Rational Buddhism Verifier
Helps you judge which spiritual or metaphysical claims to trust, using falsifiability and personal testing.
- Repository
- kangarooking/cangjie-skill
- Stars
- 11,998
- Licence
- MIT
- Files
- 3 files
What it does
This is a reasoning guide, not a tool. When you ask an AI agent whether a spiritual, metaphysical or wellness claim is worth believing, the agent follows a framework taken from Naval Ravikant's book: test things yourself, stay skeptical, keep what works, and discard claims that cannot be checked or disproven. It also helps you draw a line between useful inner practices such as meditation and untestable beliefs such as karma or chakras.
Great for
- People weighing up a spiritual practice or wellness claim who want a structured, evidence-minded way to decide
- Readers who enjoy meditation but want to separate its practical benefits from metaphysical claims
- Anyone building a personal list of beliefs with a note on the evidence behind each one
Skip it if
- Someone grieving or dying who wants religious or spiritual comfort; the skill itself says it should not be used there, since it would push a rationalist view on a personal faith choice
- Questions about literature, love or meaning, which the source says cannot be judged by a falsifiability standard
- Medical decisions: the skill does not check clinical evidence and should not replace a doctor's advice
Try asking
- “Is the idea that chakras affect health something I should believe? How could I test it?”
- “Help me design a 30-day self-test for a meditation routine and track the changes.”
- “Does science conflict with meditation? Walk me through a rational approach.”
- “Help me write three personal beliefs with the evidence level noted for each.”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 3 original files, the MIT licence and an attribution note.
rational-buddhism.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip rational-buddhism.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip rational-buddhism.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Write your question as a specific claim (e.g. 'Does X improve Y?') so the agent can apply the falsifiability test rather than give a general opinion.
- Ask for the agent's reasoning to be shown, so you can check the evidence standard it applied.
- The source text is in Chinese; writing your request in Chinese may get more precise results, though English triggers are also listed.
What's inside
- SKILL.md
- test-prompts.json
- test-results.md
Redistributed unmodified from kangarooking/cangjie-skill under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.