From coreweave-pack
Collects CoreWeave Kubernetes cluster diagnostics—nodes, pods, events, GPU allocation, failed pod logs—into a tar.gz bundle for support tickets.
How this skill is triggered — by the user, by Claude, or both
Slash command
/coreweave-pack:coreweave-debug-bundleThis skill is limited to the following tools:
The summary Claude sees in its skill listing — used to decide when to auto-load this skill
```bash
#!/bin/bash
set -euo pipefail
BUNDLE="coreweave-debug-$(date +%Y%m%d-%H%M%S)"
mkdir -p "$BUNDLE"
kubectl get nodes -o wide > "$BUNDLE/nodes.txt"
kubectl get pods --all-namespaces -o wide > "$BUNDLE/pods.txt"
kubectl get events --sort-by=.lastTimestamp > "$BUNDLE/events.txt"
kubectl describe nodes | grep -A10 "Allocated resources" > "$BUNDLE/gpu-allocation.txt"
# Pod logs for failing pods
for pod in $(kubectl get pods --field-selector=status.phase=Failed -o name); do
kubectl logs "$pod" --tail=100 > "$BUNDLE/$(basename $pod)-logs.txt" 2>&1
done
tar -czf "$BUNDLE.tar.gz" "$BUNDLE" && rm -rf "$BUNDLE"
echo "Bundle: $BUNDLE.tar.gz"
For rate limit handling, see coreweave-rate-limits.
npx claudepluginhub jeremylongshore/claude-code-plugins-plus-skills --plugin coreweave-packCollects CAST AI diagnostic bundle for Kubernetes clusters: agent logs, Helm releases, pod status, events, nodes, API status, and RBAC for support tickets and troubleshooting.
Diagnoses and fixes CoreWeave Kubernetes errors: GPU scheduling failures, pending pods, CUDA OOM, NCCL timeouts, PVC mounting, image pull issues.
Collects diagnostic logs from HyperPod clusters (EKS and Slurm) via SSM for troubleshooting and AWS Support case preparation. Use when investigating node failures or performance issues.