SKILLEMALL.ai
GitHub ↗ RU Sign in

BC hostinger-mcp

Operational guide for managing Hostinger infrastructure — VPS, websites/hosting, domains, DNS, email marketing (Reach), and billing — via the official Hostinger MCP server (npm hostinger-api-mcp), across one or several Hostinger accounts. Use whenever the user mentions Hostinger, hPanel, a Hostinger VPS, a Hostinger-hosted site, Hostinger domains/DNS, domain purchase/transfer/lock, Hostinger email/Reach contacts, or Hostinger billing/subscriptions. Any write operation (create/update/delete/recreate a VPS, change firewall/DNS, purchase a domain or VPS, change a subscription or payment method, deploy/import a site) requires explicit confirmation of the target resource and intended action — and the cost, for money-spending operations — before execution.

ClawHub Agent Skills author: Ben Kalsky v1.2.1 MIT-0 5 files body ≈ 2 177 tokens Open the sourceclawhub.ai↗ analyzed 41 min ago

Operational guide for managing Hostinger infrastructure — VPS, websites/hosting, domains, DNS, email marketing (Reach), and billing — via the official…

As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice

IntegrationAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
B
85/100
safety, quality, tests
Safety 60%
83
Quality 40%
89
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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 · 17

    ✓ No critical or high findings

    Medium and low: 17
    • low Secrets in code secret-high-entropy-token references/installation.md:25
      High-entropy token-like string (may be an id, hash or a credential)
      sha5…0kf+yX0O…GcQ==
    • low Secrets in code secret-high-entropy-token references/installation.md:36
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
      EXPECTED='sha5…0kf+yX0O…GcQ=='
      detector
    • low Secrets in code secret-high-entropy-token references/tools-catalog.md:16
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | `VPS_…sV1` | R | Get detailed configuration for a single virtual machine. |
      table
    • low Secrets in code secret-high-entropy-token references/tools-catalog.md:36
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | `VPS_…eV1` | W! | 💸 Purchase and set up a new virtual machine (spends money). |
      table
    • low Secrets in code secret-high-entropy-token references/tools-catalog.md:37
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | `VPS_…eV1` | W | Configure and initialize a purchased VM in `initial` state. |
      table
    • low Secrets in code secret-high-entropy-token references/tools-catalog.md:38
      High-entropy token-like string (may be an id, hash or a credential) (documentation table row)
      | `VPS_…eV1` | W! | Recreate a VM from scratch — reinstalls OS, wipes data. |
      table
    • low Secrets in code secret-high-entropy-token references/tools-catalog.md:66
      High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition; documentation table row)
      | `VPS_…tV1` | W | Add a new post-install script to your account. |
      detectortable
    • low Secrets in code secret-high-entropy-token references/workflows-vps.md:24
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      1. `VPS_…sV1` — full config for a single VM (plan, OS template, hostname, nameservers, state).
      quoted
    • low Secrets in code secret-high-entropy-token references/workflows-vps.md:42
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      1. `VPS_…sV1` — confirm target and current state.
      quoted
    • low Secrets in code secret-high-entropy-token references/workflows-vps.md:48
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      4. **VERIFY:** `VPS_…sV1` (state) and `VPS_…sV1` (operation completed).
      quoted
    • low Secrets in code secret-high-entropy-token references/workflows-vps.md:71
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      3. **CONFIRM (W! + cost):** `VPS_…eV1` — confirm plan, term, COST, and account.
      quoted
    • low Secrets in code secret-high-entropy-token references/workflows-vps.md:72
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      4. After purchase the VM sits in `initial` state. **CONFIRM (W):** `VPS_…eV1` — apply template, hostname, password, SSH keys, optional post-install script.
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:50
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      3. **Money-spending operations require cost-confirmation.** `doma…nV1`, `VPS_…eV1`, enabling billing auto-renewal, and `bill…dV1` spe
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:52
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      4. **Destructive operations double-confirm (W!).** Any `*delete*` tool, `VPS_…eV1` (reinstalls the OS, **wipes all data**), and `DNS_…sV1` on production require confir
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:54
      High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
      5. **Multiple workloads per VPS.** A single VPS may host several sites/services. `VPS_…eV1`, `VPS_…eV1`, and `VPS_…eV1` affect **everything** on
      quoted
    • low Secrets in code secret-high-entropy-token SKILL.md:69
      High-entropy token-like string (may be an id, hash or a credential)
      Tool: VPS_…eV1
    • low Secrets in code secret-high-entropy-token SKILL.md:96
      High-entropy token-like string (may be an id, hash or a credential)
      mcp_…sV1

    Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    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
    • 30Running it twice. 3 mutating operations with no state check
    • 60Tools and files. Uses tools (bash) that frontmatter does not declare
    • 60Failures and branches. 2 branches
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 17 steps, 1 vague phrases
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2177 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)
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +3Description length 760: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 17 items
    • +4Has examples (3 code blocks)
    • +4Reference files are cited in the instructions (3 of 3)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 89.

    External checks

    ClawHub: clean
    This is a transparent Hostinger operations guide that handles powerful account access, but it discloses the risks and builds in user confirmation rules.
    LLM: benign (medium) · VirusTotal: · 13 Sept 2026