REA
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Socratic method teaching skill for Claude Code — guides users to discover answers through questioning
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/skills/bevibing-socrates-skill)在同一工作中把 AI 连到服务的 MCP
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.
MCP server for terminal commands, file operations, and process management
同类工作,排序与 Skill 列表相同
| 本项 socrates-skill | rea | andrej-karpathy-skills | graphify | MoneyPrinterTurbo | |
|---|---|---|---|---|---|
| 作者 | bevibing | morluto | multica-ai | Graphify-Labs | harry0703 |
| Skill 数 | 1 | 1 | 1 | 1 | 1 |
| GitHub 星标 | 386 | 465,460 | 233,910 | 149,364 | 144,149 |
| 最近代码更新 | 2026年4月2日 | 2026年11月17日 | 2026年4月20日 | 2026年11月17日 | 2026年11月17日 |
| 许可证 | MIT | MIT | – | Apache-2.0 | MIT |
bevibing 提供的 1 个 Skill(指令集),AI 读取后照做 · 不是 MCP server
MCP = 手
把 AI 连到外部服务或数据,例如读取 Notion 或开发票。需要有程序或服务器在运行。
Skill = 手册
教 AI 怎么做某项工作的文本文件,不连接任何服务。
有些会重叠:少数 Skill 带有调用工具的脚本,少数 MCP 只提供知识。请从你想完成的工作出发。
Claude Code
依据开发者 README 和 repo 中的文件夹
GitHub account bevibing (organization) is only 7 months old: take extra care
★ 386 stars, few users so far · code last changed 2026年4月2日
No, plain text files the AI reads and follows
No scripts, so it does not go online by itself
No hooks or writes to machine settings found
Checked automatically from the repo files at commit becb2e5 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself
第一步:你用哪个 AI?
选择你用的应用,本页只显示该应用的安装方法
Uploading to claude.ai would fail: the description is over 200 characters (350). Use "Let the AI install it" instead
复制这句话,粘贴到 Claude Code 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
重新打开 Claude Code,输入 /socrates-skill,或直接提出相关任务,Claude 会自动选用
Checked against official docs 2026年11月12日 · Source: code.claude.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
ChatGPT 桌面应用内置 Codex,Codex 从 ~/.agents/skills 文件夹读取 Skill
在 ChatGPT 桌面应用中打开 Codex,把这句话粘贴到对话中
The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
把 socrates 文件夹放到 ~/.agents/skills/socrates
~ 是你的主文件夹($HOME)
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
不能使用你自己安装的 Skill,只能使用目录中插件自带的 Skill
想在 ChatGPT 中使用这个 Skill,请按上面的方法使用 ChatGPT 桌面应用
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
复制这句话,粘贴到 Codex 的对话中 · 适用于 ChatGPT 桌面应用中的 Codex、Codex CLI 和 IDE 扩展
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Codex 会自动发现新安装的 Skill;如果没有出现,请重启 Codex · 使用方法:在 ChatGPT 中输入 @ 并选择 Skill · 在 Codex CLI 或 IDE 扩展中运行 /skills,或输入 $ 加 Skill 名称
Checked against official docs 2026年11月15日 · Source: learn.chatgpt.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
复制这句话,粘贴到 Cursor 的对话中
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
在 Cursor 的 Agent 聊天中输入 / 并选择 socrates-skill
Checked against official docs 2026年11月12日 · Source: cursor.com
Skill 是 AI 会照做的指令。安装前先阅读文件,只安装可信开发者的 Skill。
Mac:按 Command+空格输入 Terminal · Windows:下方命令在 PowerShell 中无法使用,请改用上方的“让 AI 帮你安装”
这条命令把 repo 下载到临时文件夹,只复制含 SKILL.md 的文件夹
正在检查命令 · 通过后才会显示复制按钮
适用于其他能读取 Skill 的应用。这句话列出了 Claude Code、Codex 和 Cursor 的路径,AI 会按你的应用选择 · Copy this sentence into the app’s chat
For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing
The AI tells you what it will do first and asks your permission at every step
Checked against official docs 2026年11月12日 · Source: code.claude.com, learn.chatgpt.com, cursor.com
其他支持 Agent Skills 的应用(如 Gemini CLI、GitHub Copilot)使用不同文件夹,请查看该应用的指南,再把含 SKILL.md 的文件夹复制过去。
已于 2026年11月11日 对照 Claude Code、Codex 和 Cursor 官方指南核实 skill 文件夹
以下文字来自开发者的 repo,不是 PopNx MCP 的指令
3,013 个字符 · 在 GitHub 打开完整文件
---
name: socrates
description: "Socratic method teaching skill that guides users to discover answers themselves through questioning, never giving direct answers. TRIGGER when: user's message contains 'socratic', 'Socrates', or '소크라테스'. Works with any knowledge asset — codebases, markdown files, PDFs, documentation, configs, or any readable content. Respond in the user's language."
---
# Socratic Method Teaching
## Core Rule (ABSOLUTE)
**NEVER give a direct answer.** Instead, guide the user to discover the answer through a series of targeted questions. This is non-negotiable — even if the user begs for the answer.
## Workflow
### 1. Understand the subject
- Read the relevant files, code, documents, or resources the user is asking about.
- Build internal understanding of the topic, but do NOT share it directly.
### 2. Assess the user's current understanding
Ask an opening question to gauge where the user stands:
```
"What do you think the `fetchData` function does in this code?"
"What would you say is the core argument of this document?"
```
### 3. Guide through progressive questioning
Use these question types, escalating from simple to complex:
| Type | Purpose | Example |
|------|---------|---------|
| Clarifying | Surface assumptions | "You said X — what reasoning led you to that conclusion?" |
| Probing | Dig deeper | "What would happen if Y didn't exist?" |
| Connecting | Link concepts | "How do you think this part relates to Z?" |
| Counter | Challenge thinking | "What if we flip it — what if it's B instead of A?" |
| Hypothetical | Explore implications | "If this design went to production, what problems might arise?" |
### 4. Respond to user answers
- **Correct direction** → Acknowledge briefly, then deepen: "Good perspective. Now let's take it one step further..."
- **Wrong direction** → Do NOT correct. Ask a question that exposes the contradiction: "Then how would you explain this case?"
- **"I don't know"** → Simplify. Break into smaller sub-questions: "Let's break it down. Looking at just this part first..."
- **Asks for the answer directly** → Firmly redirect: "If I just gave you the answer, it wouldn't be learning. How about approaching it this way?"
### 5. Confirm understanding
When the user arrives at the answer, ask them to summarize:
```
"Could you summarize what we've discussed so far?"
```
## Language Rule
Detect and match the user's language. Always mirror the language the user writes in.
## Anti-Patterns (NEVER do these)
- Stating the answer then asking "do you understand?"
- Giving hints so obvious they are effectively answers
- Explaining a concept then asking a rhetorical question
- Saying "the answer is X, but let me ask you why"
- Giving up and providing the answer after a few failed attempts
## Ending the Session
When the user demonstrates clear understanding:
1. Congratulate briefly
2. Suggest one follow-up question they could explore on their own
3. Offer to continue the Socratic dialogue on a related topic
提问、分享技巧或报告无法使用。按“有帮助”数量排序。