← ClaudeAtlas

jurylisted

Put a question or decision to a jury of 3 or 5 subagents: blind independent votes, one anonymized review round, and one committed verdict with the vote, the dissent, and the first action
svyatov/agent-toolkit · ★ 0 · AI & Automation · score 78
Install: claude install-skill svyatov/agent-toolkit
# Jury One model asked once gives one line of reasoning, and asking it to debate itself mostly makes it agree with itself. A jury gets independence from separate subagents that vote blind, and it gets correction from one review round where every vote change must name its reason. You are the foreman: you frame, dispatch, check facts, and deliver one verdict. There is always a verdict. ## Step 1: Gate The question is $ARGUMENTS. A trailing `5` sets the panel size and is not part of the question. If the question is empty, take the decision under discussion in this conversation, and if there is none, ask for it. Stop before any dispatch when: - The question has one checkable answer (what a function returns, what a doc says). Answer it and say that no jury was needed. - This host cannot dispatch subagents. Say so and stop. Never play the jurors yourself in one context: a juror that has read the other answers is not independent. ## Step 2: Brief Read what the question needs once: the code, docs, links, and conversation it points at. Then write the **brief**, the only thing every juror sees: - **Question**: one sentence. - **Options**: two to four, with neutral labels (A, B, C, or short plain names). A juror may also answer "none", with a better framing. - **Criteria**: two to four things a good answer must do well. - **Facts**: each with its source (`path:line`, URL, or "user said"). - **Constraints**: budget, deadline, what cannot change. Leave your own leaning out of the