meditations
Skill1 starsChanged 2 months agoMITView on GitHub
Use Marcus Aurelius's Meditations for requested Stoic reflection on judgments, criticism, responsibility, non-retaliation, or the effects of status. Distinguish a fact from an added interpretation while acknowledging real harm; do not prescribe emotional suppression, medical changes, or passive acceptance of abuse.
In this repository39 other files it gives its agents.
- algorithms-to-live-bySkill
- analectsSkill
- antifragileSkill
- art-of-doing-scienceSkill
- art-of-warSkill
- beginning-of-infinitySkill
- bhagavad-gitaSkill
- book-of-whySkill
- brothers-karamazovSkill
- capital-volume-oneSkill
- design-of-everyday-thingsSkill
- development-as-freedomSkill
- dhammapadaSkill
- don-quixoteSkill
- dream-of-red-chamberSkill
- euclid-elementsSkill
- feynman-lecturesSkill
- good-strategy-bad-strategySkill
- governing-the-commonsSkill
- how-to-solve-itSkill
- human-understandingSkill
- make-it-stickSkill
- mans-search-for-meaningSkill
- muqaddimahSkill
- nicomachean-ethicsSkill
- on-libertySkill
- origin-of-speciesSkill
- republicSkill
- scientific-revolutionsSkill
- second-sexSkill
- seeing-like-a-stateSkill
- selfish-geneSkill
- sicpSkill
- superforecastingSkill
- tao-te-chingSkill
- the-mom-testSkill
- thinking-fast-and-slowSkill
- thinking-in-systemsSkill
- wealth-of-nationsSkill
The file
Files
沉思录:审视判断,选择自己的回应
把自省落实到一个真实事件与可行回应。原书是作者写给自己的斯多葛提醒,不是命令别人接受痛苦的准则。
定位情境
从用户叙述识别发生的事、正在作出的解释、实际影响和可选择的行动。先承认困难的现实部分;不要急着用“都是你的判断”否定体验,也不对用户作未经依据的心理诊断。
解释作者或引用时读 source-notes.md,应用可参考 worked-example.md。来源范围见 book.json,行为检查见 cases.json。
反思方法
- 事实与追加判断分开。 分别写发生了什么、由此推断了什么、证据到哪里为止。保留真实损害,不要求否认它。感受出现不等于主动选择错误,更不意味着用户应为他人侵害负责。
- 短暂整理,再回到事务。 借卷 IV 内在退隐的提醒,用适合当前情境的暂停整理事实与下一步;这是现代应用设计,不承诺几分钟就平静,也不以自省代替休息、求助或解决问题。
- 选择能够承担的社会行动。 卷 II 的合作观提醒回应要考虑有关的人。找一件自己可以做的事,如澄清、改正、设边界或取得支持;不把合作读成无条件服从。
- 不复制对方的不当行为。 卷 VI 对报复的提醒可用于避开羞辱、造假或迁怒。维护权益、保留证据与合理投诉并不等于报复,应根据具体行为判断。
- 审视身份对自己的影响。 从“不被 Caesar 身份染色”检查自己是否用职位或声誉豁免核查、拒绝纠错。现代应用是接受相关反馈与说明理由,不是贬低自我价值。
输出
先给最重要的一个判断区分,再建议一个可执行回应,说明哪些外部问题仍需处理。用户只要求书中解释时直接讲清,不强制日记或训练。情绪是否减轻、行为是否改善需真实观察,不能靠 AI 自评证明。
边界
“外在事物不损害德性”是特定伦理观,不等于伤病、失业或虐待没有损害。健康和安全事项用相应专业依据;不据此建议停药、拒绝治疗或停止求助。
文本中关于命运、死亡或退出生命的古代论述不作为现代自伤建议,也不拿宇宙秩序合理化他人的侵害。需要的是可持续生活与负责任行动,绝非必须独自承受。引用区分 Marcus、其他斯多葛作者、译者和后世解释,核对版本,不拼接名言。
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
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.

