Browse reusable Agent Skills, each with a clear purpose and practical guidance.
Use to understand and prepare for the Econometric Theory (ET) review process — single-anonymous refereeing (reviewers see the author), the Article/Miscellanea/ET-Interview article types, and war-gaming the proof-checking referee before submitting.
Use when deciding whether a result is the right kind of contribution for Econometric Theory (ET) — a general, foundational econometric-theory result (asymptotics, proofs, theorems) rather than an applied estimate, and whether it fits a full Article or a short Miscellanea.
Use when designing or auditing The Econometrics Journal (EctJ) Monte Carlo simulations, empirical applications, estimator comparisons, robustness checks, computation, seeds, and applied-value evidence.
Use when positioning a The Econometrics Journal (EctJ) paper against econometric theory, applied econometrics, statistics, and machine-learning literatures while keeping the leading-case contribution compact under the roughly 20-page RES format, including the frontier-versus-use citation split.
Use when positioning an EDBT submission against the data-management literature across SIGMOD, VLDB/PVLDB, ICDE, EDBT, the co-located ICDT, and the database journals (VLDBJ, TODS, TKDE), writing delta-first contrast rather than a citation catalog, and handling the 12-month EDBT resubmission ban, preprints, and prior-version overlap.
Use when reasoning about how an EDBT research submission is evaluated, covering Microsoft CMT reviewing, the author-feedback phase, the accept / revise / reject decision, the in-cycle revise-and-resubmit second read by the original reviewers, the cycle-to-conference roll, and how EDBT's rolling model differs from SIGMOD/VLDB/ICDE and the co-located ICDT.
Use when the empirical causal-identification argument is the bottleneck for a European Economic Review (EER) manuscript — DiD/event-study, IV, RDD, or experiment. Stress-tests the design to EER's general-interest credibility bar before exhibits are finalized; it does not build the theory model or the robustness battery.
Use when designing or auditing the experimental program of an EMNLP paper — baseline fairness and tuning budgets, dataset and language coverage matched to claims, contamination audits for pretrained and API models, significance testing and seed variance, human evaluation protocols, prompt sensitivity, and the error analysis EMNLP reviewers expect.
Use when positioning an EMNLP submission inside NLP's fast-moving literature — covering ACL Anthology lineages and arXiv concurrency, citing Findings and workshop papers correctly, tracing dataset and benchmark ancestry, verifying every reference resolves under the hallucinated-citation policy, and keeping self-citation double-blind.
Use when hardening an EMNLP paper's reproducibility record — answering the Responsible NLP checklist truthfully under desk-reject enforcement, pinning model versions and API snapshot dates, logging decoding parameters and prompts, documenting data licensing and annotation, and reporting compute so another lab could rerun the study.