Use when packaging AAAI code, data, multimedia appendices, technical appendices, reproducibility evidence, and post-acceptance artifact releases without violating double-blind or immutable-supplement rules.
日本語の概要は準備中です。原文の説明を表示しています。
Use when deciding which aejmac-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for an American Economic Journal: Macroeconomics (AEJ: Macro) submission. Routes — it does not replace — the specialized skills.
インストールする前に、エージェントに与えられる指示の中身を確認できます。
This is the router. It tells you which aejmac- skill to use at the current stage* of a manuscript aimed at the American Economic Journal: Macroeconomics (AEJ: Macro) — the American Economic Association's quarterly, broad-interest macro journal (founded 2009; one of four AEJs). AEJ: Macro rewards papers that bring quantitative discipline and policy relevance to a substantive macro question across growth, business cycles, monetary and fiscal policy, labor-macro, international macro, and macro-finance.
The defining feature of AEJ: Macro is methodological breadth: it publishes both quantitative-theoretical work (DSGE, heterogeneous-agent, structural estimation, calibrated models) and identified-empirical work (SVAR, local projections, narrative identification, micro-data macro). A paper does not have to be one or the other — the bar is that whichever tool you use, the mapping from model/data to the macro conclusion is disciplined.
Default assumption: unless the user says otherwise, treat the target as AEJ: Macro. Operational tells that you are at AEJ: Macro and not a field-macro or general-interest sibling: submission via the AEA submission system; a membership-scaled submission fee (member/nonmember × income tier; 检索于 2026-06,以官网为准); single-blind external review managed by the editor/coeditors; JEL codes required; the AEA Data Editor (Lars Vilhuber) runs a pre-publication reproducibility check — covering simulation and calibration code, not only regression scripts — with materials deposited at the AEA Data and Code Repository on openICPSR. Editor as of 2026: Ayşegül Şahin (检索于 2026-06;以官网为准). Re-verify volatile specifics on the official AEA pages.
| Current symptom | Next skill |
|---|---|
| Question feels narrow / field-macro / not broad-interest | aejmac-topic-selection |
| Contribution vs. the macro frontier is fuzzy or undersold | aejmac-literature-positioning |
| Empirical identification (SVAR / LP / narrative / IV) is shaky | aejmac-identification |
| A quantitative model needs calibration / estimation discipline | aejmac-theory-model |
| Headline number not shown robust to specification / sample / tuning | aejmac-robustness |
| Exhibits are dense; IRFs/fan charts/fit plots unclear | aejmac-tables-figures |
| Prose buries the question; abstract/intro do not land | aejmac-writing-style |
| Data/code/simulation deposit, README, or AEA Data Editor prep | aejmac-replication-package |
| Want to anticipate referee objections / desk-reject odds | aejmac-referee-strategy |
| Ready to submit via the AEA system; need a preflight | aejmac-submission |
| Received an R&R; need a response-letter strategy | aejmac-rebuttal |
aejmac-topic-selection — lock the broad-interest macro questionaejmac-literature-positioning — stake the contribution vs. the macro frontieraejmac-identification — SVAR / LP / narrative / IV credibility (empirical branch)aejmac-theory-model — calibration / structural-estimation discipline (quantitative branch)aejmac-robustness — show the headline number is not fragileaejmac-tables-figures — IRFs, fan charts, model-fit exhibits done rightaejmac-writing-style — make the idea land (abstract + intro last; ≤100-word abstract)aejmac-replication-package — assemble the AEA-compliant data/code/simulation packageaejmac-referee-strategy — pre-empt the objections macro referees raiseaejmac-submission — AEA system preflightaejmac-rebuttal — after the R&R
aejmac-identificationandaejmac-theory-modelare siblings, not a strict order: an empirical paper leans on the former, a quantitative paper on the latter, and a hybrid paper visits both.aejmac-writing-styleis a late-stage polish; do not rewrite the intro before the headline number settles.
