agentleFS
wangchuan2003-a11ywangchuan2003-a11y/book-to-action-skills/.agents/skills/on-liberty/SKILL.md

on-liberty

Skill1 starsChanged 2 months agoMITView on GitHub

Use Mill's On Liberty to examine restrictions on personal choice, dissent, and experiments in living, or to discuss these arguments in the book. Appropriate for rule design and ethical reasoning; it does not determine current law or prove policy effects.

The file

Files
SKILL.md

论自由:审查干预的理由

把争议还原为“谁限制谁的什么选择,凭什么”。本 Skill 提供 Mill 式规范论证及明确标识的现代应用设计,不把本书当作现行法律或效果证据。

定位任务

识别用户需要解释原书、评估规则,还是提出修订。解释与引用时读 source-notes.md;实际规则争议可参考 worked-example.md。书目与已读范围见 book.json,检查场景见 cases.json。

至少辨认被限制的行为、限制者、受影响者与据称会发生的损害。信息不足时做有限判断或明确标注的演示;不虚构投诉、制度或法律要求。

决策方法

  1. 写出干预对象。 区分劝说、批评、拒绝合作、组织处分与法律强制,也检查非正式的多数压力。不同干预强度需要不同理由。
  2. 说明损害链。 将令人不适、违反习惯、对本人不好,与对他人权利、机会或安全的具体影响分开。写出行为→影响对象→损害的机制、证据与未知。可识别伤害可以构成讨论限制的理由,但不自动证明每种限制都适当。
  3. 重建反方最强理由。 为限制者与被限制者各写一个当事人能认可的论证。多数票、资历和作者权威不能代替回答对方。正确意见也应能解释根据。
  4. 提出有限的生活试验。 在保护他人的边界内,考虑保留选择并用小范围、可撤回的试验获得信息。写出什么观察支持保留或收紧规则。试验设计是本项目的迁移推断,不是 Mill 的现代实验协议。
  5. 比较干预方案。 比较直接禁止、说明理由、降低外部影响和自愿选择;交代残余影响、成本承担者、异议渠道与改变建议的新证据。

交付与边界

先给结论,再说明具体损害、双方最强理由和可执行修改。必要时用表格比较方案,不机械填满固定模板。

第 III 章谷物商例子区分一般传播与具体情境下的鼓动行为。不能以自由为由替恐吓、定向骚扰或明确煽动开脱;也不能把所有冒犯都当作已证实伤害。

第 I 章关于“文明”与“野蛮人”的排除是作者的历史局限,不作为今天压制群体的依据。法律、儿童、能力受限者与具体安全风险问题,须结合真实制度与相关证据;本书本身不足以决定规则。引用只定位已核实章节,现代组织建议显式标为应用推断。

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.