Cangjie Skill is a system that turns methods from books, long videos, podcasts, and other source material into executable skills for AI agents. It helps users package knowledge into callable workflows, using the repository's code, methods, and templates; catalogue add-ons relate to these agent skills.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kangarooking/cangjie-skill --skill rational-buddhismgit clone --depth 1 https://github.com/kangarooking/cangjie-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kangarooking/cangjie-skill/rational-buddhism)<a href="https://agentmods.dev/skills/kangarooking/cangjie-skill/rational-buddhism"><img src="https://agentmods.dev/badge/skills/kangarooking/cangjie-skill/rational-buddhism/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kangarooking/cangjie-skill/rational-buddhism"><img src="https://agentmods.dev/badge/skills/kangarooking/cangjie-skill/rational-buddhism.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00166 | $0.01678 |
| Opus 5 | $0.00083 | $0.00839 |
| Sonnet 5 | $0.00033 | $0.00336 |
| Haiku 4.5 | $0.00017 | $0.00168 |
Grade A, and why
rational-buddhism scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
理性佛教：验证一切
R — 原文 (Reading)
尝试一切，亲自测试，保持怀疑，保留有用的，舍弃没用的。……理性的部分意味着我必须与科学和进化和解。我必须拒绝所有我不能验证的内容。……如果我无法验证它，或者如果我不能通过科学到达那里，那么它可能是真的，也可能是假的，但它肯定是无法证伪的，所以我不能将它视为基本真理。
— 纳瓦尔·拉维坎特, 《纳瓦尔宝典》 第二章·幸福
I — 方法论骨架 (Interpretation)
「理性佛教」是用科学标准过滤、保留内在技术的精神立场： ① 可证伪底线——「如果不能做出可证伪的预测，那它就不是科学」；无法验证/无法证伪的主张（业报、脉轮、超能力）不能进入基本真理； ② 亲自测试——冥想对你有好处吗？理清思路是好事吗？亲自验证后再采纳； ③ 保留有用的——冥想、观察、接纳等经时间考验的内在工作方法与科学并不冲突； ④ 进化是约束原则——进化论解释人是什么（生存与复制机器），佛教解释内在状态怎么调，二者可调和； ⑤ 保持怀疑但不关闭体验——「我不赞成任何幻想的东西」，但也别因「听起来玄」就拒绝亲测（读《当下的力量》的例子：先合上书说屁话，后来带着积极心态尝试，感觉很好）。
A1 — 书中的应用 (Past Application)
案例 1: 拒绝不可验证的教义
- 问题: 佛教里的业报/脉轮该信吗
- 方法论的使用: 「我看过。我不记得任何前世。我没有任何相关记忆。我就只是不能相信。」
- 结论: 无法亲自验证=不能视为基本真理
- 结果: 保留佛教的内在工作，拒绝玄学部分
案例 2: 读《当下的力量》的转变
- 问题: 对能量练习的第一反应是「这是屁话」
- 方法论的使用: 「我会带着积极的心态去做。我躺下，并尝试冥想。」
- 结论: 「很好，如果我相信它，或许它能起作用」
- 结果: 体验很好——验证优先于偏见
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 面对玄学/灵修/伪科学主张：「这个该信吗」
- 建立个人验证标准：「我该信什么」
- 科学与精神之间的摇摆：「科学和冥想冲突吗」
- 想尝试但保持理性：「怎么亲测又不走火入魔」
语言信号
- "这东西是真的吗/该信吗"
- "怎么验证一个说法"
- "科学 vs 灵修/冥想"
- "is this true / falsifiable / rational approach to spirituality"
与相邻 skill 的区分
- 与
judgment-training的区别: 判断力是通用思考能力；本 skill 是「什么可以信」的验证标准 - 与
monkey-mind-meditation的区别: 冥想是技术，本 skill 是允许/拒绝技术的哲学框架
E — 可执行步骤 (Execution)
-
跑可证伪测试
- 完成标准: 对主张问「它能做出可证伪的预测吗？失败时我能发现吗？」；不能→标记为「非基本真理」
-
跑亲自验证
- 完成标准: 若主张可体验（冥想/断食/练习），设计一个 30 天亲测计划，记录前后差异
-
按结果取舍
- 完成标准: 保留有用的（可复现体验），舍弃没用的（无效果/无法验证），不因来源迷信也不因标签拒绝
-
写入个人原则
- 完成标准: 形成 3 条自己的「相信清单」，注明每条的证据等级
B — 边界 (Boundary) ★
不要在以下情况使用此 skill
- 用户寻求宗教/灵性安慰的临终关怀、哀伤场景（尊重信仰选择，不灌输理性主义）
- 用「可证伪」标准审判一切人文领域（文学/爱/意义不适用该标准）
作者在书中警告的失败模式
- 把无法证伪当真理: 脉轮、业报等「花里胡哨的命名」不能进入基本真理
- 迷信权威替代亲测: 一切都要亲自测试
作者的盲点 / 时代局限
- 「亲自验证」本身也是主观证据，作者对玄学用可证伪标准、对自己体验用个人标准，存在双标
- 理性主义框架对非理性需求的解释力有限
容易混淆的邻近方法论
judgment-training: 可证伪性是判断力心智模型库之一
相关 skills (阶段 3 定稿)
- depends-on:
judgment-training（可证伪标准是判断力产物） - composes-with:
monkey-mind-meditation、life-meaning
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 121 lines · 166 tokens per session scan A 4be72c3847eb
rational-buddhism is a skill published in the GitHub repository kangarooking/cangjie-skill (9,795 stars, last pushed 4d ago), licensed MIT. It adds 166 tokens to every session and 1,678 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
skill-builder
Use when automatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.
us-program-research
This skill should be used when the user needs structured research and ranking of US academic programs (PhD, Master.
legend-lore
Use this spell when you need everything knowable about a person, company, library, framework, concept, or system — not a quick answer, but a deep dossier.
comprehend-languages
Use this skill when the words are legible but the meaning is trapped inside an unfamiliar dialect, format, or community.
capability-circle
A framework for deciding which companies and industries an investor understands well enough to judge their future cash flow.
concentrated-investing
An investing framework about putting a larger share of money into a small number of companies you understand well. It distinguishes concentrated investing from broad diversification used for general wealth management.