Look Through Earnings

Community

kangarooking

look-through-earnings

用户需要看穿会计数字，理解一个企业或投资组合的真实经济收益。特别适用于评估盈利质量、资本支出真实性、EBITDA误导。语言信号:"这家公司利润很高"/"EBITDA是多少"/"折旧算不算成本"/"自由现金流和利润为什么不一样" 不适用于:不需要财务分析的纯定性决策。

Overview

Publisher	kangarooking
Repository	`buffett-letters-skill`
Skill name	`look-through-earnings`
Stars	109
Forks	20
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 Look Through Earnings 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/buffett-letters-skill/tree/main/look-through-earnings
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.

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/buffett-letters-skill.git /tmp/buffett-letters-skill
mkdir -p .claude/skills
cp -r /tmp/buffett-letters-skill/look-through-earnings .claude/skills/look-through-earnings

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

Use it in TypingMind

Enable Look Through Earnings 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 Look Through Earnings 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 Look Through Earnings 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.

透视盈余（含所有者收益/反EBITDA）

R — 原文 (Reading)

"We feel that the undistributed earnings of companies we hold in large amounts are fully as important to us as those we report." (1978) "References to EBITDA make us shudder — does management think the tooth fairy pays for capital expenditures?" (2000)

I — 方法论骨架

两个核心概念合并为一个skill：

透视盈余: 真实经济收益 = 报告利润 + 被投资公司未分配利润份额 - 假设税款

会计只显示已收股息，但未分配利润也是你的（如果有控制权或长期持有）

所有者收益: 净利润 + 折旧摊销 - 维持性资本支出 ≠ EBITDA

折旧不是"非现金费用"——它是预付资本的回收
EBITDA忽略了维持竞争地位所需的真实资本支出

A1 — 书中的应用

案例: Apple的透视盈余

问题: 伯克希尔从Apple投资中获得多少？
使用: 2021年伯克希尔享有的Apple收益=$56亿，但仅收股息=$7.85亿
结果: 会计利润严重低估真实经济进展（差7倍）

A2 — 触发场景

分析一家利润高但资本支出也高的公司
评估一家控股/参股公司的真实盈利能力
有人用EBITDA估值——需要指出问题
理解为什么净利润和现金流差距很大

语言信号

"这家公司EBITDA很高"
"折旧不是现金成本"
"利润和现金流为什么差这么多？"
"未分配利润算不算我的？"

与相邻 skill 的区分

与 economic-moat 的区别：护城河分析企业竞争力，透视盈余分析企业真实赚钱能力

E — 可执行步骤

计算所有者收益 = 净利润 + 折旧摊销 - 维持性资本支出
- 完成标准：区分"维持性"vs"扩张性"资本支出
检查EBITDA陷阱
- 完成标准：如果EBITDA >> 所有者收益，标注"盈利质量存疑"
- 判停：如果EBITDA与自由现金流差距>50% → 发出警告
计算透视盈余（适用于有参股公司的情况）
- 完成标准：报告利润 + 按持股比例的未分配利润 - 假设税款

B — 边界

估计"维持性"vs"扩张性"资本支出需要判断——不同人可能得出不同结论
透视盈余对短期投资者意义不大（未分配利润可能永远不实现）
作者盲点：巴菲特有足够的控制权来确保未分配利润最终实现——散户没有

审计信息

验证通过: V1 ✓ / V2 ✓ / V3 ✓
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.json2 KB

Frequently asked questions

What does the Look Through Earnings AI skill do?

Why use Look Through Earnings on TypingMind?

Because you install it once and use it with any model. Look Through Earnings 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 Look Through Earnings in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/kangarooking/buffett-letters-skill/tree/main/look-through-earnings. 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 Look Through Earnings?

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 Look Through Earnings?

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

Is the Look Through Earnings 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

To Questionnaire

mattpocock

CommunityPopular

Turn a decision you can't fully answer into a questionnaire for someone else to fill in.

Wait What

Stop. That last message did not land: re-pitch it.

Get Search View Results

microsoft

OrganizationPopular

Get the current search results from the Search view in VS Code

React Sync

Build local React changes in the bundle variants consumed by Next.js, sync them into a local Next.js checkout, and test the resulting integration. Use when working on React changes that need…

Look Through Earnings

Overview