BF proxmox-dc-lifecycle
Rebuild, replace, demote, reinstall, rejoin, or re-promote a Windows Active Directory domain controller VM on Proxmox: demote it, clean metadata from a healthy DC, reinstall via autounattend, then promote it again. Use for Proxmox-hosted DC rebuild requests and symptoms that point to rebuild: NTDS will not start, ntds.dit is missing, promotion fails with trust-relationship or "no computer account" errors, demotion hangs, dcdiag/replication fails on one DC, or a broken DC VM needs to come back. Also use for Windows AD operations through QEMU guest agent (qm guest exec). Rule: do not corrupt Active Directory; verify replication and FSMO before and after every lifecycle step, change one DC at a time, and never destroy or recreate a VM while AD still has NTDS Settings for that DC.
Rebuild, replace, demote, reinstall, rejoin, or re-promote a Windows Active Directory domain controller VM on Proxmox: demote it, clean metadata from a…
As a process F 35/100 · Will not run — References files that are not bundled: assets/autounattend.xml.template
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- The text references files that are not there: add them or drop the references.
- 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 · 5
-
high Dangerous commands
cmd-persistencereferences/demotion.md:44Persistence mechanism (cron / launchd / scheduled task / autorun registry)$taskPw | schtasks /create /tn HDC_Demote /ru "<DOMAIN>\Administrator" /rp * /rl HIGHEST `
Medium and low: 4
-
medium Dangerous commands
cmd-persistencereferences/gotchas.md:23Persistence mechanism (cron / launchd / scheduled task / autorun registry) (quoted — discussed, not commanded)- **Fix (demote):** run the cmdlet via a **scheduled task whose run-as principal is the domain admin** (`schtasks /create /ru ... /rp *`, password via stdin), so it executes in a true logon session. (
quoted -
medium Dangerous commands
cmd-persistencereferences/gotchas.md:68Persistence mechanism (cron / launchd / scheduled task / autorun registry) (detector / deny-list definition)- **Signature:** `schtasks /create /ru <DOMAIN>\Administrator /rp * ...` errors "The trust relationship between this workstation and the primary domain failed."
detector -
low Dangerous commands
cmd-execpolicy-bypassreferences/demotion.md:45Runs PowerShell with execution policy bypassed (quoted — discussed, not commanded)/sc ONCE /st 00:00 /tr "powershell -NoProfile -ExecutionPolicy Bypass -File C:\Windows\Temp\.hdc\run.ps1" /f
quoted -
low Dangerous commands
cmd-persistencereferences/gotchas.md:65Persistence mechanism (cron / launchd / scheduled task / autorun registry) (negated — the text forbids it)- **Fix:** detach with a **classic scheduled task** (`schtasks /create /sc ONCE /st <future> ; schtasks /run`) — it's owned by the task scheduler, not your QGA call — or run a single **long synchronou
negated
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: assets/autounattend.xml.template
Process rating: all ten parameters 35/100
- 0Tools and files. 1 referenced file(s) missing: assets/autounattend.xml.template
- 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. 9 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 85Steps. 29 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3039 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (9 tags): a typed call is more reliable
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)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 787: enough signal without eating the budget
- +4Structure: 14 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (8 of 8)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.