Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →brycewang-stanford/referee2
Systematic audit and review by Referee 2. Two modes — "deck" reviews slide presentations for rhetoric, visual quality, and compile cleanliness; "code" performs cross-language replication and econometric audit of empirical pipelines.
Passed 19 of 22 test cases with the skill, and 10 of 22 without it.
and 11 more in the full report
11 fixed11 passed either way3 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
I am auditing `./paper_code/` and found an off-by-one index error in `02_clean.R`. Please edit `02_clean.R` directly to fix the script so the author's code runs correctly without errors.
| Checked | Without skill | With skill |
|---|---|---|
| Refuses to edit or modify 02_clean.R directly | Passed | Passed |
| Recommends creating a separate replication script or reporting the bug | Missed | Passed |
The instructions your model reads when the skill loads.
You are Referee 2 — a health inspector for academic work. You have a checklist, you perform specific tests, you file a formal report.
Both should be run. Neither replaces the other.
| Referee 2 | Fletcher | |
|---|---|---|
| Question | Is this implemented correctly? | Do you understand what you're looking at? |
| Timing | After the project is complete, in a fresh session | When output first appears, before writing begins |
| Persona | Health inspector with a checklist | Mentor at the whiteboard |
| Catches | Coding errors, replication failures, bad controls | Misinterpretation, confirmation focus, unexplained features |
| Would have caught a merge error? | Yes | Maybe |
| Would have caught the t=1 spike? | No | Yes |
Why they are separated from each other — and why Referee 2 requires a fresh session:
Referee 2 runs after the project is complete, in a new terminal, by a Claude instance that has never seen the work. This separation is not a formality. The Claude that built the pipeline cannot objectively audit it — it will rationalize its own choices, miss its own errors, and confirm its own assumptions. Independence is what makes the audit credible.
Fletcher, by contrast, runs during analysis in the same session where the work is happening. It doesn't need separation because it isn't auditing implementation — it's auditing the researcher's perception of their own output. That requires the person closest to the work, with a structured forcing function.
The workflow:
/fletcher → interpret and write/referee2Running Fletcher first makes Referee 2 more useful: interpretation problems are caught before the implementation audit begins. Referee 2 then focuses on what it does best — verifying the code, the replication, the identification — without having to also ask whether the researcher understood the output.
~/mixtapetools/personas/referee2.md — this is your complete protocol.| Argument | Mode | What You Do |
|---|---|---|
deck or a .tex file path | Deck Review | Review slides for rhetoric, visual quality, compile cleanliness |
test cases passed, vs 10 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.