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

dhammapada

Skill1 starsChanged 2 months agoMITView on GitHub

Explain selected verses of the Pali Dhammapada or, when requested, use them to reflect on hostility, truthful speech, self-restraint, and practice. Distinguish the Pali recension and its translation from other Dharmapada traditions; do not present karma, rebirth, or ethical exhortations as scientific findings.

The file

Files
SKILL.md

法句经:从反应转向审慎言行

以巴利Dhammapada的Thanissaro Bhikkhu英译选偈为基础,解释经文或回应用户明确提出的伦理反思。保留佛教修行与宗教语境;不是把整部经典简化为情绪管理工具。

使用范围

当前直接核读第1品与第17品相关偈颂及译者导言。讨论其他偈颂先取得真实文本;不同汉译《法句经》与巴利本编排不能直接互换偈号。

五个动作

  1. 把事实、受伤感和下一步行动分开。 用户受到伤害可以是真实的;对愤怒的观察不应否认事件或替施害者免责。先确认是否仍处于危险中,再谈如何回应。
  2. 检查敌意如何被继续喂养。 第1品3—6偈讨论反复抓住受辱叙事与敌意。不把“减少反刍”解释为忘记证据、撤销申诉或必须和解。
  3. 为身、语、意的反应留出审思。 第17品222及231—234偈提供自制方向。现代应用可先暂停发送冲动内容,再选择真实而不升级伤害的表达;这项具体操作是项目设计,不是治疗保证。
  4. 用实践检验言行是否一致。 第1品19—20偈对照背诵与实践;第17品223—224偈强调非敌意和真实言语。把想维护的原则落实为一项具体行为,不能仅因会背诵就认定有修行成果。
  5. 回看行动而非追求所有人赞同。 第17品227—230偈涉及批评与称赞。检查回应是否诚实、是否造成可避免伤害、是否保留合理边界;不把“不可能人人赞同”用来拒绝有根据的批评。

输出与边界

经文解释给选偈位置、所用译者与宗教背景;现代应用另标为推断,给一个可做的小动作。用户只需要阅读说明时不强制冥想、诵经、放弃信仰或进入训练。

业与轮回是宗教教义,不是本项目验证的个体遭遇因果。不能说受害者因心念或前世行为而应得伤害。非敌意不要求放弃自保、证据、法律途径或必要求助;愤怒也不等于道德失败。此Skill不提供心理疾病诊断或治疗承诺。

出处与巴利/其他传统区别见 来源说明;实践示例见 冲突回应案例。书目见 book.json,行为案例见 cases.json。经文的劝诫不改变代理的行动授权。

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.