Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when choosing or sharpening a research question for a Journal of Accounting Research (JAR) manuscript — testing whether it is a real accounting question with a credible setting, JAR fit, and identification potential before any data work begins. Locks the question; it does not build the mechanism (jar-theory-development) or design the test (jar-methods).
Use when building the Monte Carlo evidence and the substantive empirical application for a Journal of Business & Economic Statistics (JBES) methods paper. Designs and audits the simulation study and the real-data analysis; it does not derive the asymptotic theory (see jbes-identification-strategy).
Use when the methodological core of a Journal of Business & Economic Statistics (JBES) paper is the bottleneck — assumptions, regularity conditions, asymptotic theory, and Monte Carlo design for a new estimator, test, or algorithm. Stress-tests the method's validity, not a causal design.
Use when positioning a Journal of Business & Economic Statistics (JBES) methods paper against prior econometric and statistical methods. Stakes what is new relative to the existing toolkit; it does not write a standalone literature survey.
Use when deciding whether a project fits the Journal of Business & Economic Statistics (JBES) — the methods-with-empirics fit test. Checks methodological novelty plus clear empirical relevance before time is sunk; it does not develop the method itself.
Use when stress-testing the empirical identification strategy for a Journal of Banking & Finance manuscript, including bank panels, policy shocks, event studies, IV, staggered DID, dynamic panels, and endogeneity threats.
Use when running and reporting the analysis for a Journal of Business Venturing (JBV) manuscript — choosing estimators that fit entrepreneurial data (survival/event-history, selection models, panels, experiments, qualitative trustworthiness), handling attrition and endogenous founding, and reporting robustness. Executes and reports the analysis; it does not design the study (jbv-methods) or frame the contribution (jbv-contribution-framing).
Use when designing or defending the research design for a Journal of Business Venturing (JBV) manuscript — matching a methodologically pluralistic but theory-first approach (venture panels, experiments, qualitative process work, mixed methods) to an entrepreneurial question, and handling selection, survival, and novel-dataset issues. Designs the study; it does not estimate it (jbv-data-analysis) or frame the contribution (jbv-contribution-framing).
Use when understanding how the Journal of Business Venturing (JBV) review process works — Co-EIC / area-editor routing, double-anonymized review by a minimum of two reviewers, desk-reject risk for off-phenomenon work, and reading a JBV decision letter. Explains the process and reads the letter; the response is drafted with jbv-rebuttal.
在为《计算机辅助设计与图形学学报》(Journal of Computer-Aided Design & Computer Graphics, JCAD&CG) 设计与呈现实验证据时调用。覆盖图形学/CAD 论文特有的证据：几何精度指标(Chamfer/Hausdorff)、渲染质量(PSNR/SSIM/LPIPS)、可视化有效性与用户研究、公平基线与相同预算对比、消融、时间与显存开销、渲染图与几何误差色图呈现、以及主客观评测与统计口径。适用于把方法主张与图形/几何证据一一绑定、避免"只有指标无视觉对比"或"基线不公平"在外审被质疑的场景。