AB vmware-vdi
Use this skill whenever the user needs to operate a VMware/Omnissa Horizon VDI environment via its Connection Server: list and manage desktop pools, RDS farms and published apps, inspect and act on user sessions (log off, disconnect, send message), manage desktop machines (reset, maintenance, remove), view and change entitlements, read Horizon events/health/statistics, and push instant-clone golden images. Always use this skill for "log off VDI user", "reset this desktop", "why is the desktop pool not provisioning", "push the new image to the pool", "list Horizon sessions", "who is entitled to the pool", "VDI health" — when the context is explicitly Horizon / Omnissa / VDI / desktop-pool / RDS-farm. Do NOT use for the underlying vCenter VM lifecycle/power/snapshot/migrate (use vmware-aiops), read-only vSphere monitoring (use vmware-monitor), or NSX microsegmentation (use vmware-nsx-security). This skill manages the Horizon broker layer; vmware-aiops manages the vCenter VMs backing the desktops.
Use this skill whenever the user needs to operate a VMware/Omnissa Horizon VDI environment via its Connection Server: list and manage desktop pools, RDS farms…
As a process B 67/100 · Nearly there — weak spots: result and completion, inputs and preconditions, running it twice
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- 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
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "installer"
Process rating: all ten parameters 67/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 11 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 13 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2669 tokens
- 100Progress reporting. Reports progress
- low 11 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
- +3Description length 1009: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 7 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 12 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (5 code blocks)
- +4Reference files are cited in the instructions (2 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.