Diagnose a Proxmox VE cluster with an AI assistant

An AI assistant that can run shell commands can use cv4pve-diag to check a Proxmox VE cluster and explain what it finds: it runs the analysis with JSON output, reads the code, severity and resource of each finding, and looks up the code in the Checks pages to tell you what is wrong, why it matters and how to fix it.

The cv4pve-diag skill

The repository ships a skill, skills/cv4pve-diag/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 the findings, not the exit code, which is 0 even with Critical findings;
• look for WC0020 and WG0042 before calling an area clean, and leave fixes and ignore rules to you.

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

npx skills add Corsinvest/cv4pve-diag

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-diag
curl -fL -o .claude/skills/cv4pve-diag/SKILL.md https://raw.githubusercontent.com/Corsinvest/cv4pve-diag/master/skills/cv4pve-diag/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-diag, 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.