Right Things First

Community

kangarooking

right-things-first

当用户面临方向性决策纠结时使用——先判断方向对不对，再考虑怎么做好。典型触发：用户说"我在纠结要不要做XX""做了很久但效果不好""方向对不对""值不值得坚持""是方向问题还是执行问题"。核心框架："做对的事情"（方向判断，道）vs "把事情做对"（执行效率，术），二者不可颠倒。不适用于：纯执行层面的问题（已经有了正确方向，只需要方法）、日常小事。

Overview

Publisher	kangarooking
Repository	`duan-yongping-skill`
Skill name	`right-things-first`
Stars	57
Forks	13
Bundled files	1
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.
1 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 Right Things First 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.
https://github.com/kangarooking/duan-yongping-skill/tree/main/business-logic/right-things-first
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/duan-yongping-skill/tree/main/business-logic/right-things-first

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/duan-yongping-skill.git /tmp/duan-yongping-skill
mkdir -p .claude/skills
cp -r /tmp/duan-yongping-skill/business-logic/right-things-first .claude/skills/right-things-first

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

Use it in TypingMind

Enable Right Things First 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 Right Things First 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 Right Things First 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.

"做对的事情"二元决策框架

R — 原文 (Reading)

"做对的事情，把事情做对。知道要做对的事情（或者说，知道什么样的事情不该做），然后去追求高效率把事情做对的公司。"

— 段永平, 第1节

"做对的事情就是发现是错的事情时要马上停止，不管多大的代价都是最小的代价。"

— 段永平, 第3节

I — 方法论骨架 (Interpretation)

这是一个将决策分为两个维度的框架：

维度一："做对的事情"（道/方向）

只有对错，没有程度——要么方向对，要么方向错
判断方法：用排除法——知道什么"不对"比知道什么"对"更容易
发现错了立刻停，此刻的代价永远是最小的

维度二："把事情做对"（术/执行）

有高低之分，是学习过程——可以越做越好
需要时间、经验和迭代

核心原则：顺序不可颠倒

方向错了，执行越好结果越差（在错误的道路上跑得越快离目标越远）
"坚持到底"指的是坚持做对的事情，不是坚持做错的事情
难点不在知道什么是对的——人们往往知道什么不对，但短期诱惑让人明知故犯

配套思维工具：

从否定面判断法：判断"对"很难，判断"不对"相对容易
"不本分"反推法：不确定是否本分时，先看是否不本分

A1 — 书中的应用 (Past Application)

案例 1: 步步高退出VCD做手机

问题: VCD业务在衰退，要不要继续？
方法论的使用: 先问方向——VCD是夕阳行业，继续投入是"把错的事情做对"。手机是新的长坡，方向对了
结论: 停止VCD，全力做手机
结果: OPPO/vivo成为全球前五手机品牌

案例 2: 投资GE vs 苹果

问题: 段永平投资了GE后反思
方法论的使用: 买了GE后发现自己"理解并不是很透"——这本身就是方向性怀疑。而苹果是他"能真的理解的公司"——方向确认
结论: 如果重来，不会买GE而是买苹果
结果: 苹果投资成为段永平最成功的投资之一

案例 3: 判断管理层——从否定面入手

问题: 如何判断一个领导层是否"对"？
方法论的使用: "很难判断是否'对'，但相对容易判断是否'不对'"
结论: 不对的就不碰，错误的概率大幅度降低
结果: 段永平用此法避开了大量问题公司

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?

