메뉴
Route psychology statistics requests to the smallest Pingouin workflow. Use when the user asks what analysis to run, gives a psychology design, asks to analyze data with Pingouin, or needs lower-token guidance before code generation.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Screen psychology datasets before Pingouin analysis: variable types, missingness, duplicates, long/wide shape, assumption checks, and safer preprocessing.
Run or generate Pingouin code for multivariate comparisons — Hotelling's T-squared test (multivariate_ttest) — plus the multivariate assumption checks box_m (equal covariance) and multivariate_normality, for designs with several dependent variables.
Compute or generate Pingouin Bayes factors for t tests, correlations, and proportions (bayesfactor_ttest, bayesfactor_pearson, bayesfactor_binom), and read the BF10 already returned by pg.ttest and pg.corr.
Run or generate Pingouin code for categorical / contingency-table analyses — chi-square test of independence, McNemar's paired test, 2x2 crosstabs, and chi-square power — for psychology data with nominal variables.
Run or generate Pingouin code for rank-based non-parametric tests — Mann-Whitney U, Wilcoxon signed-rank, Kruskal-Wallis, Friedman, and Cochran Q — when outcomes are ordinal or parametric assumptions fail.
Review and approve Pingouin psychology analyses before final reporting. Use after data screening or statistical output and before interpretation to catch common problems: wrong test, ignored repeated measures, missing assumption checks, multiple-comparison errors, unsupported causal claims, incomplete reporting, or output-format mismatches.
| name | pingouin-stat-router |
| description | Route psychology statistics requests to the smallest Pingouin workflow. Use when the user asks what analysis to run, gives a psychology design, asks to analyze data with Pingouin, or needs lower-token guidance before code generation. |
Compatibility entry point. For end-to-end work, prefer pingouin-stat (adds intake, approval, and deliverable planning around routing).
Use this skill first when the requested statistical analysis is unclear or broad.
Read only these references unless another skill requires more:
../../references/workflow-index.md../../references/supervision-gates.md../../references/pingouin-api-quickref.md only when generating concrete code.../../references/apa-output-template.md only if the user asks for report text or formatted output.Select the smallest downstream skill and analysis plan that fits the study design. Do not run a statistical test until the design, variables, and data shape are clear enough to avoid an obvious wrong test.
Resolve from the user's text or data before choosing the test:
If these cannot be inferred, ask the minimum necessary clarifying question. If a reasonable default is safe, state it explicitly.
pg-data-screening.pg-mean-tests.pg-anova.pg-correlations.pg-regression-mediation.pg-nonparametric.pg-categorical.pg-multivariate.pg-bayesian.pg-reliability.pg-power.pg-reporting.Return this compact block:
Recommended: <skill> using <function(s)>.
Why: <design-to-test mapping>.
Need: <columns/data shape/missing item>.
Guardrail: <one highest-risk assumption or correction>.
Next: <code / run screening / one clarifying question>.
Audit: <S0-S5 compact gate status>.
pairwise_tests, not deprecated pairwise_ttests.alternative="two-sided" unless the user gives a directional hypothesis.