aejmac-replication-package until acceptance — the AEA Data Editor verifies before publication, and for macro this includes simulation/calibration code, not just data cleaningaejmac-tables-figures polish IRFs while the identification or calibration is still movingAEJ: Macro spans several macro branches, and the bottleneck differs by branch. Read the archetype, then enter the chain at the right link.
| Archetype | Likely first bottleneck | Enter at |
|---|---|---|
| empirical shock-identification (monetary/fiscal) | SVAR / narrative / proxy-VAR credibility | aejmac-identification |
| dynamic-effects estimation | local-projection specification + inference | aejmac-identification → aejmac-robustness |
| quantitative DSGE / HANK | calibration targets + parameter identification | aejmac-theory-model |
| structural estimation | what data moments identify each parameter | aejmac-theory-model → aejmac-robustness |
| model + evidence hybrid | does the model match the identified empirical response | aejmac-identification + aejmac-theory-model |
A user says: "My HANK model matches the data, but a referee says my monetary-shock series is not credibly exogenous and the consumption response is not robust to the lag length." That is two distinct AEJ: Macro pushbacks — identification of the shock (owned by aejmac-identification, narrative/high-frequency branch) and fragility of the dynamic response (owned by aejmac-robustness). The model side (aejmac-theory-model) only matters once the empirical target it is matched to is credible. Route to identification first; once the shock and the response settle (say the peak MPC-driven consumption response stabilizes at 1.4%, 90% CI [0.9, 1.9], illustrative), return to aejmac-tables-figures and aejmac-rebuttal.
if decision_letter_arrived: -> aejmac-rebuttal
elif ready_to_submit: -> aejmac-submission
elif anticipating_referees: -> aejmac-referee-strategy
elif data_code_deposit: -> aejmac-replication-package
elif exhibits_unclear: -> aejmac-tables-figures
elif headline_fragile: -> aejmac-robustness
elif model_calibration_estimation: -> aejmac-theory-model
elif shock_or_design_shaky: -> aejmac-identification
elif claim_or_positioning_fuzzy: -> aejmac-literature-positioning
else: -> aejmac-topic-selection
まだレビューはありません。使ってみた感想をお寄せください。
概要と使いどころ
Use when packaging AAAI code, data, multimedia appendices, technical appendices, reproducibility evidence, and post-acceptance artifact releases without violating double-blind or immutable-supplement rules.
日本語の概要は準備中です。原文の説明を表示しています。
Use when drafting an AAAI author response (rebuttal) under the single short character-limited author-feedback window, the no-URL rule, no-new-results guidance, AI-generated-review handling, and the AAAI two-phase review process where Phase-2 papers receive one feedback round before SPC/AC discussion.
日本語の概要は準備中です。原文の説明を表示しています。
Use when preparing an accepted AAAI paper for camera-ready source submission to AAAI Press, including proceedings page limits, two-column template compliance, copyright transfer, purchased extra technical pages, deanonymization, registration, oral or poster presentation, and final public artifact release.
日本語の概要は準備中です。原文の説明を表示しています。
Use when designing or auditing AAAI experiments for the broad-AI program committee, including baselines, ablations, statistical significance, robustness, human evaluation, AI-for-Social-Impact and alignment/safety evidence, compute and cost reporting, and reproducibility-checklist alignment for Phase-1 survival.
日本語の概要は準備中です。原文の説明を表示しています。
Use when positioning an AAAI paper's novelty against archival work, contemporaneous arXiv or workshop papers, and AAAI/IJCAI/NeurIPS/ICML/ICLR neighbors across the broad AI scope, while staying inside AAAI's dual-submission and AI-as-source policy constraints and writing a related-work section legible to non-specialist reviewers.
日本語の概要は準備中です。原文の説明を表示しています。
Use when strengthening an AAAI paper's reproducibility checklist (placed after references), experimental traceability, seed and hyperparameter reporting, compute and cost disclosure, dataset access and licensing, code/data ZIP readiness, and the claim-to-evidence map that Phase-1 reviewers use to judge rigor across AAAI's broad AI scope.
日本語の概要は準備中です。原文の説明を表示しています。