hetzner-cloud

Solid

Read and operate Hetzner Cloud servers, server types, locations, networks, volumes, snapshots, and cost estimates through gateway-proxied API requests.

AI & Automation 126 stars 11 forks Updated today MIT

Install

View on GitHub

Quality Score: 85/100

Stars 20%
70
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
50
License 10%
100
Description 5%
100

Skill Content

# Hetzner Cloud Use this skill for Hetzner Cloud VPS inventory, provisioning, network and volume inspection, cost estimates, and snapshot lifecycle work. ## Default Workflow 1. Start read-only: list servers, locations, server types, images, prices, volumes, and networks. 2. Use `plan` for natural-language requests before building any write request. 3. Treat `hetzner_cloud.cjs` as the API wrapper. Do not handcraft Hetzner Cloud API URLs, JSON bodies, tiers, or secret refs from memory. 4. For prompt/user testing, stop after `plan` or after helper `http-request` payload generation. Do not call helper `run` or the built-in `http_request` tool. 5. For real user requests that need live Hetzner API data, use helper `run`. The helper constructs the request, sends it through the HybridClaw gateway, and the gateway injects `bearerSecretName: "HETZNER_API_TOKEN"` server-side. Do not rewrite that secret reference into `secretHeaders`, preflight it, inspect it, or ask the model for the token. 6. Use `http-request` only when you need to inspect the generated gateway payload or when the active runtime cannot give the helper gateway access. 7. If a live helper `run` or `http_request` call returns 401 or 403, stop after that first failure. Do not retry, do not fan out to more endpoints, and ask the operator to set or verify `HETZNER_API_TOKEN`. 8. Require an explicit operator grant before any changing action, including delete, upgrade, downgrade, buy/...

Details

Author
HybridAIOne
Repository
HybridAIOne/hybridclaw
Created
5 months ago
Last Updated
today
Language
TypeScript
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category