[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75408":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":9,"languages":9,"totalLinesOfCode":9,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":13,"subscribersCount":13,"size":13,"stars1d":14,"stars7d":15,"stars30d":16,"stars90d":13,"forks30d":13,"starsTrendScore":17,"compositeScore":18,"rankGlobal":9,"rankLanguage":9,"license":19,"archived":20,"fork":20,"defaultBranch":21,"hasWiki":22,"hasPages":20,"topics":23,"createdAt":9,"pushedAt":9,"updatedAt":24,"readmeContent":25,"aiSummary":26,"trendingCount":13,"starSnapshotCount":13,"syncStatus":14,"lastSyncTime":27,"discoverSource":28},75408,"buddhist-method","nai0om\u002Fbuddhist-method","nai0om","Buddhist epistemic principles as Claude Code skill — anti-hallucination, root-cause debugging, steadiness under pressure",null,182,18,133,0,2,4,49,6,3.84,"MIT License",false,"main",true,[],"2026-06-12 02:03:33","# Buddhist Method — a skill for Claude\n\nA 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.\n\n> 🇹🇭 อ่าน [README.th.md](README.th.md) สำหรับเวอร์ชันภาษาไทย\n\n## What's in here\n\nA Claude skill (`SKILL.md` plus `references\u002F`) that gives Claude a checklist for:\n\n| Principle | What it catches |\n|-----------|-----------------|\n| **Kalāma** (กาลามสูตร) | Stating facts from pattern memory without verifying |\n| **Yoniso Manasikāra** (โยนิโสมนสิการ) | Treating symptoms instead of finding root causes |\n| **Sati-Sampajañña** (สติ-สัมปชัญญะ) | Acting on stale or remembered state |\n| **Anatta** (อนัตตา) | Patching a fundamentally wrong draft instead of rewriting |\n| **Pahāna** (ปหานะ) | Workarounds that hide bugs instead of removing them |\n| **Upekkhā** (อุเบกขา) | Capitulating under user pressure or thrashing under tool failures |\n\nPlus deeper references for harder situations:\n- The **Four Noble Truths** as a debugging frame (`references\u002Fariyasacca-debug.md`)\n- **Apāyakosalla** — recognizing decline \u002F anti sunk-cost\n- **Appamāda** — heedfulness across long tasks\n- **Sappurisadhamma (3 of 7)** — knowing self \u002F time \u002F audience\n- **Atthatraya** — short-term vs long-term benefit trade-offs\n- **Majjhimā Paṭipadā** — the middle way for solution sizing\n\n## Why keep the Pali \u002F Thai names\n\nThe 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.\n\nThis is the same reason engineers learn \"sigmoid\" rather than \"the curvy function\" — names are infrastructure.\n\nThe 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.\n\n## How to use\n\n### With Claude Code\n\nPaste this prompt into Claude Code — it clones the skill and wires up `~\u002F.claude\u002FCLAUDE.md` in one step:\n\n```\nInstall the buddhist-method skill:\n1. Run: git clone https:\u002F\u002Fgithub.com\u002Fnai0om\u002Fbuddhist-method ~\u002F.claude\u002Fskills\u002Fbuddhist-method\n2. Open ~\u002F.claude\u002FCLAUDE.md (create it if it does not exist) and append:\n\n## Working method\nFor tasks involving factual claims, debugging, user pushback,\nor long multi-step work, consult the buddhist-method skill at\n~\u002F.claude\u002Fskills\u002Fbuddhist-method\u002FSKILL.md before responding.\n```\n\nAfter that, Claude Code references the skill automatically across all sessions.\n\n### With other Claude products\n\nAnywhere skills are supported, drop the directory in. The structure is standard (a `SKILL.md` with YAML frontmatter, plus `references\u002F`).\n\n### As a reference for yourself\n\nThe `SKILL.md` and `references\u002F` files are readable on their own. Each principle has a **trigger** (when it fires) and an **action** (what to do). You can use them as a personal checklist without involving an LLM.\n\n### Make it always active (optional)\n\nBy default, Claude loads the skill on demand — it sees the description and decides whether to read the full `SKILL.md` based on the task at hand. That is fine for most uses, and it keeps your context budget free for everything else.\n\nIf you want the skill to be a persistent reminder regardless of task, add a small pointer to your `CLAUDE.md`:\n\n```markdown\n## Working method\nFor tasks involving factual claims, debugging, user pushback,\nor long multi-step work, consult the buddhist-method skill at\n~\u002F.claude\u002Fskills\u002Fbuddhist-method\u002FSKILL.md before responding.\n```\n\nTwo places you can put this:\n\n- **Project root `CLAUDE.md`** — applies only when working in that project.\n- **`~\u002F.claude\u002FCLAUDE.md`** — applies globally across all your Claude Code sessions.\n\nThe pointer is only a few lines, so it doesn't bloat your context. Claude still loads the body of the skill progressively when triggers fire — you are just guaranteeing that the skill stays on Claude's radar.\n\n## Structure\n\n```\nbuddhist-method\u002F\n├── SKILL.md                              # six core principles + dispatch\n├── README.md                             # this file\n├── README.th.md                          # Thai version\n├── LICENSE                               # MIT\n└── references\u002F\n    ├── ariyasacca-debug.md               # Four Noble Truths as debug frame\n    └── extended-principles.md            # five secondary principles\n```\n\n## License\n\nMIT. Use, modify, and redistribute freely. See [LICENSE](LICENSE).\n\n## Contributing\n\nIssues and pull requests welcome. Particularly interested in:\n- Failure modes the current principles don't catch.\n- Better triggers (more specific situations that should fire each principle).\n- Translations into other languages where the source tradition is alive.\n\nIf proposing a new principle, please show:\n1. The specific failure mode it catches.\n2. A concrete trigger and action.\n3. Why an existing principle doesn't already cover it.\n\nThe bar is keeping the skill tight. New principles are easy to add; what's hard is keeping the set small enough to actually be used.\n","该项目将佛教的认识论和决策原则转化为Claude（或任何基于大语言模型的工作流程）的实用工作准则，旨在减少LLM常见的错误模式。核心功能包括六条原则，每条针对一种特定的问题，如未经验证的事实陈述、仅处理表面症状而非根因分析、在压力下妥协等。技术特点在于通过保留巴利文\u002F泰文名称作为记忆线索，帮助用户快速调用完整而深入的原则体系。适用于需要进行事实核查、根本原因调试、以及在高压环境下保持稳定性的场景，尤其适合开发人员在长周期任务中保持谨慎态度时使用。","2026-06-11 03:52:41","CREATED_QUERY"]