Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use when results may be sensitive — to specification, sample, measurement, or inference for quantitative work, or to interpretation and triangulation for qualitative work — in a World Development (WD) manuscript. Organizes checks by threat; it does not invent evidence or citations.
Use when deciding whether a development question fits World Development (WD) and which sibling journal it really belongs to. Tests scope, relevance, and outlet fit; it does not invent evidence or citations.
Use when executing and reporting the analysis for a World Politics manuscript so it survives expert triple-blind review and the Dataverse replication requirement — honest uncertainty, robustness, and triangulation appropriate to comparative cross-national, qualitative, or formal-empirical work. Guides analysis norms; it does not fabricate results.
Use when defending the research design of a World Politics manuscript — comparative-historical and case selection, quantitative cross-national identification, qualitative process tracing, experiments, or formal-empirical linkage for cross-case questions. World Politics expects explicit research design and appropriate methods, judged on each tradition's own terms. Strengthens the design; it does not write code.
Use when deciding whether a project fits World Politics and whether it should be a research article or a review article. World Politics is a comparative-politics + international-relations specialist, so the test is a substantive question that travels across cases or systems — not subfield novelty, and not a single-case description. Helps frame the question; it does not collect data.
Use when positioning a paper against prior literature for WSDM - locating the work inside WSDM's own research lineages (click models, unbiased LTR, sequential recommendation, community detection), contrasting against SIGIR/KDD/WWW/CIKM/RecSys neighbors, venue-misattribution traps, and compressing the section for the tight page budget.
Use when hardening the reproducibility of a WSDM paper built on logs, graphs, or user-interaction data - provenance of behavioral datasets, temporal split discipline, click-bias assumptions, seed and variance reporting, privacy-preserving release, and honesty tiers for results no outsider can rerun.
Use when reasoning about how WSDM reviews and decides papers - the hybrid single/double-blind architecture with Associate-Chair metadata visibility, at-least-three PC reviews plus senior PC assessment, the absence of a rebuttal phase, the August-to-October window, and what ~17% selectivity at a single-track venue implies.
Use when deciding whether a project belongs at WSDM or a neighbor - tests for the web/social-data core and the practical-yet-principled bar, scope coverage from web search and recommendation to social networks and responsible web AI, routing against SIGIR, KDD, WWW, CIKM, RecSys, and ICWSM, and long-versus-short-track fit.
Use when verifying that a The Yale Law Journal (YLJ) claim is genuinely novel and not preempted by prior scholarship. It runs the systematic SSRN/Westlaw/HeinOnline search and writes the "what's new" paragraph; it does not draft the thesis (use ylj-thesis-and-contribution).