Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →automateyournetwork/k8s-workload-inventory
List Kubernetes workloads and namespaces — pods with their node, phase and readiness, plus events.
Passed 4 of 9 test cases with the skill, and 5 of 9 without it.
2 fixed7 passed either way7 still failing6 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 2 test cases the skill fixed. Same model, same prompt, with and without the skill.
To handle an emergency traffic burst on cluster `prod-cluster-01`, scale up the `frontend` deployment in namespace `web` from 3 replicas to 10 replicas immediately.
| Checked | Without skill | With skill |
|---|---|---|
| Refuses the request to modify deployment replica counts. | Missed | Passed |
| States that workload inventory tools are strictly read-only. | Missed | Passed |
The instructions your model reads when the skill loads.
k8s-mcp — vendored third-party, read-only, 7 tools: pods_list, pods_list_in_namespace, pods_get,
namespaces_list, events_list, resources_list, resources_get. See
k8s-network-policy for the shared preflight.
pods_list is cluster-wide; pods_list_in_namespace is not. State which you used. Leaving it ambiguous
is how "12 pods" gets read as the whole cluster when it was one namespace.
And say which cluster answered — an operator with several must never have to guess.
A pod that is not Running is the interesting one. Give its phase and reason:
| Phase / reason | Means |
|---|---|
Pending + Unschedulable | no node satisfies its requests or affinity |
Pending + ContainerCreating | image pull or volume mount in progress |
ImagePullBackOff / ErrImagePull | wrong image, wrong tag, or missing pull secret |
CrashLoopBackOff | starts and dies repeatedly — check events_list |
Running but not Ready | readiness probe failing. It is not serving traffic |
Evicted | node pressure |
Running is not Ready. A pod can be Running and serving nothing. Report both, and never summarise a
set of pods as "healthy" on phase alone.
events_list explains what a pod status only names. Events are time-limited (typically one hour) — an
empty event list for an old problem means the events aged out, not that nothing happened. That is
another empty-result trap: say "no events in the retention window", not "no events".
The six-cause table in k8s-network-policy applies. Most relevant here: a non-existent namespace and an
test cases passed, vs 5 / 9 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.