跳到正文
码上手 coding.chengyu.dev
CO

hyperplan

code-yeongyu/oh-my-openagent/.agents/skills/hyperplan

执行对抗性多代理规划生成可执行计划

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'.

把下面的话发给 Claude Code、Codex 或 Cursor。智能体会先检查内容,经你确认再安装。

请帮我安装这个 Agent Skill:https://github.com/code-yeongyu/oh-my-openagent/tree/dev/.agents/skills/hyperplan

1. 先读取该目录下的 SKILL.md 和其他文件,检查是否有可疑内容(执行未知脚本、读取密钥、向外发送数据等),用中文告诉我它会做什么、需要哪些权限;
2. 等我确认后,再把整个目录安装到 ~/.claude/skills/hyperplan/(如果你不是 Claude Code,安装到你自己约定的 skills 目录);
3. 安装后告诉我怎么触发它。

Skill 可以让智能体执行脚本。安装第三方 Skill 前务必看一遍内容,详见「安全」一课。

该仓库未声明开源许可证,本站不转载全文,请到 GitHub 查看。

Esc

输入关键词开始搜索,例如「CLAUDE.md」「MCP」「部署」