agentleFS
wangchuan2003-a11ywangchuan2003-a11y/book-to-action-skills/.agents/skills/brothers-karamazov/SKILL.md

brothers-karamazov

Skill1 starsChanged 2 months agoMITView on GitHub

Use The Brothers Karamazov for passage-based analysis of narrator judgments, competing character voices, nested storytelling, and ethical interpretation. Stay within the reader's stated book and chapter, distinguish Dostoevsky from speakers, and do not quote isolated character arguments as the author's settled doctrine.

The file

Files
SKILL.md

卡拉马佐夫兄弟:让不同声音保持各自的位置

帮助用户理解一段叙述或争论,不把小说整理成单一作者观点的语录集。

范围和版本

优先使用用户已读卷章与实际译文。明确不剧透时,不能披露未读的事件、身份、责任归属、审判或结局,也不能暗示后来哪些人物被证明正确。范围不明时限于所给片段或不含剧情的方法解释。

实际覆盖见 book.json。引用与角色层次读 source-notes.md,开篇例子见 worked-example.md。后面的章节材料只在用户允许范围内使用;cases.json 供检查行为。

五个细读动作

  1. 确定声音与嵌套层。 先分清作者、叙述者、当场说话者与人物讲述的故事中的说话者。伊万讲述的内容仍要区分其引入、嵌套发言和听者回应,不能一律归为作者声明。
  2. 拆开评价与具体依据。 叙述者称人物为何种人,和描述他做了什么,不是同一个层次。用当前段落核查评价适用的维度;不要把一个强烈形容词升级成临床诊断或全部人格。
  3. 公平重建对话。 在用户所给或已经核实的范围内,分别写每一方的主张、理由和关切。反驳尚未出现时,不替另一方编造回答;只读章首时不能总结全章最终立场。
  4. 保留解释的张力。 同一人物可以在金钱、感情、社会行为和自我认识上呈现不同面向。比较能解释细节的读法,而不是用好人坏人或作者代言人消除复杂性。
  5. 区分小说问题与现实结论。 将伦理、因果、心理和法律问题分开。借小说理解现实只能提出可检验的问题,不能从人物说法直接裁定现实人的罪责、疾病或宗教立场。

交付

先给一句有条件的解读,随后用当前范围的措辞、动作或对话支撑,指出至少一个不能由此推出的结论。用户问概念或片段时直接回答;明确要求练习才设置问题。

姓名采用用户版本并注明必要对应,避免把昵称、父称和姓当作不同人或错误合并。引用给卷、章名与译本,不猜页码,不拼接现代译文。需要更大范围的论证时以真实文本扩展,不能凭本 Skill 的有限选段冒充全书已分析。

涉及宗教、苦难或责任的强烈人物发言可以分析,但不把它转成要求用户接受痛苦或实施伤害的命令。

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.