BB Hetzner
Runs Hetzner Cloud and Hetzner dedicated servers end to end: sizing, private networks, firewalls, volumes, backups, and the bill. Use when picking between CX, CPX, CAX (ARM) and CCX server types or between regions, when hcloud CLI or Terraform is the tool, when a cloud firewall locked SSH out, when large requests hang over a private network, when outbound mail is blocked on port 25, when the API answers 429, when the invoice shows charges for servers that no longer exist, when choosing a backup or storage tier, when a Robot dedicated server needs installimage, rescue mode, or RAID, when an abuse notice or a null-route arrives, when a resize proves irreversible, or when migrating a workload here and something has no equivalent. Covers EU data residency, VAT, and k3s. Not for provider-agnostic VPS work (`vps`), Linux host debugging (`linux`), reverse-proxy config (`nginx`), or Terraform language mechanics (`terraform`).
Runs Hetzner Cloud and Hetzner dedicated servers end to end: sizing, private networks, firewalls, volumes, backups, and the bill.
As a process B 79/100 · Nearly there — weak spots: inputs and preconditions, running it twice
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 1
✓ No critical or high findings
Medium and low: 1
-
low Risky intent
intent-offensive-securitystorage.md:71Offensive-security / dual-use content (legitimate for authorised testing; review intended use)2. The SSH key used for backups is restricted to append-only Borg operations on the server side, so a host that gets rooted **cannot delete or rewrite its own history** — the classic ransomware failur
Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
body-longSKILL.md body ≈ 7886 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "slug" - note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "changelog"
Process rating: all ten parameters 79/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 39 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 7886 tokens
- 100Tools and files. No external tools needed
- 100Steps. 41 steps
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
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
- +3Description length 931: 120–800 characters recommended
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +4Structure: 15 headings
- +3Step-by-step instructions: 41 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 66.