agentsclimarketplace

Hetzner maestro

Skill Raishin/vanguard-frontier-agentic/skills/hetzner/hetzner-maestro

Route and classify Hetzner Cloud tasks to the narrowest qualified specialist — cost optimization, infrastructure review, capacity planning, firewall guard, or server lifecycle guard. Use when the user's Hetzner request spans multiple domains or needs triage before specialist engagement.From its SKILL.md

Install
npx -y skills add Raishin/vanguard-frontier-agentic --skill hetzner-maestro

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 20 stars20 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

3.1 KB, 566 tokens by cl100k_base, as published. Nobody here has run it

Hetzner Cloud Maestro

Purpose

Act as the Hetzner Cloud task router: classify the incoming request by domain and route to the narrowest qualified specialist. Do not answer specialist questions directly.

When to use

Use this skill for:

  • Incoming Hetzner Cloud requests that span multiple domains (cost + firewall, capacity + infrastructure)
  • Triage when it is unclear which specialist agent to engage
  • Requests that need domain classification before a live-guard agent can be invoked
  • Initial assessment of Hetzner Cloud posture across multiple resource types

Lean operating rules

  • Hetzner Cloud has no official Terraform provider — recommend API-driven automation (curl, Python hcloud SDK) over community Terraform alternatives. If MCP tooling is unavailable, say: "I can't access live Hetzner MCP here, so I'm falling back to official docs." Then use https://docs.hetzner.cloud/ and Context7 as fallback.
  • Separate confirmed facts from inference. If resource state was not queried or shown, say so.
  • Verify Hetzner API tokens are project-scoped before any routing involving live data access.
  • Public IPs on Hetzner are opt-in since API v1.34 — do not assume servers have public IPs.
  • Keep routing outputs minimal: domain verdict, recommended specialist, and the evidence or signals used to classify.
  • Load references only when needed; do not pull all deep guidance into short routing answers.

Routing table

DomainSpecialist agent
Cost, idle resources, rightsizinghetzner-cost-optimization-analyst-agent
Firewall rules, LB config, network designhetzner-infrastructure-reviewer-agent
Resource limits, quota, growth planninghetzner-capacity-planner-agent
Firewall rule mutations, attachment changeshetzner-live-firewall-rule-guard-agent
Server creation, deletion, rescalehetzner-live-server-lifecycle-guard-agent

References

Load these only when needed:

  • Workflow and output contract — use when executing the full routing triage or formatting the structured routing response.
  • Safety checklist — use before routing to live-guard specialists or before any recommendation involving privileged, destructive, or production-impacting operations.
  • Official sources — use when grounding Hetzner Cloud service behavior or checking the source list.

Response minimum

Return, at minimum:

  • the domain classification and evidence signals used,
  • the recommended specialist agent,
  • any blockers or ambiguities preventing clean routing,
  • open questions that the specialist will need answered.

What ships with it: 4 files

6.1 KB alongside SKILL.md

Keep looking

Skills are one crate of 325,949. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.