Skip to main content
skill CX Codex

aer-referee-sim — Claude Code skill: mock AER referees before submission

aer-referee-sim runs a finished manuscript through a mock AER desk screen and three referees, then returns a verdict and a prioritized revise list.

no license ★ 240 updated 2026-09-18

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add franklee16/academic-research-skills --skill aer-referee-sim -a claude-code
Open on GitHub

What aer-referee-sim does

This skill stages the American Economic Review process on a finished draft. Stage one is the editor's quick pass: opening pages, main tables, bibliography. The editor only asks whether the paper deserves three referees' time, so the run checks whether the contribution fits in one sentence, whether an identification strategy is named early, and whether exhibits follow house style. A failed item in the desk audit ends the run with a rejection letter.

If the draft gets through, three referees read it separately. One attacks the identifying assumption and re-derives a magnitude from the tables; a second checks novelty against current working papers; a third, from another subfield, asks whether the first pages stand alone. Major comments must point at a page or table and say what evidence would settle them. The editor then scores the paper on a fixed rubric, issues a verdict and merges the comments into one revise list, blocking items first, each tagged with the skill that fixes it.

You need a complete draft with exhibits and bibliography, plus an aer-consistency run that reports all-pass. Feed it half a manuscript and the simulation simply reports the paper as unfinished, so the run goes to waste.

What it helps with

  • run a mock desk screen before sending the paper out
  • collect three independent referee reports with different priors
  • merge scattered comments into one ordered revise list
  • test after a real rejection whether the revision would survive the same reports
  • settle a coauthor dispute about whether the draft is ready

Example prompts for the agent

  • Run aer-referee-sim on paper/draft.tex: desk screen first, then the three reports.
  • Do the editor synthesis, score the rubric dimensions and give me the verdict with the revise list.
  • Rerun the simulation with harsher referee priors, the last verdict felt lenient.

How to install aer-referee-sim

1Skills CLI (Vercel)

npx skills add franklee16/academic-research-skills --skill aer-referee-sim -a claude-code

2Manually: put the files in place

~/.claude/skills/aer-referee-sim/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/aer-referee-sim/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about aer-referee-sim

How do I install aer-referee-sim in Claude Code?

Run npx skills add franklee16/academic-research-skills --skill aer-referee-sim -a claude-code; the skill then lives at ~/.claude/skills/aer-referee-sim/SKILL.md.

What does aer-referee-sim do?

It simulates the AER desk screen, writes three referee reports from different angles, and turns them into a verdict with rubric scores and a revise list.

Does it replace aer-consistency?

No. It expects a draft that already passed aer-consistency; hunting typos is not part of its job.

Similar skills

All skills for Science and research →

From the same set98

The whole set →
quality-checks-diagnosis quality-checks-diagnosis helps choose the right survey check and interpret failures. Use it when you need to distinguish inattention from unclear instructions or a weak experimental treatment. CX Codex +1 ★ 240repo stars avoid-leading-questions avoid-leading-questions reviews a draft survey question, names the bias behind it, and gives a concrete rewrite for each of the three cases it covers. CX Codex +1 ★ 240repo stars dril-dataset-construction dril-dataset-construction implements the DRIL methodology to assemble economic datasets from primary sources via AI agents. Ideal for constructing panel data, legal variables, and cited codebooks. CX Codex +1 ★ 240repo stars extract-figures extract-figures pulls figures, charts, diagrams, and images from .docx, converts EMF/WMF assets to PNG, and prepares LaTeX usage notes. CX Codex +1 ★ 240repo stars practitioner-finance-voice The practitioner-finance-voice skill rewrites academic finance drafts into the direct tone of practitioner outlets like FAJ and JPM. It frames findings for portfolio managers without fabricating facts. CX Codex +1 ★ 240repo stars comments-synthesis comments-synthesis turns feedback from several discussants, referees or workshop readers of one paper into a single revision plan, with the points they repeat ranked first. CX Codex +1 ★ 240repo stars nature-figure nature-figure structures high-impact publication figure design using Python or R backends. CX Codex +1 ★ 240repo stars llm-replication-disclosure llm-replication-disclosure is a Claude Code skill that checks replication materials for LLM-assisted research and helps draft disclosure text before submission or a data-editor response. CX Codex +1 ★ 240repo stars

Project sponsors

Companies that keep this analytics open