CD trtllm-test-specialist
Runs model-level and module-level tests for TensorRT-LLM. First classifies the test scope (module test or model test), then dispatches to the appropriate workflow. Model tests are further classified by type (functionality/smoke test, benchmark, or evaluation). Prompts the user for parallelism parameters (tp, ep, dp), dataset paths, device type, or a config file as needed. All test execution is delegated to trtllm-case-executor.
Runs tests for TensorRT-LLM by classifying them (module or model type), then routes to the right workflow. Prompts for parallelism settings, dataset paths, device type, or a config file. Delegates actual execution elsewhere.
Files present but untested on models and no sandbox run. Quality score sits at 60. Broken references or missing files confirmed. No critical issues flagged, though process score of 46 signals underlying problems. Install if you're testing TensorRT-LLM locally and willing to verify the dispatcher works yourself. Skip if you need something production-ready.
Runs model-level and module-level tests for TensorRT-LLM.
As a process D 46/100 · Unfinished process — References files that are not bundled: examples/disaggregated/slurm/benchmark/config.yaml
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: 12. 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 ≈ 8989 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: examples/disaggregated/slurm/benchmark/config.yaml
Process rating: all ten parameters 46/100
- 0Tools and files. 1 referenced file(s) missing: examples/disaggregated/slurm/benchmark/config.yaml
- 0Result and completion. Does not say what the result is
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 40Execution cost. Instruction body is 8989 tokens: crowds the task out of the window
- 70Inputs and preconditions. Inputs and preconditions are listed
- 85Steps. 75 steps, 3 vague phrases
- 100Failures and branches. 5 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- low 12 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (20 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 431: enough signal without eating the budget
- +4Structure: 41 headings
- +3Step-by-step instructions: 75 items
- +4Has examples (14 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 5 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.