Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Topic Selection & Venue Fit (aeja-topic-selection) · brycewang-stanford | DecimalAI

researchby brycewang-stanford

Topic Selection & Venue Fit (aeja-topic-selection)

brycewang-stanford/aeja-topic-selection

Source brycewang-stanford/awesome-journal-skills ↗License MIT

Use when deciding whether an applied-micro project belongs at the American Economic Journal: Applied Economics (AEJ: Applied) rather than AER, AEJ: Economic Policy, or a field journal, and what its central question should be. Sets venue fit and question scope; it does not design the identification (see aeja-identification).

SkillScore95Maintained

Automatic

Research pack

Last verified 8/15/2026

What it changes

Passed 21 of 22 test cases with the skill, and 10 of 22 without it.

Without skill45%

With skill95%

Checks it passed that the model alone missed

The response must place AEJ: Applied as the main venue fit.
The response must place AEJ: Applied as the core venue verdict.
The response must identify AEJ: Applied as the core venue match.

and 17 more in the full report

12 fixed9 passed either way0 still failing1 broke

Pass-rate lift: +50 pp
Tokens: +11%
Agent turns: 0%
Response time: -37%

Model gemini-3.6-flashMeasured 8/15/2026v121 of 22 cases passed with skill

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-aeja-topic-selection/SKILL.md https://app.decimal.ai/s/brycewang-stanford-aeja-topic-selection/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add brycewang-stanford-aeja-topic-selection, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/brycewang-stanford-aeja-topic-selection/ and pins it in .decimal/skills.lock

decimalai skills add brycewang-stanford-aeja-topic-selection

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-aeja-topic-selection/SKILL.md https://app.decimal.ai/s/brycewang-stanford-aeja-topic-selection/SKILL.md

Raw file: /s/brycewang-stanford-aeja-topic-selection/SKILL.md ↗ · machine-readable summary at /s/brycewang-stanford-aeja-topic-selection.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 12 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 12

Prompt

I am working on an empirical project studying how top marginal tax rate cuts affect firm-level R&D investments using a shift-share instrument across states. I need to sharpen the pitch and determine the right journal target. Please return a topic analysis containing a concise one-sentence question naming the population and estimand, a venue recommendation evaluating AEJ: Applied relative to AER, AEJ: Policy, and field journals, two additional economic subfields likely to cite this work, an expected headline finding sentence with specific magnitude/units, the candidate identification seed, initial JEL codes, and the next suggested step.

What was checked, without and with the skill
Checked	Without skill	With skill
The response must state a research question identifying state tax cuts as the intervention.	Missed	Passed
The response must evaluate AEJ: Applied relative to AER and field journals.	Passed	Passed
The response must identify literature positioning as the next workflow step.	Missed	Passed

case-03 · 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.md75 linessingle file

Topic Selection & Venue Fit (aeja-topic-selection)

When to trigger

A project is empirically promising but you are unsure it is "AEJ: Applied-shaped"
The question reads like a policy evaluation, a field-specialist note, or a top-general-interest swing — and you need to place it
Several possible framings of the same dataset exist and you must pick the one that lands here
Reviewers (or a co-author) say "this is fine but why this journal?"

The AEJ: Applied fit test

AEJ: Applied wants empirical applied microeconomics where a credible causal research design answers a substantive economic question of broad applied-micro interest — above a pure field journal but more specialized than AER. Use this decision table to place the project.

Signal in your project	Likely fit
Clean identification + a question labor/dev/health/ed/public economists all care about	AEJ: Applied (core)
Same design but the contribution is mainly a policy verdict / program ROI framing	lean AEJ: Economic Policy
Genuinely general-interest, agenda-setting, methodologically ambitious, long	aim AER first
Contribution is field-internal (only sub-field specialists will cite it)	a field journal (JHE / JOLE / JDE)
New estimator with a toy application	Econometrica / REStud / JoE, not AEJ: Applied

AEJ: Applied is empirical-first: theory appears to interpret and discipline the estimate, not to lead. A descriptive or measurement paper can fit if the question is sharp and the measurement is the contribution — but it must not overclaim causality.

Sharpening the question (do this before writing anything)

One-sentence question with the causal object named: "What is the effect of X on Y for population P, identified by design D?"
Why broad applied-micro readers care — name two subfields beyond your own that should cite it.
What the headline number will be (a magnitude with units, even if approximate) — if you cannot imagine the sentence "we find X raises Y by ___," the question is not yet AEJ: Applied-shaped.
The credible-design seed — which design (RCT / DID / RD / IV / shift-share) makes the estimate believable; if none, the topic is not ready (route to aeja-identification).

Checklist

One-sentence causal (or sharply descriptive) question with a named estimand
Venue placed against the table above; reason it is AEJ: Applied and not AER / AEJ: Policy / a field journal written in one line
Two subfields beyond your own that will cite it, named
An imaginable headline sentence with a magnitude and units
A candidate research design that could make the estimate credible
JEL codes drafted (required at submission) reflecting the cross-field appeal

Anti-patterns

Track record

Benchmark

21 / 22

test cases passed, vs 10 / 22 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

brycewang-stanford / awesome-journal-skills

AEJ-Applied-Economics-Skills/skills/aeja-topic-selection/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Other skills for the same job

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.

Ready to supercharge your AI agents?

See it in action

What's inside

Topic Selection & Venue Fit (aeja-topic-selection)

When to trigger

The AEJ: Applied fit test

Sharpening the question (do this before writing anything)

Checklist

Anti-patterns

Track record

Benchmark

Adoption

SkillSafety

Source

Other skills for the same job

Related skills