Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/aejpol-referee-strategy
Use when anticipating how AEJ: Economic Policy referees and editors will read a manuscript, before submission or before an R&R, to pre-empt the objections that sink policy-evaluation papers. Maps likely pushback to fixes and calibrates expectations; it does not write the response letter (see aejpol-rebuttal) or fix the identification.
Passed 19 of 22 test cases with the skill, and 11 of 22 without it.
and 8 more in the full report
9 fixed10 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 9 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am finalizing an empirical manuscript on municipal minimum wage increases across US counties and want to anticipate referee critiques before submitting to AEJ: Policy. Please conduct a referee strategy assessment for this paper. The review should cover: 1) a verdict on whether this meets the broad policy interest threshold, 2) the most critical identification objection along with a main-text pre-emption plan, 3) an analysis of whether our welfare claim is derived or hand-waved with fixes, 4) a structured objection-to-exhibit mapping, 5) a list categorizing what needs fixing now versus what should be bounded and disclosed, and 6) the recommended next step.
| Checked | Without skill | With skill |
|---|---|---|
| Includes the section header 【Broad-interest verdict】. | Missed | Passed |
| Includes the section header 【Top identification objection】. | Missed | Passed |
| References aejpol-submission in the next step line. | Missed | Passed |
The instructions your model reads when the skill loads.
AEJ: Policy reviews are single-blind through the AEA system (referees see the authors; authors do not see referees), refereed by economists who expect both credible causal evidence and a policy-relevant welfare reading. A referee typically tests four things in order; a paper dies at the first one it fails:
aejpol-topic-selection test) — a clean estimate with no policy lever or welfare reading invites a "better suited to a field journal / AEJ: Applied" rejection.aejpol-identification test) — staggered TWFE, asserted parallel trends, a weak instrument, or an over-generalized RDD are the usual kill shots.aejpol-theory-model test) — a hand-waved "this is welfare-improving" or a sufficient-statistic formula whose assumptions are violated.aejpol-robustness / aejpol-replication-package tests).| Likely referee objection | Pre-emption to build before submitting |
|---|---|
| "This isn't a policy paper / not broad-interest" | Lead with the policy question + welfare stake; state the cost-benefit reading in the abstract |
| "Staggered TWFE is biased here" | Heterogeneity-robust DID + Bacon decomposition + flat leads, in the main paper |
| "Parallel trends is assumed, not shown" | Event-study leads + honest-DID bounds |
| "Exclusion restriction is not credible" | Institutional + theoretical defense + falsification |
| "The welfare claim is hand-waved" | Explicit sufficient-statistic / MVPF / cost-benefit derivation |
| "External validity is unclear" | Heterogeneity by setting; explicit scope of the policy lesson |
| "Effect is significant but tiny / not policy-relevant" | Benchmark the magnitude against budget / status quo |
| "Not reproducible / data unavailable" | AEA-compliant package + restricted-data access path ready |
test cases passed, vs 11 / 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.