SKILLEMALL.ai
GitHub ↗ RU Sign in

AB perf-nsight-systems

Nsight Systems (nsys) CLI for system-level timeline profiling. Use when the user wants to run nsys profile, analyze .nsys-rep reports, use nsys stats/analyze/recipe commands, diagnose GPU idle time from timeline traces, or profile distributed training with NCCL overlap analysis. NOT for kernel-level metrics like SOL%, occupancy, or roofline (use perf-nsight-compute-analysis for ncu). NOT for writing or generating kernels. NOT for applying optimizations like CUDA Graphs.

The skillemall take

This skill wraps Nsight Systems CLI for system-level profiling. Promises to run nsys profile, parse .nsys-rep reports, analyze GPU idle time from timeline traces, and catch NCCL overlap in distributed training. Explicitly skips kernel metrics (SOL%, occupancy) — that's a separate skill.

Eight files, no lint errors. Quality score 96, process score 77 means the spec is solid but commands might need clarification. No critical findings. Sourced from official TensorRT-LLM, runs on all major platforms. Install if you're profiling GPU load at system level, not individual kernels.

NVIDIA/TensorRT-LLM Agent Skills author: NVIDIA NOASSERTION 8 files body ≈ 3 513 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Nsight Systems (nsys) CLI for system-level timeline profiling.

As a process B 77/100 · Nearly there — weak spots: progress reporting

IntegrationData and analyticsWriting and documentsInfrastructuretype 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
A
98/100
safety, quality, tests
Safety 60%
100
Quality 40%
96
Run on models
none yet
Process rating
B
77/100
Nearly there
Progress reporting w 2
0
Failures and branches w 10
50
Tools and files w 18
60
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 · 0

    ✓ No critical or high findings

    Files scanned: 8. 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 77/100

    • 0Progress reporting. Says nothing while it works
    • 50Failures and branches. 0 branches, has a failure section
    • 60Tools and files. Uses tools (bash, web, python, node) that frontmatter does not declare
    • 60Result and completion. Output format stated, no completion criterion
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 100Steps. 21 steps
    • 100When it triggers. States when to use and when not to
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3513 tokens
    • 100Running it twice. Mutating operations check current state

    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
    • +2Single-language instructions
    • +4Description says when NOT to use the skill
    • +3Description length 474: enough signal without eating the budget
    • +4Structure: 21 headings
    • +3Step-by-step instructions: 21 items
    • +3Output format is stated explicitly
    • +4Has examples (19 code blocks)
    • +4Reference files are cited in the instructions (7 of 7)
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 96.