CC statistical-conventions
Chooses and reports statistical tests the way a careful referee expects, deciding paired versus unpaired and parametric versus rank-based from the design, using ordered-trend tests such as Jonckheere-Terpstra and Cochran-Armitage for dose or grade levels, correcting for multiple comparisons with Bonferroni, Holm or Benjamini-Hochberg and showing raw and adjusted p-values side by side, giving effect sizes such as Cohen's d, Cliff's delta and odds ratios with confidence intervals, bootstrapping intervals when no formula applies, and stating checked assumptions, exact p-values and degrees of freedom. Use whenever an analysis will report a p-value, a group difference, a trend across ordered categories or a correlation; use statistical-power for sample-size planning and experimental-design for laying out the study.
Chooses and reports statistical tests the way a careful referee expects, deciding paired versus unpaired and parametric versus rank-based from the design…
As a process C 61/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
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 · 1
✓ No critical or high findings
Medium and low: 1
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Read Bash python
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "summary" - note
frontmatter-keyunknown frontmatter key "role"
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
- 0Failures and branches. Linear process with no failure handling
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. Tools declared in frontmatter
- 100Steps. 38 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3220 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
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)
- +3Description length 821: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +2Single-language instructions
- +4Structure: 8 headings
- +3Step-by-step instructions: 38 items
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.