agentleFS
wangchuan2003-a11ywangchuan2003-a11y/book-to-action-skills/.agents/skills/art-of-war/SKILL.md

art-of-war

Skill1 starsChanged 2 months agoMITView on GitHub

Use The Art of War to examine resources, avoidable conflict, information gaps, and adaptation in a concrete strategy decision, or to explain its cited chapters. Modern applications must be identified as analogies; do not treat colleagues as enemies or justify deception or unauthorized intelligence gathering.

The file

Files
SKILL.md

孙子兵法:先审条件,再选行动

用古典战略原则审视具体选择,不预测必胜,也不把合作、人际关系和市场默认视为战争。

输入与定位

确定结果、可支配资源、时间窗口、有关各方,以及尚未做出的选择。优先用已有事实,缺失数据按未知处理。

解释篇章时读 source-notes.md,辨认正文与 Giles 译注;现代应用可参考 worked-example.md。book.json 记录阅读范围,cases.json 提供检查场景。

问题主要是建立信任、情绪支持或修复关系时,不强行使用敌我与胜负框架;可以只取资源与信息检查,或说明类比帮助有限。

具体方法

  1. 审查条件。 由计篇的道、天、地、将、法启发,检查目标一致性、时机环境、场域限制、负责者能力和执行补给机制。现代对应项是分析类比,不是古文的项目管理定义。找出决定可行性的少数未知。
  2. 计算全程消耗。 由作战篇检查启动、持续、协调与机会成本,以及资源耗尽后的处境。写清单位与依据;缺数据时给区间或待调查项,不杜撰估算。长期任务不必然错误,须比较消耗与收益形成机制。
  3. 寻找降低冲突的路径。 由谋攻篇比较缩小目标、改变顺序、互利合作、选择不同对象或放弃争夺。不要把“不战”曲解为暗中胁迫或操纵。
  4. 补足会改变决定的信息。 由知彼知己与用间篇区分自身能力证据、外部事实、传闻和推测。现代获取方式限于公开信息、经授权访谈、合法试用或已提供材料。指定最小调查动作和它会改变的选择,不无限收集。
  5. 按变化调整并限定投入。 由虚实篇启发,选择一个可撤回动作、预期观察及继续、调整、停止条件。这是现代应用设计。条件改变时重比方案,不把变更本身当作英明。

交付与边界

先给建议与关键条件,再比较少量替代方案。说明重要未知、下一步和使建议失效的结果。执行仍遵循真实授权;古文不会授予外部操作权限。

知彼知己不保证百战百胜;军事判断不等于现代实验结论。不从诡道、用间推导欺诈、破坏、隐私侵入或对同事的敌意。长期科研与基础设施不能仅凭“忌久战”被否定。引用限于已核实篇章,标明原书原则、译者解释或现代类比。

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.