CD trtllm-case-executor
Run TensorRT-LLM test cases, benchmarks, evaluations, or custom scripts by checking the environment (local GPU or Slurm), selecting the appropriate Docker image, and executing either locally or via Slurm job submission. Accepts pre-built command strings — command construction for trtllm-bench, trtllm-eval, and test_perf_sanity is handled upstream by the caller (e.g. trtllm-test-specialist using build_test_command.py).
This skill runs TensorRT-LLM tests and benchmarks: checks GPU availability, picks a Docker image, and executes jobs locally or via Slurm. Commands arrive pre-built—the skill only executes them, not constructs them.
Two files, one script. Quality score of 56 out of 100 signals working but incomplete code: broken references and missing files. No critical bugs found, but a process score of 49 points to execution logic issues. The skill fits into a pipeline where another module (like trtllm-test-specialist) generates commands and this one runs them.
Install if you use TensorRT-LLM and accept that some features may need fixes. For standalone use—risky.
Run TensorRT-LLM test cases, benchmarks, evaluations, or custom scripts by checking the environment (local GPU or Slurm), selecting the appropriate Docker…
As a process D 49/100 · Unfinished process — References files that are not bundled: scripts/slurm_run_custom.sh
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- The text references files that are not there: add them or drop the references.
- 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-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 8488 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/slurm_run_custom.sh
Process rating: all ten parameters 49/100
- 0Tools and files. 1 referenced file(s) missing: scripts/slurm_run_custom.sh
- 0Result and completion. Does not say what the result is
- 40Execution cost. Instruction body is 8488 tokens: crowds the task out of the window
- 50When it triggers. No condition that starts the skill
- 60Steps. 41 steps, 5 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 3 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 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 The response is described with custom markup (26 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)
- +3Output format is not stated: the model decides each time
- -4Absolute local paths (C:\Users, /home/…): not portable
- +2Single-language instructions
- +3Description length 421: enough signal without eating the budget
- +4Structure: 21 headings
- +3Step-by-step instructions: 41 items
- +4Has examples (12 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 56.