SKILLEMALL.ai
GitHub ↗ RU Sign in

BD trtllm-visualgen-bench

Benchmark a TensorRT-LLM VisualGen model end to end, server included — pick the workload, bring up the `trtllm-serve` server it needs (resolve the checkpoint, write the config, launch, verify it came up as configured) or use one already running, then run and read the result. Use when the user asks to benchmark or serve a VisualGen model, or asks for a model's request YAML or its default generation params.

NVIDIA/TensorRT-LLM Claude Code author: NVIDIA 28 files · 5 scripts body ≈ 2 186 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Benchmark a TensorRT-LLM VisualGen model end to end, server included — pick the workload, bring up the trtllm-serve server it needs (resolve the checkpoint…

As a process D 49/100 · Unfinished process — weak spots: result and completion, inputs and preconditions, failures and branches

AnalyzerAI 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
B
93/100
safety, quality, tests
Safety 60%
97
Quality 40%
88
Run on models
none yet
Process rating
D
49/100
Unfinished process
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

How to improve

    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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • low Dangerous commands cmd-background-process serve/README.md:149
      Starts a background / autostarted process
      setsid trtllm-serve <checkpoint> --host 0.0.0.0 --port $PORT --visual_gen_args $CFG \
    • low Dangerous commands cmd-background-process serve/README.md:156
      Starts a background / autostarted process (quoted — discussed, not commanded)
      `setsid` is what step D needs: it makes the server lead its own process group, so
      quoted
    • low Dangerous commands cmd-background-process serve/README.md:190
      Starts a background / autostarted process (detector / deny-list definition)
      `kill $SERVER_PID` leaves the `spawn` workers holding GPUs and the port, and `pgrep -f trtllm-serve` does not match them. Signal the group the `setsid` in step C created, which is the server and its w
      detector

    Files scanned: 25. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 49/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 6 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
    • 70When it triggers. States when to use, but not when not to
    • 100Steps. 5 steps
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 2186 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)
    • +3Output format is not stated: the model decides each time
    • +2Single-language instructions
    • +3Description length 408: enough signal without eating the budget
    • +4Structure: 8 headings
    • +3Step-by-step instructions: 5 items
    • +4Has examples (6 code blocks)
    • +3All 2 scripts are documented
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.