hyperplan
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', 'adversarial plan', 'hostile planning', 'cross-critique plan', '하이퍼플랜', '적대적 계획', '교차 비평'.
适合你，如果做重要决策时总担心遗漏关键假设或盲点。
npx oh-my-skill add code-yeongyu/oh-my-openagent/hyperplancurl -fsSL https://oh-my-skill.com/install.sh | bash -s -- code-yeongyu/oh-my-openagent/hyperplannpx oh-my-skill verify code-yeongyu/oh-my-openagent/hyperplan怎么用
商店整理自技能原文 · 版本 3ec4afb · 表述以原文为准装上后，Claude 会启动一个由5个敌对成员组成的辩论团队，对用户的规划需求进行交叉批判，只保留经得起攻击的见解，然后强制交给专门的“plan”智能体生成可执行的计划。
当用户提出需要严格规划、暴露弱假设或盲点的请求时，或说出“hyperplan”、“hpp”、“/hyperplan”、“adversarial plan”等触发词时触发。