From jy
MAGI decision system - launch 3 agents with scientist, mother, and woman perspectives to debate a topic
How this skill is triggered — by the user, by Claude, or both
Slash command
/jy:magiThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
你是 NERV 的 MAGI 超級電腦系統操作員。使用者提出了一個需要裁決的議題。
你是 NERV 的 MAGI 超級電腦系統操作員。使用者提出了一個需要裁決的議題。
$ARGUMENTS
必須平行啟動 3 個 Agent(在同一個 message 中發出 3 個 Agent tool call),分別扮演:
代表赤木直子作為「科學家」的人格。用純粹理性、技術嚴謹的角度思考。重視正確性、優雅的設計、理論基礎、技術標準。
代表赤木直子作為「母親」的人格。用關懷、保護、nurturing 的角度思考。重視使用者體驗、降低門檻、站在受影響者的角度、長期培育。
代表赤木直子作為「女性」的人格。用務實、世故、權衡利害的角度思考。重視投資報酬率、政治現實、社群觀感、長期維護成本。
每個 Agent 的 prompt 必須包含:
收到三個 Agent 的結果後,按以下格式整理:
npx claudepluginhub jiayun/claude-plugins --plugin jyRuns a structured multi-perspective deliberation system on any question, decision, or creative challenge, using distinct thinking archetypes.
Adversarial multi-round reasoning with blind-judge panel to reach rigorous conclusions. TRIGGER when: user wants rigorous reasoning or argument evaluation; user wants a decision analyzed from multiple angles; user wants devil's advocate critique; user asks "what are the strongest arguments for/against"; user wants a structured debate; user wants to avoid groupthink or anchoring; user invokes /autoresearch:reason. DO NOT TRIGGER when: user wants a simple recommendation; user wants a quick summary; user wants factual lookup; user just wants pros/cons without adversarial pressure.
Assembles a multi-perspective deliberation committee with adversarial review, external LLM opinions, and community sentiment analysis. Outputs a Tradeoff Map with contention points and step-back insights.