用户在纠结一个重大决策，列了很多理由但心里没底
用户在一个方向上投入了很多但效果不好，不确定该坚持还是转向
用户面临诱惑——一个方向"不对"但短期回报很高
用户在问"我该不该做XX"——在做方向性判断
用户在分析失败原因，区分"方向错误"和"执行不足"

语言信号 (用户的话里出现这些就应激活)

"我该不该做XX" / "要不要XX"
"方向对不对"
"值不值得坚持"
"我已经投入了这么多，放弃是不是浪费"
"是方向问题还是执行问题"
"怎么做才能成功"（隐含方向判断未完成）

与相邻 skill 的区分

与 stop-doing-list 的区别: 本 skill 是底层哲学（"为什么要先判断方向"），stop-doing-list 是操作工具（"具体不做什么"）
与 profit-above-pursuit 的区别: 本 skill 是通用的方向判断框架，profit-above-pursuit 是"做对的事情"在企业价值观层面的具体诊断

E — 可执行步骤 (Execution)

先判断方向——这是"做对的事情"吗？
- 完成标准: 用排除法回答"这有什么是不对的？"如果发现不对的地方，立刻标记
- 判停条件: 如果方向明确不对 → 停止，不管已投入多少。不要进入步骤2
如果是方向对的，评估执行——怎么"把事情做对"？
- 完成标准: 列出3-5个关键执行要素，标出当前做得好和做得不好的
- 注意: 这一步只在方向确认后才做
设置方向纠错检查点
- 完成标准: 明确"什么信号出现时说明方向可能错了"，以及对应的叫停机制
- 关键原则: 发现错了的瞬间，代价最小

B — 边界 (Boundary) ★

不要在以下情况使用此 skill

纯执行层面的问题（方向已定，只需要方法）
日常小事（不需要做方向性判断）
信息不充分的决策（需要先收集信息再判断方向）

作者在书中警告的失败模式

明知故犯: "人们往往知道什么是不对的，但不认为它会造成致命后果"——知道方向不对但短期诱惑太大
把"坚持"当万能药: "坚持到底"指的是坚持做对的事情，很多人拿它来合理化继续做错的事情
沉没成本陷阱: 已经投入了很多所以不愿转向——但这恰恰是代价最大的时候

作者的盲点 / 时代局限

"做对的事情"听起来简单但判断"什么是对的"本身可能极难——段永平的判断力来自数十年经验，普通人未必具备
有时候"方向对不对"要到事后才知道——事前判断需要极强的洞察力或运气

容易混淆的邻近方法论

第一性原理思维: 第一性原理从根本事实推演，本框架用排除法逼近——路径不同但都追求回到本质
OKR/目标管理: OKR管理"做什么"和"怎么衡量"，本框架先判断"该不该做"——是前置过滤器

审计信息

验证通过: V1 ✓ / V2 ✓ / V3 ✓
测试通过率: {{%}} (详见 test-prompts.json)
蒸馏时间: 2026-04-16

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.json8 KB

Frequently asked questions

What does the Right Things First AI skill do?

Why use Right Things First on TypingMind?

Because you install it once and use it with any model. Right Things First 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 Right Things First in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/duan-yongping-skill/tree/main/business-logic/right-things-first. 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 Right Things First?

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 Right Things First?

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

Is the Right Things First 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

Faq Collector

CherryHQ

OrganizationPopular

将成功解决的用户问题收录到 FAQ 知识库。问题解决后自动判断是否收录。也可以在用户说"收录到 FAQ"、"记录这个问题"、"add to FAQ"时手动触发。

Issue Reporter

只在用户明确要求提交 GitHub Issue、GitHub Bug Report 或 GitHub Feature Request 时使用。用户只说“提交问题”“提交反馈”“上报 bug”“这是个 bug”或描述功能建议但未点名 GitHub 时不得触发，必须改用 cherry-studio-feedback 并默认提交飞书。

Skills Manager

搜索、安装和协调创建 Claude Code Agent Skills。当用户想要搜索技能、安装工具、创建自定义 Skill，或者说"find a skill"、"搜索技能"、"帮我做个 skill"、"create a skill"时触发。也适用于用户说"有没有做 X 的工具"、"我想扩展 Agent 能力"，或当前能力不足需要先查找可复用方案的场景。

Cli Anything 3mf

3MF mesh geometry editor — detect and resize cylindrical holes, repair meshes, compare 3D printing files. Works with BambuStudio and PrusaSlicer 3MF files.

Right Things First

Overview