Eight Claude Referees That Try to Reject Your Paper Before a Journal Does
An economist open-sourced the referee panel he runs on his own papers: an editor, six specialist reviewers and a fact-checker, all Claude. How to set it up, the commands, and the catch
Most papers find out what's wrong with them the slow way: months later, in a desk rejection or a harsh referee report.
Economist Claes Backman built a set of Claude Code skills that do that review first. The main one runs seven Claude reviewers on your paper at once, then an eighth checks every finding against your actual text and throws out anything wrong or minor.
What the panel checks
- The editor: would this paper be sent to referees, or desk rejected? It gives a preliminary recommendation.
- The contribution judge: six questions on whether the idea is big enough for your target journal.
- Unsupported claims and causal overclaiming: every 'this proves' that the data doesn't back.
- Math, equations and notation; tables and figures; numbers that don't match across sections.
- Spelling, grammar and academic style, reported once per pattern so the list stays short.
- Every finding is tagged CRITICAL, MAJOR or MINOR and lands in one ranked report saved in a reviews folder.
Free, for your email
Get the full setup steps + the copy-paste setup prompt
The rest of this guide (4 more sections, 3 copy-paste prompts) opens right here. The setup prompt, one paste into Claude that sets it all up, comes by email only. Use your real address.
Unlocks: Step 1: set it up · Step 2: the commands · The catch · Sources
50,000+ follow where these guides come from. No spam, reply “unsubscribe” any time.