec:
+  scaleTargetRef: # Defines the target resource to scale
+    apiVersion: apps/v1 # API version of the target resource
+    kind: Deployment # The type of resource to scale (e.g., Deployment, ReplicationController)
+    name: example-deployment # The name of the Deployment to scale (REPLACE_ME)
+  minReplicas: 2 # The minimum number of replicas to maintain
+  maxReplicas: 10 # The maximum number of replicas to scale to
+  metrics: # Defines the metrics used to trigger scaling
+    - type: Resource # Scale based on resource utilization
+      resource:
+        name: cpu # The resource to monitor (CPU in this case)
+        target:
+          type: Utilization # Target utilization percentage
+          averageUtilization: 70 # Target CPU utilization percentage (e.g., 70%)
+    - type: Resource # Scale based on memory utilization
+      resource:
+        name: memory # The resource to monitor (Memory in this case)
+        target:
+          type: Utilization # Target utilization percentage
+          averageUtilization: 80 # Target Memory utilization percentage (e.g., 80%)
+  behavior: # Optional: Define scaling behavior
+    scaleUp: # Define scale up behavior
+      stabilizationWindowSeconds: 300 # Delay for scaling up after a scaling event
+      policies: # Scaling policies (e.g., percentage or fixed number of replicas)
+        - type: Percent # Scale up by a percentage
+          value: 20 # Percentage increase
+          periodSeconds: 60 # Evaluate every 60 seconds
+    scaleDown: # Define scale down behavior
+      stabilizationWindowSeconds: 300 # Delay for scaling down after a scaling event
+      policies: # Scaling policies (e.g., percentage or fixed number of replicas)
+        - type: Percent # Scale down by a percentage
+          value: 10 # Percentage decrease
+          periodSeconds: 60 # Evaluate every 60 seconds