Socrates logo

Socrates

Community
fainshare
socrates

Argument audit (苏格拉底诘问): external claim quality review via fact-check + symmetry + independence. Use when user says "审查这个论点", "苏格拉底", "socrates", "这个分析靠谱吗", "看空观点审查", "/socrates". 审查外部论点的质量(外审),与 feynman(内省自己的推理)互补。

Overview

Publisherfainshare
RepositoryLiam-Skills
Skill namesocrates
Stars
113
Forks
19
Bundled files
4
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 4 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by fainshare on GitHub. Read the source before you install it.

Installation

Install the Socrates AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/fainshare/Liam-Skills/tree/main/skills/socrates
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/fainshare/Liam-Skills.git /tmp/Liam-Skills
mkdir -p .claude/skills
cp -r /tmp/Liam-Skills/skills/socrates .claude/skills/socrates
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Socrates in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Socrates on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Socrates is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Socrates 苏格拉底诘问(外审)

"The unexamined argument is not worth accepting." — 改编自苏格拉底

概述

看空报告、第三方分析、市场观点——这些外部论点听起来有道理,但经得起推敲吗?

外部论点常包含两类问题:事实错误(数据引用错误、案例描述失真)和论证技巧(选择性对比、隐含假设不成立、对照组不匹配)。这两类问题比真正的风险更常见,也更难识别。

这个 skill 用苏格拉底诘问法的三维度审查外部论点:事实核查(论点中的事实声明准确吗?)、对称性检查(批评是否同样适用于对照组?)、独立性检查(去掉这条,其他论点还成立吗?)。每条论点给出质量评级(高/中/低)和建议(保留/降级/排除),输出审查报告。

边界:与太虚五转的分工

Skill审查对象方向问什么
feynman我的推理/产出内省我哪里可能自欺?
bayes我的结论验证结论经得起数据检验吗?
socrates外部论点外审对手的论证可靠吗?
debono被过度批判的命题回溯被否掉的东西有被忽略的价值吗?

边界保护

socrates 的输入必须是外部论点:

  • ✅ 看空报告、卖方分析、媒体报道、市场观点
  • ✅ 第三方的投资建议、行业分析、技术评估
  • ❌ 自己的推理过程(→ 路由到 feynman)
  • ❌ 自己的结论(→ 路由到 bayes)

如果检测到输入是"自己的推理"或"自己的结论",skill 会提示路由到 feynman 或 bayes。

三维度审查流程

外部论点输入
    ↓
Route Check: 外部/内部/结论?
    ↓ (外部)
Step 1: 事实核查(调用 bayes mode:fact_check)
    ↓
Step 2: 对称性检查(对照组是否同样受限?)
    ↓
Step 3: 独立性检查(去掉这条,其他论点还成立吗?)
    ↓
Quality Rating: 高/中/低 + 保留/降级/排除
    ↓
Audit Report: 审查报告(可选:与 thesis 交叉比对)

Step 1: 事实核查

问什么: 论点中的事实声明准确吗?

方法: 调用 bayes skill(mode: fact_check),仅做事实核查,不做预测分解。

典型案例:

  • ❌ "康方生物仅中国数据" → 事实核查发现 HARMONi 有 38% 非中国患者
  • ✅ "HARMONi-3 中期 PFS 未达显著性" → 事实核查确认

Step 2: 对称性检查

问什么: 这个批评是否同样适用于对照组/基准?

方法:

  1. 识别隐含的对比基准
  2. 测试同样的批评逻辑是否适用于基准
  3. 如果批评对双方都适用但只攻击一方 → 论证技巧

典型案例:

  • ❌ Brahmer 批评 HARMONi-6 人群特征(90% 男性、排除 75+ 岁)→ 对称性检查发现 K 药对照组同样受限
  • ✅ "K 药在真实世界高龄患者中效果下降" → 对称性检查发现这是独立弱点

Step 3: 独立性检查

问什么: 去掉这条论点,其他论点还成立吗?

