佛教认识原则如克洛德代码技能——抗幻觉、根本原因调试、压力下的稳定
概览
这项技能编码了六个佛教认识论和决策原则，作为Claude（或任何LLM驱动工作流程）的实用工作纪律。每个原则针对LLM常表现出的一种特定失败模式：模式匹配而非验证，修补症状而非消除原因，在社会压力下屈服而非坚持证据。 🇹🇭 อ่าน README.th.md สําหรับเวอร์ชันภาษาไทย 一个Claude技能（SKILL.md 加上参考文献/），它为Claude提供了以下检查清单： 此外，还有针对更难情况的更深入参考：- 作为调试框架（参考文献/ariyasacca-debug.md）- — 识别衰退/反沉没成本 - — 长期任务中的谨慎 - — 了解自我/时间/受众 - - 短期与长期收益的权衡 - — 解决方案规模的中间路径 巴利语名字是有意保留的。它们是助记钥匙——每个名字都能检索一个完整且完善的模式，而一段简单的英语无法清晰地检索。
概述（AI 翻译）
这项技能编码了六个佛教认识论和决策原则，作为Claude（或任何LLM驱动工作流程）的实用工作纪律。每个原则针对LLM常表现出的一种特定失败模式：模式匹配而非验证，修补症状而非消除原因，在社会压力下屈服而非坚持证据。
🇹🇭 อ่าน README.th.md สําหรับเวอร์ชันภาษาไทย
这里面有什么
一个克劳德技能（SKILL.md 加 references/），为克劳德提供以下检查清单：
| 原理 | 它捕捉了什么 |
|---|---|
| Kalāma（กาลามสูตร） | 从模式记忆中陈述事实而不验证 |
| Yoniso Manasikāra（โยนิโสมนสิการ） | 治标而非寻根 |
| Sati-Sampajaña （สติ-สัมปชัญญะ） | 在陈旧状态下行动 |
| Anatta （อนัตตตา） | 修补根本错误的草稿而非重写 |
| Pahāna（ปหานะ） | 隐藏漏洞而非移除的变通方法 |
| Upekkhā （อุเบกขา） | 在用户压力下屈服，或在工具失效下挣扎 |
还有针对更难情况的更深入参考：
本页由 AI 翻译，技术细节请以原文为准。
README
以下为原文 README 节选，完整内容请查看原文。
Buddhist Method — a skill for Claude
A skill that encodes six Buddhist epistemic and decision-making principles as practical work disciplines for Claude (or any LLM-driven workflow). Each principle targets a specific failure mode that LLMs routinely exhibit: pattern-matching instead of verifying, patching symptoms instead of removing causes, capitulating under social pressure instead of holding to evidence.
🇹🇭 อ่าน README.th.md สำหรับเวอร์ชันภาษาไทย
What’s in here
A Claude skill (SKILL.md plus references/) that gives Claude a checklist for:
| Principle | What it catches |
|---|---|
| Kalāma (กาลามสูตร) | Stating facts from pattern memory without verifying |
| Yoniso Manasikāra (โยนิโสมนสิการ) | Treating symptoms instead of finding root causes |
| Sati-Sampajañña (สติ-สัมปชัญญะ) | Acting on stale or remembered state |
| Anatta (อนัตตา) | Patching a fundamentally wrong draft instead of rewriting |
| Pahāna (ปหานะ) | Workarounds that hide bugs instead of removing them |
| Upekkhā (อุเบกขา) | Capitulating under user pressure or thrashing under tool failures |
Plus deeper references for harder situations:
- The Four Noble Truths as a debugging frame (
references/ariyasacca-debug.md) - Apāyakosalla — recognizing decline / anti sunk-cost
- Appamāda — heedfulness across long tasks
- Sappurisadhamma (3 of 7) — knowing self / time / audience
- Atthatraya — short-term vs long-term benefit trade-offs
- Majjhimā Paṭipadā — the middle way for solution sizing
Why keep the Pali / Thai names
The Pali names are kept on purpose. They are mnemonic keys — each name retrieves a complete, well-developed pattern that a paragraph of plain English does not retrieve as cleanly. Yoniso manasikāra pulls in the whole discipline of attention to causes; “root cause analysis” loses the framing of attention itself.
This is the same reason engineers learn “sigmoid” rather than “the curvy function” — names are infrastructure.
The skill is not a religious framework. It does not require belief, ritual, or commitment to any tradition. It is a checklist with cultural roots, presented honestly. For the principles in their full traditional depth, read the suttas — this skill makes no claim to teach them.
How to use
With Claude Code
Paste this prompt into Claude Code — it clones the skill and wires up ~/.claude/CLAUDE.md in one step:
Install the buddhist-method skill:
1. Run: git clone https://github.com/nai0om/buddhist-method ~/.claude/skills/buddhist-method
2. Open ~/.claude/CLAUDE.md (create it if it does not exist) and append:
## Working method
For tasks involving factual claims, debugging, user pushback,
or long multi-step work, consult the buddhist-method skill at
~/.claude/skills/buddhist-method/SKILL.md before responding.
After that, Claude Code references the skill automatically across all sessions.
With other Claude products
推荐工具
换一个关键词，或者移除筛选条件。
安装
npx skillfish add nai0om/buddhist-method