BB rocm_vllm_deployment
Production-ready vLLM deployment on AMD ROCm GPUs. Combines environment auto-check, model parameter detection, Docker Compose deployment, health verification, and functional testing with comprehensive logging and security best practices.
As a process B 70/100 · Nearly there — weak spots: when it triggers, consistency
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
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 Dangerous commands
cmd-shell-rcSKILL.md:243Writes to a shell startup file (documentation of a security skill)echo "Please add to ~/.bash_profile:"
security skill -
low Dangerous commands
cmd-shell-rcSKILL.md:245Writes to a shell startup file (documentation of a security skill)echo "Then run: source ~/.bash_profile"
security skill
Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens) - warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - note
frontmatter-keyunknown frontmatter key "timeout" - note
frontmatter-keyunknown frontmatter key "platform"
Process rating: all ten parameters 70/100
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (rocm_vllm_deployment) differs from the folder (rocm-vllm-deployment)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 67 steps
- 100Failures and branches. 2 branches, has a failure section
- 100Execution cost. Instruction body is 3585 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (11 tags): a typed call is more reliable
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)
- +1No license
- +2Single-language instructions
- +3Description length 237: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 67 items
- +3Output format is stated explicitly
- +4Has examples (17 code blocks)
- +3All 2 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.
External checks
ClawHub: suspicious
This deployment skill is coherent, but it exposes parts of Hugging Face tokens and stores sensitive deployment details in local reports, so it needs review before use.
LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026