SKILLEMALL.ai
GitHub ↗ RU Sign in

AC vmctl-ops

Use when vmctl is already installed and the agent must immediately run safe post-install checks and first lifecycle actions without guessing.

ClawHub Hermes author: bashrusakh v1.0.2 MIT-0 3 files body ≈ 1 126 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process C 63/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, progress reporting

ProcedureInfrastructureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
98
Quality 40%
82
Run on models
none yet
Process rating
C
63/100
Has gaps
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
20
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Risky intent intent-offensive-security README.md:48
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - **No privilege escalation guidance** in skill commands.
  • low Risky intent intent-offensive-security SKILL.md:52
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use)
    - Run as plain `vmctl` CLI (no privilege escalation or forced user switching in this skill).

Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 141 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)

Process rating: all ten parameters 63/100

  • 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
  • 60Tools and files. Uses tools (bash) that frontmatter does not declare
  • 60Consistency. The Hermes dialect needs category and tags
  • 65Failures and branches. 3 branches
  • 100Steps. 44 steps
  • 100Result and completion. Output format and completion criterion are stated
  • 100Execution cost. Instruction body is 1126 tokens
  • 100Running it twice. Mutating operations check current state
  • low 14 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
  • +4Description does not say when NOT to use the skill (false activations)
  • +2Single-language instructions
  • +3Description length 141: enough signal without eating the budget
  • +4Structure: 15 headings
  • +3Step-by-step instructions: 44 items
  • +3Output format is stated explicitly
  • +4Has examples (7 code blocks)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.

External checks

ClawHub: clean
This is a transparent vmctl post-install validation playbook that can create and remove test VMs, so it should be used only in the intended test environment.
LLM: benign (high) · VirusTotal: · 29 May 2026