BC perf-analyze
Launch and operate this repo's perf-analyze workflow, which DIAGNOSES a TensorRT-LLM serving deployment without applying changes — benchmark at one concurrency or a Pareto curve of them (tok/s/user vs tok/s/gpu), analytical SOL projection on by default (via the internal-perf-sol-analysis skill), nsys + ncu per-kernel deep dive (via the perf-nsight-compute-analysis skill), and a report naming the single dominant bottleneck. Use when the user wants to analyze / profile / diagnose trtllm-serve performance (throughput, TTFT, TPOT, ITL, e2e latency) or says "run perf-analyze". To actually APPLY optimizations, use the perf-optimize workflow instead.
This skill launches a built-in workflow to diagnose TensorRT-LLM serving performance without applying changes. Promises benchmarking at single or multiple concurrency levels, theoretical throughput ceiling (SOL) calculation, kernel profiling via nsys and ncu, and a report identifying the dominant bottleneck.
One instruction file with 3325 tokens, no critical bugs or broken references. Code quality scores 85/100, process score 61/100—suggests complex logic that holds together. No model runs or sandbox execution on record. The skill is diagnostic only; to actually optimize, you'd use perf-optimize instead.
Worth installing if you're profiling TRTLLM and want a quick path from metrics to root cause without manual digging.
Launch and operate this repo's perf-analyze workflow, which DIAGNOSES a TensorRT-LLM serving deployment without applying changes — benchmark at one…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, running it twice
How to improve
- 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: 1. 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 61/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 3 mutating operations with no state check
- 60Tools and files. Uses tools (python, node) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 24 steps
- 100Failures and branches. 4 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3325 tokens
- 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 (3 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 651: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 85.