Explorar skills

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

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

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

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).

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

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.

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

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

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

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

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

Esta skill deve ser utilizada para validar especificações, documentos de design ou arquitetura, especialmente quando o usuário solicita testes, identificação de lacunas ou um 'stress-test' antes da implementação.