Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/aeja-workflow
Use when deciding which aeja-* sub-skill to invoke next, or when sequencing manuscript work from topic selection through rebuttal for an American Economic Journal: Applied Economics (AEJ: Applied) submission. Routes — it does not replace — the specialized skills.
Passed 21 of 22 test cases with the skill, and 8 of 22 without it.
and 10 more in the full report
13 fixed8 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
We have valid causal empirical estimates showing a 3.1 percentage point increase in employment, but we need a simple theoretical framework to structure the underlying economic mechanism and interpret our empirical findings. Which module should we turn to?
| Checked | Without skill | With skill |
|---|---|---|
| Route the user to aeja-theory-model. | Missed | Passed |
The instructions your model reads when the skill loads.
This is the router. It tells you which aeja- skill to use at the current stage* of a manuscript aimed at the American Economic Journal: Applied Economics (AEJ: Applied) — the American Economic Association's quarterly journal for empirical applied microeconomics with credible causal identification: labor, development, health, education, public, urban, environmental, and household finance. AEJ: Applied is empirical-first: a clean research design carrying a substantive economic question, with theory used to interpret and structure rather than to lead.
Default assumption: unless the user says otherwise, treat the target as AEJ: Applied. Operational tells that you are at AEJ: Applied and not a sibling: review is single-blind (author identities are visible to referees); submission is via the AEA ScholarOne system with fee tiers by AEA membership and country-income status; JEL codes and a 100-word abstract are required; and the signature stable differentiator is the AEA Data and Code Availability Policy — administered by the AEA Data Editor (Lars Vilhuber), accepted papers deposit data + code to the AEA Data and Code Repository on openICPSR, and the package is checked for reproducibility before publication. On 2026-06-20 the editor page listed Raymond Fisman (Boston University) as Editor, with coeditors Leah Boustan, Marika Cabral, Peter Hull, Xavier Jaravel, and Nicholas Ryan. Check live AEA pages for fees and editors before submission-week advice.
| Current symptom | Next skill |
|---|---|
| Unsure the paper fits AEJ: Applied vs AER / AEJ: Policy / a field journal | aeja-topic-selection |
| Contribution vs. the literature is fuzzy or undersold | aeja-literature-positioning |
| Causal design rests on OLS+controls, TWFE on staggered timing, or a weak IV | aeja-identification |
| A model is needed to interpret estimates or structure a mechanism | aeja-theory-model |
| Results not shown robust to specification, sample, inference | aeja-robustness |
| Exhibits are dense; main result not legible in one table/figure | aeja-tables-figures |
| Prose buries the design; abstract/intro do not land | aeja-writing-style |
| Data/code deposit, README, openICPSR prep for the AEA Data Editor | aeja-replication-package |
| Want to anticipate referee objections before submitting | aeja-referee-strategy |
| Ready to submit via the AEA portal; need a preflight | aeja-submission |
| Received an R&R; need a response-letter strategy | aeja-rebuttal |
aeja-topic-selection — lock the applied-micro question and venue fitaeja-literature-positioning — stake the marginal contributionaeja-identification — make the data-to-causal-estimate mapping credibleaeja-theory-model — add only the theory that interprets/structures the estimateaeja-robustness — show the headline survives specification, sample, inferenceaeja-tables-figures — make the main result legible in one exhibitaeja-writing-style — make the design and estimate land (abstract + intro last)test cases passed, vs 8 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.