BC proxmox-ops
Ops-focused Proxmox VE management via REST API — monitor, control, provision, and troubleshoot VMs and LXC containers with battle-tested operational patterns. Use when asked to: - List, start, stop, restart VMs or LXC containers - Check node status, cluster health, or resource usage - Create, clone, or delete VMs and containers - Manage snapshots, backups, storage, or templates - Resize disks (API + in-guest filesystem steps) - Query guest agent for IP addresses - View tasks or system event logs Includes helper script (pve.sh) with auto node discovery from VMID, operational safety gates (read-only vs reversible vs destructive), vmstate snapshot warnings, post-resize guest filesystem steps, and a separate provisioning reference. Requires: curl, jq. Credentials: PROXMOX_HOST, PROXMOX_TOKEN_ID, PROXMOX_TOKEN_SECRET — set as env vars or stored in ~/.proxmox-credentials (sourced at runtime, user-created, mode 600). Writes: ~/.proxmox-credentials (user-created, API token, mode 600). Network: connects to user-configured Proxmox host only (HTTPS, TLS verification disabled for self-signed certs). Helper script: scripts/pve.sh (relative to this skill) Configuration: ~/.proxmox-credentials
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- Shorten the description to 1024 characters.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1202 chars, limit 1024
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 13 mutating operations with no state check
- 60Tools and files. Uses tools (web, node) that frontmatter does not declare
- 100Steps. 24 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1871 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1201: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 17 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (11 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 63.