Who will referee your paper, and what will they say? Find out before you submit.
Fresh sessions read the paper cold, like real referees. Names carry a lot: “as Jerker Denrell would” brings survivor bias and the firms that quietly died with it.
Who are the five most likely referees for this paper, judging by its references? One line each: what would they care about?
Argue with the list. Add the one you fear most.
The underused move: ask the agent how to do the job before you ask it to do it.
I want simulated referee reports on this paper. How does a good referee for its journal work? How deep should they go? Should they try to reproduce the main results? Propose a procedure.
Argue with it. Then: “Save what we agreed as reviews/how-to-referee.md.”
Type /clear, then:
Referee this paper as [name] would, following reviews/how-to-referee.md. Save it as reviews/[name].md.
Repeat for each referee.
In a hurry? Run them side by side: a second window with its own claude or codex, or in Claude Code: “Run the referees as parallel subagents.”
Change the procedure, not the report. For example:
Edit how-to-referee.md, /clear, rerun. Doing this for every paper? “Turn the procedure into a skill called referee-panel.”
/clear, then:
You’re the editor. Read the reports in reviews/. Where do the referees agree, where do they disagree, and what must be fixed before submission?