Agent skill · research science · personamanagmentlayer
research-expert
Expert-level research methodology, academic writing, statistical analysis, and scientific investigation. Use when the user mentions methodology, statistics, academic writing, or experimental design, or when the task involves Research Design, Statistical Analysis, or Data Analysis.
Why this skill is useful
Includes executable scripts for sample size calculation and experimental design randomization that extend the AI's capabilities in research methodology.
What it needs
Requires numpy, scipy, statsmodels installed locally. About 4k tokens when loaded. Last updated 2026-03-30. 41 stars on the source repository.
What this skill does
Research Methodology Expert Expert guidance for research methodology, experimental design, statistical analysis, and academic writing. Core Concepts Research Design Experimental vs observational studies Randomized controlled trials (RCTs) Cross-sectional, longitudinal, cohort studies Case-control studies Systematic reviews and meta-analysis Sample size determination Statistical Analysis Descriptive statistics Hypothesis testing Confidence intervals Regression analysis ANOVA and t-tests Non-parametric tests Multiple testing correction Academic Writing Literature review Research proposals Manuscript structure (IMR AD) Citation management Peer review process Publishing ethics Experimental Design Statistical Analysis Literature Review Best Practices Research Design Pre-register studies when possible Calculate adequate sample sizes Use appropriate controls Randomize when applicable Blind assessors to reduce bias Consider confounding variables Document protocol deviations Data Analysis Pre-specify analysis plan Check statistical assumptions Report effect sizes, not just p-values Apply multiple testing corrections Use appropriate statistical tests Report confidence intervals Make data and code available Academic Writing Follow journal guidelines Use clear, precise language Report methodology in detail Discuss limitations openly Acknowledge conflicts of interest Properly cite all sources Use reference management software Anti-Patterns ❌ P-hacking and data dredging ❌ HARKing (Hypothesizing After Results are Known) ❌ Cherry-picking results ❌ Inadequate sample sizes ❌ Ignoring failed experiments ❌ No pre-registration ❌ Selective reporting of outcomes Resources ClinicalTrials.gov: https://clinicaltrials.gov/ CONSORT Statement: http://www.consort-statement.org/ Cochrane Handbook: https://training.cochrane.org/handbook APA Style: https://apastyle.apa.org/ StatsModels: https://www.statsmodels.org/
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills personamanagmentlayer/research-expert