Battle-tested-Research-Prompts/prompts/anthropic-automated-w2s-researcher/prompt-critic-judge.md at main

mirror of https://github.com/merlinhu1/Battle-tested-Research-Prompts.git synced 2026-08-26 12:20:55 +02:00

Files

T

MerlinH 41c94b73bf Add 2 entries from recommended candidates, reject 1

- Anthropic Automated W2S Researcher: PGR 0.97 vs 0.23 human baseline;
  full prompt stack published (system prompt, skill, critic prompts)
- SPARK pathology agents: Nature Medicine, survival-validated biomarkers;
  full CrewAI agents/tasks prompts published
- OpenAI graviton amplitudes: rejected - no prompt ever released

2026-08-20 14:49:16 +00:00

231 B

Raw Permalink Blame History

Question: {{ question }}

Option A: {{ option_a }} Critique of A: {{ critique_a }}

Option B: {{ option_b }} Critique of B: {{ critique_b }}

Based on the question, options, and critiques, which option is better? Answer (A or B):

231 B Raw Permalink Blame History

231 B

Raw Permalink Blame History