BD perf-host-optimization
Profiles and optimizes TensorRT-LLM host/CPU overhead using line_profiler (with nsys support planned). Runs iterative profile-analyze-optimize-validate rounds. Use when GPU utilization is low or optimizing PyExecutor throughput.
This skill profiles CPU overhead in TensorRT-LLM using line_profiler and reserves space for nsys integration. Promises iterative cycles: profile → analyze → optimize → validate. Targets low GPU utilization or PyExecutor throughput bottlenecks.
Contains 13 files, but half the references point nowhere—documentation is incomplete. Never ran on actual models, sandbox unavailable. Grade B reflects decent code quality (83%) but weak process maturity (40%). No critical bugs, but logic gaps remain.
Install if you're willing to debug and actually face GPU starvation. Otherwise, wait for the next iteration.
Profiles and optimizes TensorRT-LLM host/CPU overhead using lineprofiler (with nsys support planned).
As a process D 40/100 · Unfinished process — References files that are not bundled: ../perf-host-analysis/references/trtllm-nvtx-ranges.md
How to improve
- 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: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../perf-host-analysis/references/trtllm-nvtx-ranges.md
Process rating: all ten parameters 40/100
- 0Tools and files. 1 referenced file(s) missing: ../perf-host-analysis/references/trtllm-nvtx-ranges.md
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 85Steps. 61 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3497 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low The response is described with custom markup (4 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
- +2Single-language instructions
- +3Description length 228: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 61 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (6 of 6)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 83.