Judgment Training

Q: What does the Judgment Training AI skill do?

当用户需要做方向性判断、评估「该往哪走/这事靠谱吗」、或想提升决策能力时调用。 核心理念: 判断力(知道行为长期后果)比努力重要; 清晰思考=从基础学科重建推理; 收集心智模型(复利/委托代理/可证伪性/基础数学)。 不适用于: 需要立即执行的具体任务步骤。 Triggers: 判断力/方向/第一性原理/心智模型/思维模型/判断靠不靠谱/judgment/mental model/first principles

CommunityPopular

kangarooking

judgment-training

当用户需要做方向性判断、评估「该往哪走/这事靠谱吗」、或想提升决策能力时调用。核心理念: 判断力(知道行为长期后果)比努力重要; 清晰思考=从基础学科重建推理; 收集心智模型(复利/委托代理/可证伪性/基础数学)。不适用于: 需要立即执行的具体任务步骤。 Triggers: 判断力/方向/第一性原理/心智模型/思维模型/判断靠不靠谱/judgment/mental model/first principles

Overview

Publisher	kangarooking
Repository	`cangjie-skill`
Skill name	`judgment-training`
Stars	10.2K
Forks	1.2K
Bundled files	2
License	MIT
Links	Skill source Repository

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.
2 bundled files
Scripts, templates, and references the model can read while it works. Files are read-only and never executed.
Open source
Published by kangarooking on GitHub. Read the source before you install it.

Installation

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

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.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
Enable the skill in any chat where you want it available.

Store

Installed

Skills

Add skills

Import one or more skills from a public GitHub folder or a local .skill or .zip archive, or SKILL.md file.

From GitHub URLFrom .skill, .zip, or SKILL.md

GitHub repo or folder

https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/judgment-training

Points to a single skill folder, or any folder that contains multiple skills. Public repos only.

CancelContinue

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

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/kangarooking/cangjie-skill.git /tmp/cangjie-skill
mkdir -p .claude/skills
cp -r /tmp/cangjie-skill/books/naval-almanack-skill/judgment-training .claude/skills/judgment-training

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Judgment Training 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 Judgment Training 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 Judgment Training 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.

判断力训练

R — 原文 (Reading)

努力工作的价值真的被高估了。在现代经济中，努力工作不是那么重要。那什么被低估了？判断力。……真正聪明的思考者是思维清晰的思考者。他们理解非常非常基本的基础知识。……如果你不能根据需要从基础知识重新推导出概念，你会迷惑不解。你只是熟记而已。

— 纳瓦尔·拉维坎特, 《纳瓦尔宝典》第一章·财富

I — 方法论骨架 (Interpretation)

判断力=知道行为长期后果并据此决策的能力，它是杠杆时代最重要的生产力—— 一个正确的决定可以赢过大量低效努力，而错误方向上的努力只会放大损失。训练判断力有三个路径： ① 从基础重建——真正理解=能从头推导；高级概念无法推导就只是熟记；最聪明的人能把事情向小孩讲明白； ② 打牢基础学科——数学、微观经济学、可证伪性等是「严肃知识」，比背诵复杂概念更值钱； ③ 收集心智模型——复利、委托代理、黑天鹅、进化论等模型库，遇到新问题先找合适的模型套用； ④ 留出思考空白——每周至少一天不安排会议，伟大的想法只在你无聊之后出现。

A1 — 书中的应用 (Past Application)

案例 1: 费曼三页纸讲数学

问题: 如何判断一个人是否真的懂
方法论的使用: 费曼从数字→计算→初级微积分，用不打破的逻辑链串起来，不靠定义
结论: 能重建逻辑链才是真懂
结果: 「如果你无法向小孩子讲明白，那么你并不是真的知道」

案例 2: 每周留白思考

问题: 忙碌挤掉了思考时间
方法论的使用: 每周留一两天不安排会议
结论: 「只会在你感到无聊之后，才会有伟大的想法」
结果: 判断力和好想法随之而来

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

方向选择：「这件事该不该做/往哪走」
评估言论：「这个专家的说法靠谱吗/是真懂还是包装」
学习新领域：「怎么快速建立对陌生领域的判断力」
决策前检查：「我的依据能不能从头推导」

语言信号

"帮我判断一下/评估一下"
"他怎么知道自己在说什么"
"我想提升自己的判断力/思维模型"
"how to think clearly / build judgment / is this credible"

与相邻 skill 的区分

与 decision-heuristics 的区别: 本 skill 是底层能力训练；决策启发式是即用规则
与 rational-buddhism 的区别: 本 skill 讲如何想清楚；理性佛教是验证一切主张的总标准

E — 可执行步骤 (Execution)

识别决策类型与后果尺度
- 完成标准: 明确这是方向判断（长期后果大）还是执行选择（后果小）；判断力优先投入前者
从基础重建核心假设
- 完成标准: 把问题拆到「我能从头解释」的公理层；解释不了的部分标为未知
- 判停条件: 若发现对方/自己满口大词但无法推导，标记为「不可信」，停止采信
套用已知心智模型
- 完成标准: 至少匹配 1–2 个模型（复利/委托代理/可证伪性/黑天鹅…）交叉检验结论
预留思考留白
- 完成标准: 每周安排 ≥1 天无会议/无任务，把最难的问题放进留白时段

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

用户只需要快速执行步骤（先执行，再复盘判断）
信息查询类问题（查资料不需要完整推导）

作者在书中警告的失败模式

熟记≠理解: 「如果你不能根据需要从基础知识重新推导出概念，你会迷惑不解」
读错次序的博学: 虚假基础会过滤一切新想法

作者的盲点 / 时代局限

「基础学科优先」隐含理性人假设，未覆盖情绪/直觉在决策中的作用
判断力训练无法替代经验；作者自己也说判断力需要经验打底

容易混淆的邻近方法论

reading-metaskill: 阅读是判断力的供给管线

审计信息

验证通过: V1 ✓ / V2 ✓ / V3 ✓ (v06)
测试通过率: 见 test-results.md
蒸馏时间: 2026-08-01

Bundled files

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

test-prompts.json2 KB
test-results.md1 KB

Frequently asked questions

What does the Judgment Training AI skill do?

Why use Judgment Training on TypingMind?

Because you install it once and use it with any model. Judgment Training 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 Judgment Training in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/cangjie-skill/tree/main/books/naval-almanack-skill/judgment-training. 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 Judgment Training?

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 Judgment Training?

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

Is the Judgment Training AI skill free?

Yes. It is published on GitHub by kangarooking under the MIT license. 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

Add App Clip

sickn33

CommunityPopular

Add an iOS App Clip target to an Expo app. Use when the user mentions App Clip, AASA, apple-app-site-association, appclips, smart app banner, or wants to ship a lightweight iOS Clip invoked from a URL…

Advogado Criminal

Advogado criminalista especializado em Maria da Penha, violencia domestica, feminicidio, direito penal brasileiro, medidas protetivas, inquerito policial e acao penal.

Advogado Especialista

sickn33

CommunityPopular

Advogado especialista em todas as areas do Direito brasileiro: familia, criminal, trabalhista, tributario, consumidor, imobiliario, empresarial, civil e constitucional.

Cqrs Implementation

Implement Command Query Responsibility Segregation for scalable architectures. Use when separating read and write models, optimizing query performance, or building event-sourced systems.

Judgment Training

Overview