scitix
@scitix Organization
Public Skills
deep-investigation
by scitix
Structured hypothesis-driven investigation for complex infrastructure issues. Triggered by /dp command or [Deep Investigation] UI toggle.
node-ping-gateway
by scitix
Ping a node's gateway for a given network interface. Auto-detects gateway IP from the routing table, then pings it. Execute via node_script tool.
job-debug
by scitix
Diagnose Job and CronJob failures (BackoffLimitExceeded, DeadlineExceeded, pods failing, CronJob not triggering). Checks Job status, pod logs, and CronJob schedule to identify why batch workloads are failing.
pvc-debug
by scitix
Diagnose PersistentVolumeClaim failures (Pending PVC, StorageClass not found, PV binding issues, capacity mismatch). Checks PVC, PV, StorageClass, and provisioner events to identify why storage is not available.
hpa-debug
by scitix
Diagnose HorizontalPodAutoscaler failures (not scaling, metrics unavailable, target mismatch). Checks HPA status, metrics-server health, and scaling events to identify why autoscaling is not working.
manage-skill
by scitix
Guides the user to the Siclaw Web page to manage Skills. Use this guide when the user requests to create, edit, or view a Skill in a Channel conversation.
node-show-gateway
by scitix
Show the gateway for a network interface on a Kubernetes node. Runs ip -j route on the host via node_script tool.
pod-ping-gateway
by scitix
Ping a pod's gateway for a given network interface. Auto-detects gateway IP from the routing table, then pings it. Execute via pod_netns_script tool.
dns-debug
by scitix
Diagnose DNS resolution failures in the cluster (NXDOMAIN, timeouts, SERVFAIL). Checks CoreDNS health, service endpoints, and DNS configuration.
node-health-check
by scitix
Check node health and diagnose node-level issues (NotReady, DiskPressure, MemoryPressure, PIDPressure). Inspects node conditions, resource allocation, and real-time usage.
update-skill
by scitix
Procedure for modifying, updating, or fixing an existing Siclaw skill. Skills are on a read-only filesystem — use the update_skill tool, never edit files directly.
pod-crash-debug
by scitix
Diagnose pod crash failures (CrashLoopBackOff, OOMKilled, Error, RunContainerError). Checks pod status, events, and previous logs to identify root cause.
node-logs
by scitix
Retrieve logs from a Kubernetes node. Supports journalctl (systemd units) and file-based logs. Use when you need to inspect node-level logs (containerd, kubelet, etc.). Execute via node_script tool.
find-node
by scitix
Fuzzy-match Kubernetes nodes by keyword. Equivalent to kubectl get nodes -o wide grep <keyword>, with header preserved. Use this instead of listing all nodes to keep context minimal.
pod-pending-debug
by scitix
Diagnose pod scheduling failures (Pending, Unschedulable). Checks events, node resources, taints, affinity, and PVC bindings to identify why a pod cannot be scheduled.
create-skill
by scitix
Guide for creating new Siclaw skills from troubleshooting conversations. When a user asks to save a workflow as a skill, follow this guide to produce a well-structured skill definition using the create_skill tool.
image-pull-debug
by scitix
Diagnose container image pull failures (ErrImagePull / ImagePullBackOff). Checks pod status, containerd logs, and events to identify root cause.
deployment-rollout-debug
by scitix
Diagnose Deployment rollout failures (stuck rollouts, ProgressDeadlineExceeded, replica mismatch). Checks rollout status, ReplicaSets, and new pod health to identify why an update is failing.
cluster-events
by scitix
Analyze cluster-wide Kubernetes events to identify issues and patterns. Aggregates Warning events, detects high-frequency patterns, and correlates related events.
service-debug
by scitix
Diagnose Service connectivity issues (empty Endpoints, selector mismatch, port mismatch, no backend pods). Checks Service, Endpoints, and target pods to identify why traffic is not reaching backends.
pod-show-gateway
by scitix
Show the gateway for a network interface in a Kubernetes pod. Reads the routing table via ip -j route from the pod's network namespace. Execute via pod_netns_script tool.