SKILLEMALL.ai
GitHub ↗ RU Sign in

CC trtllm-serve-config-guide

Generate a source-backed starting `trtllm-serve --config` YAML for basic aggregate single-node PyTorch serving, aligned with checked-in TensorRT-LLM configs and deployment docs. Preserves explicit latency / balanced / throughput objectives. Excludes disaggregated, multi-node, and non-MTP speculative configs.

The skillemall take

Generates starter YAML for trtllm-serve single-node PyTorch serving, aligns with TensorRT-LLM configs, supports latency/balanced/throughput modes. Two files, no scripts. Quality 64%, process 50%, safety 100%. Critical issue: broken_references_missing_files flag is true—generated YAML may reference nonexistent paths or configs. No high-severity findings, but no guarantee it runs without edits.

Install if you'll validate paths in output before deployment. Production use requires manual config check.

NVIDIA/TensorRT-LLM Agent Skills author: NVIDIA NOASSERTION 2 files body ≈ 1 211 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Generate a source-backed starting trtllm-serve --config YAML for basic aggregate single-node PyTorch serving, aligned with checked-in TensorRT-LLM configs and…

As a process C 50/100 · Has gaps — References files that are not bundled: examples/llm-api/, examples/configs/, examples/configs/database/lookup.yaml

GeneratorInfrastructureAI and agentstype and topics are labelled automatically from the skill text
Runs in: 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) OpenClaw Goose OpenCode
JSON
Technical rating
C
86/100
safety, quality, tests
Safety 60%
100
Quality 40%
64
Run on models
none yet
Process rating
C
50/100
Has gaps
References files that are not bundled: examples/llm-api/, examples/configs/, examples/configs/database/lookup.yaml
Tools and files w 18
0
Inputs and preconditions w 11
0
Progress reporting w 2
0
the three weakest of ten parameters · all ten

How to improve

  1. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
  2. The text references files that are not there: add them or drop the references.
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 · 0

✓ No critical or high findings

Files scanned: 2. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")
  • warning missing-ref reference to a missing file: examples/llm-api/
  • warning missing-ref reference to a missing file: examples/configs/
  • warning missing-ref reference to a missing file: examples/configs/database/lookup.yaml
  • warning missing-ref reference to a missing file: examples/configs/curated/lookup.yaml
  • warning missing-ref reference to a missing file: examples/models/core/
  • warning missing-ref reference to a missing file: examples/models/core/deepseek_v3/README.md
  • note edit-residue the text marks something as outdated (lines 51): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 50/100

Will not run. References files that are not bundled: examples/llm-api/, examples/configs/, examples/configs/database/lookup.yaml
  • 0Tools and files. 6 referenced file(s) missing: examples/llm-api/, examples/configs/, examples/configs/database/lookup.yaml
  • 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
  • 50When it triggers. No condition that starts the skill
  • 55Failures and branches. 1 branches
  • 60Result and completion. Output format stated, no completion criterion
  • 100Steps. 13 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1211 tokens

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)
  • +4No input/output examples
  • +2Single-language instructions
  • +3Description length 309: enough signal without eating the budget
  • +4Structure: 9 headings
  • +3Step-by-step instructions: 13 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (1 of 1)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 64.