home/roleplay/judge-user

Judge.user

GPTClaudeGemini··1,177 copies·updated 2026-07-14
judge-user.prompt
Test: $test_identifier
Fail rate: $fail_rate

Hypotheses:
$hypotheses_json

Rank these hypotheses from most to least plausible. Consider the fail rate as a clue about timing vs state issues.

when to use it

Community prompt sourced from the open-source GitHub repo npow/claude-skills (Apache-2.0). A "Judge.user" style prompt — adapt the placeholders and specifics to your task. Imported as-is and not independently retested here, so check the output before relying on it.

tags

roleplaycommunitygeneral

source

npow/claude-skills · Apache-2.0