Back to Details

nba

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese
Find the next best action from state, not from vibes.
基于状态而非直觉确定下一步最佳行动。

Goal

目标

nba
is the manual re-entry point for a stalled cycle. It reads the current state and returns one action: the cheapest move that clears the binding constraint. It does not execute the action and it does not offer a menu, because a menu recreates the paralysis it exists to resolve.
nba
是停滞周期的手动重新切入点。它读取当前状态并返回一项行动：解除约束成本最低的举措。它不会执行该行动，也不会提供选项菜单，因为菜单会重新引发它本应解决的决策瘫痪问题。

Workflow

工作流程

  1. Read the live cycle state: plan gates, re0-memo anti-patterns, priority notes, recent git/file changes, QA evidence, and the current workflow phase.
  2. Locate the project in the cycle: FRAME, BUILD, DRIVE, RE0-MEMO, HATE, RE0-WORK, BUILD AGAIN, or SHIP.
  3. Diagnose the blank-out cause: too many open threads, lost thread, unnamed blocker, closed-loop fatigue, avoidance of the hard step, or a phase that is already done.
  4. Return one action: the cheapest move that clears the most. It may name the right skill for the human to fire, the external input needed, the first nail to test, or the phase transition that is already due.
  5. Frame it as: where you are, next best action, why now, and done when.
  1. 读取生命周期状态：计划关卡、re0-memo反模式、优先级备注、近期git/文件变更、QA证据以及当前工作流阶段。
  2. 定位项目所处的周期阶段：FRAME、BUILD、DRIVE、RE0-MEMO、HATE、RE0-WORK、BUILD AGAIN或SHIP。
  3. 诊断停滞原因：过多未关闭的任务线程、丢失任务线索、未明确的障碍、闭环疲劳、逃避困难步骤，或已完成的阶段。
  4. 返回一项行动：能解决最多问题的最低成本举措。它可能指明人类需要调用的合适技能、所需的外部输入、首个测试点，或已到期的阶段转换。
  5. 行动表述格式：当前位置、下一步最佳行动、为何此时执行、完成标准。

Rules

规则

  • One action, not a checklist.
  • State-grounded, never generic. Cite the gate, doc, evidence, or file state that drives the pick.
  • Return the avoided move, not the easy busywork.
  • If no outside truth is entering, the next action is external input, not another internal lap.
  • If the gate is already met, the action is to move phase or ship, not add another surface.
  • Read-only on the project. 
    nba
    recommends; it does not execute.
  • Do not auto-invoke user-only skills. Tell the human when one is the next move.
  • 仅返回一项行动，而非检查清单。
  • 基于实际状态，绝不泛泛而谈。需引用驱动决策的关卡、文档、证据或文件状态。
  • 返回被逃避的举措，而非轻松的琐碎工作。
  • 若没有外部信息输入，下一步行动应为获取外部输入，而非重复内部循环。
  • 若已满足关卡要求，行动应为推进阶段或交付，而非增加额外内容。
  • 仅读取项目状态。
    nba
    仅提供建议，不执行操作。
  • 请勿自动调用仅用户可用的技能。当某项技能是下一步行动时，告知用户。

Verification

验证

Before finishing:
  1. The recommendation cites the state it read.
  2. There is exactly one next action.
  3. The action has a clear "done when" observable.
  4. A reader can tell why this action beats the other visible options.
完成前需确认：
  1. 建议需引用所读取的状态信息。
  2. 恰好只有一项下一步行动。
  3. 行动有明确可观测的“完成标准”。
  4. 读者能明确知晓为何该行动优于其他可见选项。