Use when the main empirical results exist but the manuscript lacks the robustness, heterogeneity, mechanism, and placebo checks that AER referees will demand. Apply after aer-identification and before aer-introduction so that the value-added paragraph can reference these tests.
SkillScore95Maintained
Automatic
◆Research pack
Last verified 8/8/2026
What it changes
Passed 21 of 22 test cases with the skill, and 17 of 22 without it.
Without skill77%
With skill95%
Checks it passed that the model alone missed
Rejects placing the data appendix as Appendix A
Appendix outline places the data appendix as the final section
Output includes the handoff block with the exact key ROBUSTNESS COVERAGE
and 6 more in the full report
4 fixed17 passed either way1 still failing0 broke
Pass-rate lift
+18 pp
Tokens
+67%
Agent turns
0%
Response time
-8%
Model gemini-3.6-flashMeasured 8/8/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
I am preparing the empirical appendix and robustness checks for a top-tier economics manuscript on credit access and small business growth. The main OLS and difference-in-differences tables are finished, but I need to structure the supplementary validation strategy to satisfy standard referee expectations before submitting to a journal like AER. Please outline a complete referee-anticipating empirical strategy covering sensitivity checks, subgroup analysis, channel testing, and placebo designs. Include a structured outline for ordering the appendix sections and end with the standardized handoff status block detailing robustness coverage, heterogeneity type, mechanism evidence, placebos, pre-empted referee concerns, and next skill.
What was checked, without and with the skill
Checked
Without skill
With skill
Appendix outline places the data appendix as the final section
Missed
Passed
Mechanism strategy explicitly includes ruling out alternative explanations
Missed
Passed
Output includes the handoff block with the exact key NEXT SKILL
Passed
Passed
case-01 · gemini-3.6-flash · 8/8/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md173 lines2 files
AER Robustness
Overview
A modern AER referee report contains three predictable demands:
Robustness — does the result survive specification changes?
Heterogeneity — where does the effect concentrate, and is that consistent with the proposed channel?
Mechanism — why does X cause Y?
This skill anticipates all three so that the referee finds the answer already in the paper. Skipping this step turns a referee report into a 6-month delay.
When to Use
The main result table exists but the rest of the empirical section is thin
An R&R demands "additional checks" without specifying which
Drafting the appendix before submission
Diagnosing why a prior submission drew a "needs more robustness" rejection
The Referee-Anticipating Battery
Every empirical AER paper should report, at minimum:
Robustness
Alternative specifications — drop covariates one at a time; include fixed effects at finer/coarser granularity; weight observations differently
Alternative samples — drop the largest unit; drop the most influential time period; restrict to balanced panel; restrict to comparable subsets
Alternative outcome definitions — log vs. level; winsorized at 1% / 5%; alternative deflators
Alternative clustering — cluster at the next-higher level (e.g., state if main is county); two-way cluster; wild cluster bootstrap if few clusters
Alternative estimators — if main is OLS, show IV; if main is TWFE, show Callaway-Sant'Anna; if main is RD, show donut and bandwidth grid