proxmox-pbs-backup-joblisted

This skill should be used when adding a new host (LXC or VM) to an existing Proxmox Backup Server nightly backup schedule, creating a vzdump job via `pvesh`, debugging a backup job that succeeds but the prune step fails with a permission error, excluding one specific mount point (e.g. a bulky media/data volume) from an LXC's backup while still backing up its rootfs, setting up PBS-to-PBS replication via a Remote + Sync Job (a second physical PBS instance holding a pulled copy of another datastore), a PBS API token that returns `{}` from `/access/permissions` despite a correct-looking ACL grant, `apt update` failing with `401 Unauthorized` against `enterprise.proxmox.com` on a no-subscription PBS install, or restore-testing a PBS datastore/replica by restoring to a throwaway VMID/CTID. Trigger phrases include "add backup job pvesh", "vzdump schedule new host", "pbs prune permission denied", "Datastore.Modify Datastore.Prune missing", "backup job finished with errors", "proxmox-backup-client prune permission ch
jackson2w/claude-code-skills · ★ 1 · API & Backend · score 64

Install: claude install-skill jackson2w/claude-code-skills

# Adding a host to an existing PBS nightly backup schedule Use this when a new LXC/VM needs to join an existing Proxmox Backup Server datastore's nightly backup rotation (as opposed to setting up PBS or a datastore from scratch — that's a bigger, one-time task). Verified end-to-end adding the Homepage dashboard (VMID 140) to an existing `pihole-and-friends` datastore already backing up Pi-hole and Home Assistant. ## Create the job via `pvesh`, not by hand-editing `/etc/pve/jobs.cfg` `pvesh` is available directly on the Proxmox host (`pve`) even though it isn't installed on the PBS host itself — backup jobs are configured cluster-side (`/etc/pve/jobs.cfg`), not on PBS. Match whatever schedule offset and retention the existing jobs already use rather than inventing new values: ```bash # Check what's already scheduled first, so the new job doesn't collide: pvesh get /cluster/backup --output-format json pvesh create /cluster/backup \ --vmid <new-vmid> \ --storage <existing-pbs-storage-name> \ --mode snapshot \ --schedule 'sun..sat HH:MM' \ --enabled 1 \ --comment '<Host> nightly backup to PBS' \ --prune-backups keep-daily=7,keep-weekly=4 ``` Stagger the schedule time a few minutes after the last existing job in the same datastore (e.g. `03:00`, `03:15`, `03:20`) rather than running them concurrently. ## Always manually trigger the new job once — don't just wait for the cron schedule A scheduled job succeeding tonight doesn't confirm the *prune* step works (s