From homelab
Diagnose app or infra component failures. Maps app name to namespace, runs pod+HR+log diagnostics, reasons against known traps.
How this skill is triggered — by the user, by Claude, or both
Slash command
/homelab:hl-debugThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Debug an app or infrastructure component. Argument: app name (keycloak, bookstack, linkding, mealie, falco, monitoring) or a namespace.
Debug an app or infrastructure component. Argument: app name (keycloak, bookstack, linkding, mealie, falco, monitoring) or a namespace.
Map argument to namespace using INFRA.md context (already loaded at session start). If no argument, ask which app.
Run this diagnostic sequence:
HelmRelease status (if applicable):
kubectl get helmrelease <name> -n <ns> -o jsonpath='{.status.conditions}'
Pod status:
kubectl get pods -n <ns>
Pod logs (last 30 lines):
kubectl logs <pod> -n <ns> --tail=30
If CrashLoopBackOff: also run kubectl logs <pod> -n <ns> --previous --tail=30
3.5. Pod events (catches failures invisible in logs — ImagePullBackOff, OOMKilled, probe failures, scheduling):
kubectl describe pod <pod> -n <ns> | grep -A 10 "^Events:"
Format each event as: <Type> <Reason> <Message>
kubectl get cluster -n <ns>Compress output:
Then reason against known traps from INFRA.md:
Output: 2-3 lines max. Problem identified + recommended fix command. No explanation of k8s concepts.
npx claudepluginhub federicoserini/homelab-plugin --plugin homelabFetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
Applies a firm's KYC/AML rules grid to parsed onboarding records: assigns risk rating, checks required documents, outputs rule outcomes with citations, and routes for escalation.
Generates daily or weekly digests of activity from connected sources (chat, email, docs, tasks, CRM), highlighting action items, decisions, mentions, and project updates.