AB cpu-gpu-performance
Establishes CPU/GPU baselines before resource-intensive operations. Use before builds, training runs, or any task that pins cores or GPUs for over a minute
As a process B 75/100 · Nearly there — weak spots: inputs and preconditions, consistency
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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "source" - note
frontmatter-keyunknown frontmatter key "source_plugin"
Process rating: all ten parameters 75/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (cpu-gpu-performance) differs from the folder (nm-conserve-cpu-gpu-performance)
- 60Result and completion. Output format stated, no completion criterion
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Steps. 50 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 989 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- low 10 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 155: enough signal without eating the budget
- +4Structure: 11 headings
- +3Step-by-step instructions: 50 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.
External checks
ClawHub: clean
This skill is a resource-use checklist for checking CPU/GPU load before heavy work, with no hidden install steps or persistent behavior.
LLM: benign (high) · VirusTotal: · 26 Aug 2026