Ask an AI assistant about your Proxmox VE inventory

An AI assistant that can run shell commands can use cv4pve-report to answer questions about a Proxmox VE cluster: it exports the report as JSON, extracts the zip and reads the files: which VMs are running, how many snapshots each guest has, which certificates expire soon. The answers come from a dated export, not from the assistant’s memory of your cluster.

The cv4pve-report skill

The repository ships a skill, skills/cv4pve-report/SKILL.md: a short file in the Agent Skills format that Claude Code, Codex and other assistants load when a request matches its description. It tells the assistant to:

• connect only with the options file, passed with @, and never print it;
• read issues.json first, and say which export it read;
• remember that the token may not see everything: an empty list is not proof of absence.

Install it with the skills command, which needs Node.js:

npx skills add Corsinvest/cv4pve-report

Or copy the file into the skills folder of your assistant: .claude/skills/ for Claude Code, .agents/skills/ for Codex, in the project or under your home folder:

mkdir -p .claude/skills/cv4pve-report
curl -fL -o .claude/skills/cv4pve-report/SKILL.md https://raw.githubusercontent.com/Corsinvest/cv4pve-report/master/skills/cv4pve-report/SKILL.md

Give it a token of its own

The skill tells the assistant what to do; the token decides what it can do. The assistant can read the token and call the Proxmox VE API without cv4pve-report, and the skill cannot prevent that. Give it a read-only token (PVEAuditor, see Permissions) and put the connection in an options file, so the token stays out of the conversation.