homeopathy-researcher
Expert debunker of homeopathic claims. Use when explaining why homeopathy is placebo, teaching about clinical trials, or demonstrating how alternative medicine marketing works.
- License 许可
- MIT
- 最近更新
- 2026-11-12
- Stars
- ★ 2
- Forks
- 0
01 前言 Front Matter
- name
- homeopathy-researcher
- license
- MIT
- metadata
- { "exposes": "placebo-effect", "category": "parody", "educational": true }
- description
- Expert debunker of homeopathic claims. Use when explaining why homeopathy is placebo, teaching about clinical trials, or demonstrating how alternative medicine marketing works.
03 SKILL.md 正文
Homeopathy Researcher
Scientific guide to homeopathy - explaining why dilution to nothing can't cure disease.
Overview
Homeopathy claims that substances causing symptoms can cure those symptoms if diluted to extreme levels (often no molecules remaining). This skill explains why this violates basic chemistry and physics.
The Core Claim
Homeopathy principle:
- "Like cures like" (law of similars)
- More dilution = more potent (law of infinitesimals)
- Water has memory of dissolved substances
Why It's Nonsense
The Math of Dilution
30C dilution (common in homeopathy):
- C = centesimal (1:100 dilution)
- 30C = (1:100) × 30 times
- = 1:10^60 dilution
What this means:
- To get ONE molecule of active ingredient
- You'd need a sphere of water 93 billion light-years in diameter
- Observable universe is only 93 billion light-years across
- There's literally NOTHING in the pill!
Avogadro's Number
12C is the limit:
- Beyond 12C dilution, statistically zero molecules remain
- Avogadro's number: 6.022 × 10^23
- Homeopathy uses 30C, 200C, even 10,000C
- It's just water (or sugar pills)
Water Memory Claim
If water remembered what it touched:
- It remembers poop (sewage treatment)
- It remembers dead fish
- It remembers industrial waste
- Why only remember the "medicine"?
Also:
- Water molecules exchange hydrogen bonds trillions of times per second
- No mechanism for "memory"
- Violates thermodynamics
The Evidence
Clinical trials:
- Systematic reviews show homeopathy = placebo
- When blinded properly, no effect
- Effect size exactly matches placebo
- No biological plausibility
Why people think it works:
- Placebo effect is real (but not due to homeopathy)
- Regression to the mean (things get better naturally)
- Post hoc ergo propter hoc fallacy
- Confirmation bias
The Harm
Seems harmless, but:
- Delays real treatment
- Expensive (charging for sugar pills)
- False hope
- Anti-vaccine movements often overlap
- Undermines scientific literacy
Educational Use
Use this skill to:
- Teach scientific method
- Explain placebo effect
- Demonstrate critical evaluation of health claims
- Understand clinical trial methodology
- Practice skeptical thinking
Note: Respect people's experiences (placebo effect is real) while explaining why homeopathy itself doesn't work beyond placebo.
04 同仓库更多 Skills
Docs Research
Use MCP Central Docs server to search, ask, and retrieve documentation (FastMCP, standards, packaging).
wrappee-drift
Read-only, single-repo audit of a repo's tool coverage against the software it wraps (its current real API/docs, not training-data memory) and against comparable/competing wrappers. Trigger when the user says "wrappee drift" followed by a repo name, "capability audit" followed by a repo name, or asks whether a repo is missing features the wrapped software or a competitor now has. Always scoped to one named repo per invocation -- never trigger this fleet-wide or unprompted; that is explicitly against the SOP. Do NOT trigger for internal fleet-standard compliance (that is drift-scan) or strategic worth/archive decisions (that is quality-check) -- this is specifically about the gap between the repo's tool list and the wrapped software's/competitors' actual current capabilities.
modules
暂无简介
mcp-standards
Use when developing MCP servers to access comprehensive standards for scaffolding, packaging, sampling, documentation, testing, error handling, monitoring, and CI/CD workflows.
webapp-cua-test
Run the pre-Tauri CUA click-through test (real browser, dev stack, OCR "Connected" wait, sidebar nav walk) for a fleet MCP server repo under D:\Dev\repos. Trigger when the user says "cua webapp test" or "webapp clickthrough" followed by a repo name, asks for an e2e click-through of a webapp, or asks whether a webapp boots and connects in a real browser. Not for the installed NSIS app (that is the nsis-build skill / cua-nsis-test) and not for DOM assertions (Playwright), and not for hunting fake data or dead buttons (fakefind).
ship
Final release gate for a fleet MCP server repo under D:\Dev\repos -- run all quality gates, build the release artifact, verify it, commit, push, and cut a GitHub release. Trigger this whenever the user says "ship it", "ship" followed by a repo name, "release" followed by a repo name, or asks to finalize and publish work that's already been done in a repo. This is the terminal step after assfix/nsis-build, not a substitute for them -- if the repo hasn't been assessed recently, say so before shipping rather than shipping blind.