SKILLEMALL.ai

AB nvidia-cuda

Use when work targets NVIDIA GPUs for deep learning training, inference, distributed execution, CUDA/Triton kernels, or AI infra tuning. Enforces GPU-aware code conventions for PyTorch on CUDA, including dtype policy, memory movement, NCCL/DDP/FSDP choices, profiling, benchmarking, and H100/H200/B200 optimization habits.

ClawHub Agent Skills author: 刘旭凯 v0.4.0 MIT-0 22 files body ≈ 5 688 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, progress reporting

ReferenceInfrastructureSoftware developmentPersonal productivitytype and topics are labelled automatically from the skill text
JSON
Technical rating
A
92/100
safety, quality, tests
Safety 60%
100
Quality 40%
80
Run on models
none yet
Process rating
B
70/100
Nearly there
Inputs and preconditions w 11
0
Progress reporting w 2
0
When it triggers w 12
50
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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: 22. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5688 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 70/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Progress reporting. Says nothing while it works
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (python, node) that frontmatter does not declare
  • 70Execution cost. Instruction body is 5688 tokens
  • 85Steps. 307 steps, 1 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 14 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • low 21 top-level sections: this looks like several domains in one skill

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)
  • +4No input/output examples
  • +1No license
  • +2Single-language instructions
  • +3Description length 322: enough signal without eating the budget
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 307 items
  • +3Output format is stated explicitly
  • +4Reference files are cited in the instructions (2 of 3)
  • +3All 7 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 80.

External checks

ClawHub: clean
This is a coherent NVIDIA CUDA optimization skill with local diagnostic scripts and no evidence of hidden data access, persistence, exfiltration, or destructive behavior.
LLM: benign (high) · VirusTotal: · 29 May 2026