statistical-rigor — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited statistical-rigor (Agent Skill) and scored it 96/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 1 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Audit every statistical claim in a manuscript for methodological soundness, correct test selection, and proper reporting.
rigorous stat-check path/to/paper.texrigorous stat-check path/to/analysis.py --type codeUse the rigorous.stat_check tool with parameters:
file: path to manuscript or analysis codetype: paper or codeLINE 198 FAIL "p < 0.05" -- report exact p-value (e.g., p = 0.032)
LINE 204 WARN t-test used but no normality check reported
LINE 215 FAIL 12 comparisons with no multiple-comparison correction
LINE 220 WARN No effect size reported for ANOVA result
LINE 231 PASS Cohen's d = 0.82 reported with 95% CI [0.41, 1.23]0 -- all statistical claims sound1 -- warnings (missing but non-critical information)2 -- failures (incorrect tests, missing corrections)~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.