TKE=$SKILL_DIR/scripts/tke.py

python3 $TKE clusters                                              # list clusters
python3 $TKE cluster cls-xxxxxxxx                                  # one cluster's details
python3 $TKE nodes cls-xxxxxxxx
python3 $TKE pools cls-xxxxxxxx                                    # node pools
python3 $TKE kubeconfig cls-xxxxxxxx --save ~/.kube/config-tke     # write kubeconfig
python3 $TKE workloads cls-xxxxxxxx -n my-namespace
python3 $TKE pods cls-xxxxxxxx -n my-namespace
python3 $TKE events cls-xxxxxxxx -n my-namespace                   # recent events
python3 $TKE scale cls-xxxxxxxx -n my-namespace --name my-deploy --replicas 4
python3 $TKE restart cls-xxxxxxxx -n my-namespace --name my-deploy

pip install tencentcloud-sdk-python
brew install kubectl   # macOS;  apt install kubectl on Debian/Ubuntu

import os
from tencentcloud.common import credential
from tencentcloud.tke.v20180525 import tke_client, models

cred = credential.EnvironmentVariableCredential().get_credential()
client = tke_client.TkeClient(cred, os.environ["TENCENTCLOUD_REGION"])

req = models.DescribeClustersRequest()
req.Limit = 100
resp = client.DescribeClusters(req)
for c in resp.Clusters:
    print(c.ClusterId, c.ClusterName, c.ClusterStatus, c.ClusterVersion)

req = models.DescribeClustersRequest()
req.ClusterIds = ["cls-xxxxxxxx"]
resp = client.DescribeClusters(req)
c = resp.Clusters[0]
print(c.ClusterName, c.ClusterStatus, c.ClusterNodeNum, c.ClusterVersion)

req = models.DescribeClusterInstancesRequest()
req.ClusterId = "cls-xxxxxxxx"
req.Limit = 100
resp = client.DescribeClusterInstances(req)
for i in resp.InstanceSet:
    print(i.InstanceId, i.InstanceRole, i.InstanceState, i.NodePoolId)

req = models.DescribeClusterKubeconfigRequest()
req.ClusterId = "cls-xxxxxxxx"
req.IsExtranet = True            # False for VPC-internal kubeconfig
resp = client.DescribeClusterKubeconfig(req)

# Save and use immediately
import os, pathlib
kubeconfig = pathlib.Path(os.path.expanduser("~/.kube/config-tke-cls-xxxxxxxx"))
kubeconfig.parent.mkdir(parents=True, exist_ok=True)
kubeconfig.write_text(resp.Kubeconfig)
print("export KUBECONFIG=" + str(kubeconfig))

import subprocess

KUBECONFIG = os.path.expanduser("~/.kube/config-tke-cls-xxxxxxxx")
NS = "acedatacloud"

def kubectl(*args):
    return subprocess.run(
        ["kubectl", f"--kubeconfig={KUBECONFIG}", *args],
        check=True, capture_output=True, text=True,
    ).stdout

print(kubectl("get", "pods", "-n", NS))
print(kubectl("get", "deploy", "-n", NS))
print(kubectl("get", "svc", "-n", NS))
print(kubectl("get", "events", "-n", NS, "--sort-by=.lastTimestamp"))

print(kubectl("describe", "pod", "<pod-name>", "-n", NS))
print(kubectl("logs", "<pod-name>", "-n", NS, "--tail=200"))

# To 4 replicas. Confirm with the user before running for prod workloads.
print(kubectl("scale", "deploy/platform-backend", "-n", NS, "--replicas=4"))

# Forces every pod to recycle through the rolling-update strategy.
print(kubectl("rollout", "restart", "deploy/platform-backend", "-n", NS))
print(kubectl("rollout", "status", "deploy/platform-backend", "-n", NS, "--timeout=300s"))

req = models.DescribeClusterNodePoolsRequest()
req.ClusterId = "cls-xxxxxxxx"
resp = client.DescribeClusterNodePools(req)
for np in resp.NodePoolSet:
    print(np.NodePoolId, np.Name, np.LifeState, np.DesiredNodesNum, np.AutoscalingGroupId)

1. python: DescribeClusters → cluster status / version
2. python: DescribeClusterInstances → any nodes "failed" / "running"
3. kubectl get events → recent failures (image pulls, scheduling, OOM)
4. kubectl get pods → which pod is in CrashLoopBackOff / ImagePullBackOff
5. kubectl describe pod <name> → conditions, events on the pod
6. kubectl logs <name> --tail=200 → application logs
7. (optional) tencentcloud-cls skill → CLS query for the same window