Use when prose buries the result or the abstract/intro do not land for an American Economic Journal: Microeconomics (AEJ: Micro) manuscript. Applies AEA house style and the theory-paper intro arc; it does not produce the result (see aejmic-theory-model) or build exhibits (see aejmic-tables-figures).
SkillScore91Maintained
Automatic
◆Writing & Editing pack
Last verified 8/15/2026
What it changes
Passed 20 of 22 test cases with the skill, and 6 of 22 without it.
Without skill27%
With skill91%
Checks it passed that the model alone missed
Output includes bracketed tag 【Abstract】.
Output includes bracketed tag 【House style】.
Output includes bracketed tag 【Contribution】.
and 20 more in the full report
16 fixed4 passed either way0 still failing2 broke
Pass-rate lift
+64 pp
Tokens
+27%
Agent turns
0%
Response time
-30%
Model gemini-3.6-flashMeasured 8/15/2026v120 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 16 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 16
Prompt
In my empirical appendix tables, I reported p-values using dagger and star symbols († p<0.10, * p<0.05). Should I keep these for AEJ: Micro submission?
What was checked, without and with the skill
Checked
Without skill
With skill
Prohibits using dagger or asterisk symbols for significance in tables.
Missed
Passed
Directs reporting standard errors or coverage sets.
Passed
Passed
case-19 · gemini-3.6-flash · 8/15/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md67 linessingle file
Writing Style & the AEJ: Micro Intro Arc (aejmic-writing-style)
When to trigger
The introduction opens with machinery (the model's notation, an estimator) instead of the question
A reader cannot state your main result after the first page
The abstract describes activities ("we study…") rather than the result
Late-stage polish before submission (do this after the model and proofs settle)
The AEJ: Micro intro arc
A theory-first AEA journal rewards an introduction that makes a broad micro audience see the question and the result fast. The arc:
question / puzzle → model + equilibrium concept (in words) → main result (a proposition, stated in words) → what drives it / which assumption is doing the work → contribution & scope → brief roadmap.
Open with the economic question, not the model. A non-specialist should grasp what is being asked in the first breath.
State the result in words on page one — the proposition's content, not its proof. "We show that X, and this happens because Y."
Name the driving force early (which assumption / mechanism delivers the result) — this is the AEJ: Micro reader's payoff and ties to aejmic-identification.
Frame the contribution as a result with scope, including what it does not establish.
The literature delta belongs here in one or two sentences (full treatment in aejmic-literature-positioning), not a survey.
AEA house-style conventions
Abstract: short and result-bearing; lead with the result, not the activity. (Confirm the current word limit on the AEA author page — volatile; 检索于 2026-06，以官网为准.)
JEL codes and keywords required.
Statistical presentation: for any empirical/experimental content, report standard errors / confidence sets, not significance asterisks.
Notation discipline: define on first use; consistent throughout; avoid clutter.
Proofs: key proofs self-contained in the paper (main text or appendix), not exiled to supplementary files.
Single-blind note: AEJ: Micro review is single-blind (the referee sees the author), so the manuscript need not be anonymized — but acknowledgments and self-citations should still read professionally, not promotionally.
Checklist
Intro opens with the economic question, not the model/estimator
Main result stated in words on page one, with its driving force named
Contribution framed as a result with explicit scope ("we do not show…")
Abstract leads with the result; JEL codes + keywords present
No significance asterisks anywhere; SEs / coverage sets where relevant
Notation defined at first use and consistent
Self-citations and acknowledgments read professionally (single-blind: no anonymization needed)
Use when revising an American Economic Review: Insights (AER: Insights) short-format manuscript to lead with the result, fit the hard word cap (7,000 words minus 200 per exhibit), and write the ≤100-word abstract. Enforces the length budget and the lead-with-the-result arc; it does not change the analysis.