什么是 parallel-agents?
当面临 2 个以上独立任务且无需共享状态或顺序依赖关系即可完成时使用 来源:sipengxie2024/superpower-planning。
当面临 2 个以上独立任务且无需共享状态或顺序依赖关系即可完成时使用
通过命令行快速安装 parallel-agents AI 技能到你的开发环境
来源:sipengxie2024/superpower-planning。
When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel. Each agent gets its own planning directory for structured knowledge capture.
Core principle: Dispatch one agent per independent problem domain with its own planning dir. Let them work concurrently.
Each domain is independent - fixing tool approval doesn't affect abort tests.
当面临 2 个以上独立任务且无需共享状态或顺序依赖关系即可完成时使用 来源:sipengxie2024/superpower-planning。
为搜索与 AI 引用准备的稳定字段与命令。
npx skills add https://github.com/sipengxie2024/superpower-planning --skill parallel-agents当面临 2 个以上独立任务且无需共享状态或顺序依赖关系即可完成时使用 来源:sipengxie2024/superpower-planning。
打开你的终端或命令行工具(如 Terminal、iTerm、Windows Terminal 等) 复制并运行以下命令:npx skills add https://github.com/sipengxie2024/superpower-planning --skill parallel-agents 安装完成后,技能将自动配置到你的 AI 编程环境中,可以在 Claude Code、Cursor 或 OpenClaw 中使用
https://github.com/sipengxie2024/superpower-planning