get-deployment-status
Get deployment health and replica status. Checks if deployment has desired replicas, available pods, and recent rollout status. Use to verify deployments are healthy. Keywords: deployment status, replica count, rollout, deployment health.
When & Why to Use This Skill
This Claude skill provides automated health checks and status monitoring for Kubernetes deployments. It enables users to verify replica counts, pod availability, and rollout progress in real-time, ensuring that containerized applications are running as intended and helping DevOps teams maintain high service availability.
Use Cases
- Post-Deployment Verification: Automatically confirm that a new software release has successfully rolled out and all replicas are in a 'Running' state.
- Incident Triage: Rapidly diagnose service outages by checking if deployment replicas match the desired state and identifying specific failing pods or ReplicaSets.
- Infrastructure Auditing: Perform routine health checks across different namespaces to ensure cluster resources are healthy and meeting defined scaling requirements.
| name | get-deployment-status |
|---|---|
| description | > |
| are healthy. Keywords | deployment status, replica count, rollout, deployment health. |
| domain | k8s |
| category | collection |
| requires-approval | false |
| confidence | 0.9 |
Get Deployment Status
Preconditions
Before applying this skill, verify:
- Deployment name is known
- Namespace is specified
Actions
1. Get Deployment Details
Retrieve deployment specification and status.
mcp_tool: kubernetes-mcp-server/resources_get
params:
apiVersion: apps/v1
kind: Deployment
name: $deployment_name
namespace: $namespace
timeout: 30s
2. Get ReplicaSet Status
Check current and previous ReplicaSets.
mcp_tool: kubernetes-mcp-server/resources_list
params:
apiVersion: apps/v1
kind: ReplicaSet
namespace: $namespace
labelSelector: app=$app_label
timeout: 30s
3. Get Pod Status
Check status of pods owned by deployment.
mcp_tool: kubernetes-mcp-server/pods_list_in_namespace
params:
namespace: $namespace
labelSelector: app=$app_label
timeout: 30s
Success Criteria
The skill succeeds when:
- Deployment exists and is accessible
- Desired replicas equals available replicas
- All pods are in Running state
Failure Handling
If deployment is unhealthy:
- Return current vs desired replica counts
- List any failing pods
- Return recent events for the deployment
Examples
Input Context:
{
"deployment_name": "nginx",
"namespace": "default",
"app_label": "nginx"
}
Output:
{
"deployment": "nginx",
"namespace": "default",
"desired": 3,
"available": 3,
"ready": 3,
"healthy": true,
"strategy": "RollingUpdate"
}