scdenney

Design cross-national survey experiments: power, equivalence, localization.

Design and format publication-quality figures: chart choice, color, scales, legends, captions, reproducibility.

Build or audit a literature review: evidence map, gaps, synthesis plan.

Design survey instruments: questions, scales, flow, social desirability.

Draft a senior peer-review report on a social-science manuscript.

LLM-based text classification: codebook, validation, agreement statistics.

VLM-based OCR pipeline: model selection, prompts, architecture, evaluation.

Design and diagnose list experiments (item count technique).

Scaffold or audit a social-science replication package at a target directory. Generates folder structure, README, master.R, figure/table crosswalk, codebook template, LICENSE placeholder, and pre-release checklist. Adapted from Yusaku Horiuchi's replication-package-guide with FAIR-principle integration; platform-neutral (Harvard Dataverse, OSF, Zenodo, GitHub releases, institutional archives).

Design and format publication-quality tables: column order, row grouping, notes, precision, reproducibility.

Structural topic modeling: STM spec, topic count, coherence-exclusivity.

Design conjoint experiments: attributes, power, AMCE/AMIE estimation.

Audit in-text/reference parity, DOIs, claim support, and citation style.

Clean and reshape Qualtrics conjoint exports to analysis-ready long format.

Diagnose conjoint design integrity, estimation choices, and validity.

Audit manuscript and replication package against FAIR open-science principles.

Audit figures, tables, captions, cross-references, and statistical notes.

Build falsifiable causal hypotheses: DAGs, FPCI, equivalence testing.

Check methods reporting against CONSORT, JARS, DA-RT standards.

Draft scientific introductions: argument logic, framing, multi-experiment coherence.

Pre-submission audit: argument, numerics, refs, writing, figures, replication.

Run the standalone presubmit CLI: adversarial 30+ stage peer-review pipeline.

Cross-model adversarial pre-submission audit. Claude and Codex independently apply the paper-review-lite specification, then each cross-checks the other's findings; surviving issues are annotated by confidence.

Clean post-OCR text: correction, QA, multilingual handling, provenance.

Write pre-analysis plans: PAP structure, registry, analysis strategy.