💡 Summary
Best Minds simulates expert opinions by asking who knows best about a topic and mimicking their views.
🎯 Target Audience
🤖 AI Roast: “Powerful, but the setup might scare off the impatient.”
Risk: Low. Review: permissions, data flow, and dependency risk. Run with least privilege and audit before enabling in production.
name: best-minds description: 模拟器思维：不问"你怎么看"，而是问"世界上谁最懂这个？TA 会怎么说？"。触发词：最强大脑、顶级专家、世界级、best minds、谁最懂这个
Best Minds
"Don't think of LLMs as entities but as simulators." — Andrej Karpathy
核心
不要问 AI "你怎么看"。
要问：这个问题，世界上谁最懂？TA 会怎么说？
然后模拟那个人。
原则
- 问题决定人数 — 一个人够就一个，需要碰撞才多个
- 找真正最懂的 — 不是找"合适的"，是找"最强的"
- 基于真实 — 模拟要基于 TA 公开的思想、著作、言论
- 引用原话 — 尽可能用 TA 说过的话
vs ai-coaches
| ai-coaches | best-minds | |------------|------------| | 从 13 个预设智者选 | 从全世界找 | | 基于关键词匹配 | 基于问题本质 |
Pros
- Provides expert-level insights
- Encourages critical thinking
- Mimics real-world expert opinions
Cons
- May lack diverse viewpoints
- Dependent on available expert data
- Could misinterpret expert opinions
Related Skills
pytorch
S“It's the Swiss Army knife of deep learning, but good luck figuring out which of the 47 installation methods is the one that won't break your system.”
agno
S“It promises to be the Kubernetes for agents, but let's see if developers have the patience to learn yet another orchestration layer.”
nuxt-skills
S“It's essentially a well-organized cheat sheet that turns your AI assistant into a Nuxt framework parrot.”
Disclaimer: This content is sourced from GitHub open source projects for display and rating purposes only.
Copyright belongs to the original author Ceeon.