SKILLEMALL.ai

BF vllm

Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor parallelism, KV cache), OpenAI-compatible API serving, throughput and latency benchmarking, continuous batching tuning, GPU operation, and upgrade/rollback. Use when deploying or running a vLLM server (vllm serve, vllm/vllm-openai), sizing a model and its KV cache for GPUs, selecting quantization and parallelism, serving via /v1 endpoints, measuring serving throughput or latency, tuning batching, or diagnosing GPU, OOM, or startup failures in a vLLM deployment. Do not use for model training, fine-tuning, evaluation-set design, or engine-selection methodology (that is ml-engineering), or for operating the llama.cpp stack with GGUF models (that is llama-cpp); other inference engines (TGI, Ollama, Triton) are out of scope.

magnus919/agent-skills Agent Skills author: magnus919 MIT 13 files · 1 script body ≈ 3 785 tokens Open the sourcegithub.com↗ analyzed 27 h ago

Operate, configure, benchmark, and troubleshoot vLLM inference servers: Docker and Kubernetes deployment, quantization-aware model configuration (tensor…

As a process F 48/100 · Will not run — References files that are not bundled: ../ml-engineering/SKILL.md, ../llama-cpp/SKILL.md, ../kubernetes/SKILL.md

IntegrationDockerKubernetesInfrastructureAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
B
90/100
safety, quality, tests
Safety 60%
100
Quality 40%
76
Run on models
none yet
Process rating
F
48/100
Will not run
References files that are not bundled: ../ml-engineering/SKILL.md, ../llama-cpp/SKILL.md, ../kubernetes/SKILL.md
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. The text references files that are not there: add them or drop the references.
For the model run — optional
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 0

✓ No critical or high findings

Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning missing-ref reference to a missing file: ../ml-engineering/SKILL.md
  • warning missing-ref reference to a missing file: ../llama-cpp/SKILL.md
  • warning missing-ref reference to a missing file: ../kubernetes/SKILL.md
  • warning missing-ref reference to a missing file: ../docker-compose/SKILL.md
  • warning missing-ref reference to a missing file: ../platform-engineering/SKILL.md
  • warning missing-ref reference to a missing file: scripts/vllm-health

Process rating: all ten parameters 48/100

Will not run. References files that are not bundled: ../ml-engineering/SKILL.md, ../llama-cpp/SKILL.md, ../kubernetes/SKILL.md
  • 0Tools and files. 6 referenced file(s) missing: ../ml-engineering/SKILL.md, ../llama-cpp/SKILL.md, ../kubernetes/SKILL.md
  • 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. 19 mutating operations with no state check
  • 50When it triggers. No condition that starts the skill
  • 100Steps. 49 steps
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3785 tokens
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 15 top-level sections: this looks like several domains in one skill
  • low The skill ranks results itself: that belongs to the system behind the tool, not the model
  • medium 6 test cases, all positive: not one "should refuse" or "should ask first"
  • low No test case covers injection arriving through data

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
  • +3Description length 882: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -2localhost URLs: will not work for another user
  • +2Single-language instructions
  • +4Description says when NOT to use the skill
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 49 items
  • +4Has examples (1 code blocks)
  • +4Reference files are cited in the instructions (7 of 7)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.