方法:

  1. 检查这条论点是否依赖其他论点
  2. 测试去掉这条后,其他论点是否仍成立
  3. 如果链式脆弱(这条被否定会连带否定其他)→ 标记风险

典型案例:

  • ❌ "仅中国数据 → FDA 不会批准 → 商业化失败" → 独立性检查发现链式脆弱(FDA 已受理 BLA)
  • ✅ "成本失控 + 品位下降" → 独立性检查确认独立于其他论点

投资 Lens 适配

投资场景下,socrates 可作为 W/M cadence 的对抗性扫描工具:

持仓 bear case 搜索
    ↓
socrates 论证质量审查
    ↓
与 thesis 交叉比对
    ↓
更新 FC 或补充证据

调用示例:

bash
/socrates --argument "紫金矿业成本失控,品位从0.48%降至0.35%" \
          --source "雪球分析 2026-02-28" \
          --thesis-path "docs/portfolio/thesis/2899.HK/thesis.md"

使用示例

示例 1: 康方生物 bear case 审查

输入:

论点: "康方生物 HARMONi-6 仅中国患者,全球适用性存疑"
来源: Pharmaphorum 2026-06-24
上下文: 持仓 bear case 审查

输出:

markdown
## 苏格拉底诘问报告

### 1. 事实核查
❌ **部分准确**: HARMONi-6 确为中国试验,但 HARMONi(全球 III 期)有 38% 非中国患者(165 例),
且 BLA 已获 FDA 受理(PDUFA 2026-11-14)。

### 2. 对称性检查
⚠️ **论证技巧**: Brahmer 批评 HARMONi-6 人群特征(90% 男性、排除 75+ 岁),
但 K 药对照组同样受限于相同入组标准。这是选择性攻击而非独立弱点。

### 3. 独立性检查
⚠️ **链式脆弱**: "仅中国数据 → FDA 不会批准 → 商业化失败" 的推理链在第一步就被否定
(FDA 已受理 BLA)。

### 综合评估
- 质量评级: **低**
- 建议: **排除**
- 理由: 事实部分错误 + 论证技巧 + 链式脆弱

### 与 thesis 交叉比对
- 已覆盖: 是(thesis §3.2 已讨论 HARMONi 全球试验)
- 覆盖深度: 充分
- 行动建议: 无需行动,但可补充 Brahmer 批评的对称性分析作为防御论据

触发词

  • socrates
  • 苏格拉底
  • 诘问
  • 审查这个论点
  • 这个分析靠谱吗
  • 看空观点审查
  • bear case audit
  • /socrates

文件结构

socrates/
├── SKILL.md                    # 本文件
├── agents/
│   └── interface.yaml          # 输入输出接口
├── references/
│   ├── lens-investment.md      # 投资 lens 适配
│   └── socratic-method.md      # 苏格拉底诘问法理论基础
└── evals/
    └── akeso-bear-case.json    # 康方生物 bear case 审查案例

下一步迭代方向

  1. 多论点并行审查: 支持批量审查多个论点,生成综合报告
  2. 论点图谱: 构建论点间的依赖关系图,识别链式脆弱性
  3. 自动 bear case 搜索: 集成 WebSearch,自动搜索持仓的 bear case 并审查

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Socrates AI skill do?

Argument audit (苏格拉底诘问): external claim quality review via fact-check + symmetry + independence. Use when user says "审查这个论点", "苏格拉底", "socrates", "这个分析靠谱吗", "看空观点审查", "/socrates". 审查外部论点的质量(外审),与 feynman(内省自己的推理)互补。

Why use Socrates on TypingMind?

Because you install it once and use it with any model. Socrates is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Socrates in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fainshare/Liam-Skills/tree/main/skills/socrates. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Socrates?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Socrates?

As many as you like. As long as a model supports skills, you can use Socrates with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Socrates AI skill free?

It is published on GitHub by fainshare. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