Investment Checklist logo

Investment Checklist

CommunityPopular
xbtlin
investment-checklist

AI Berkshire skill: 巴菲特价值投资买入前 Checklist. Source: skills/investment-checklist.md.

Overview

Publisherxbtlin
Repositoryai-berkshire
Skill nameinvestment-checklist
Stars
16.4K
Forks
2.5K
Bundled files
Instructions only
LicenseMIT
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

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

Installation

Install the Investment Checklist 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.
  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/xbtlin/ai-berkshire.git /tmp/ai-berkshire
mkdir -p .claude/skills
cp -r /tmp/ai-berkshire/codex-skills/investment-checklist .claude/skills/investment-checklist
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Investment Checklist 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 Investment Checklist 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 Investment Checklist 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.

Codex adapter note

This skill is generated from skills/investment-checklist.md so Claude Code and Codex users share one canonical workflow.

  • Treat $ARGUMENTS as the user's request in the current Codex thread.
  • When the source mentions Claude-only surfaces such as Task, Agent, WebSearch, Bash, Read, or Write, use the closest Codex capability available in this session: subagents when available, web search when needed, shell commands for local tools, and normal file edits for workspace files.
  • Use shared project tools from tools/ in this repository. Prefer running commands from the repository root with paths like python3 tools/financial_rigor.py ...; if the current thread starts outside the repo, locate the actual checkout path first instead of assuming a fixed home-directory path.
  • Before starting research, run the date command to confirm today's date; treat it as the baseline for "latest" data and state the data cutoff date in the report header. Never assume the current date from training data.
  • Preserve the research quality rules from AGENTS.md: cross-check financial data, use exact arithmetic tools for valuation/math, and clearly label uncertainty and source gaps.

巴菲特价值投资买入前 Checklist

对 $ARGUMENTS 执行巴菲特价值投资买入前 Checklist 分析。

支持输入格式:单个或多个公司,用逗号/顿号/空格分隔。例如:腾讯, 茅台, 英伟达NVDA AAPL MSFT

执行流程

第一步:解析输入,识别所有待分析公司

从 $ARGUMENTS 中解析出所有公司名称/代码。对每家公司确定:

  • 公司全称、股票代码、上市交易所
  • 如果公司未上市,标记为"未上市"并给出简要说明(是否有间接投资途径),跳过完整Checklist

第一步半:AI研究偏见预警

对每家公司进行"信息丰富度"快速评级(A/B/C),并在报告中标注:

等级判断标准对Checklist的影响
A级上市多年、数据充裕正常执行,但警惕"共识陷阱"——所有指标看起来都清晰不代表真的确定
B级数据有限需推算每个推算指标标注置信度,"好生意"判断加权考虑数据可靠性
C级信息极度稀缺不勉强填满六关表格,诚实标注"数据不足无法判断",聚焦可验证的核心问题

核心原则:Checklist的目标是排除坏选择。对于C级公司,"数据不足"不等于"不通过",也不等于"通过"——应诚实标注为"灰色地带,需补充一手信息",而不是因为AI无法填满表格就判为否决。

段永平说过:"看不懂"有两种——一种是生意太复杂真的看不懂,一种是你还没花时间去看。AI研究的局限是容易把"资料少"和"看不懂"混为一谈。

第二步:并行数据收集

使用 Task 工具为每家公司启动独立的后台 Agent 进行数据收集(所有公司同时并行启动),每个Agent负责收集:

  1. 盈利能力:ROE(5-10年趋势)、毛利率、净利率、自由现金流
  2. 估值数据:当前股价、市值、PE(TTM)、前瞻PE、PB、股息率
  3. 增长趋势:近3年收入/利润增速
  4. 财务健康:负债水平、资本开支需求、现金储备、净现金/净负债
  5. 竞争格局:市场份额、主要竞争对手、份额变化趋势
  6. 护城河证据:品牌/转换成本/网络效应/规模效应/技术壁垒的具体证据
  7. 管理层记录:CEO履历、关键决策、持股、资本配置记录
  8. 最新动态:近6个月重大事件(业绩、并购、监管、管理层变动等)

第三步:逐公司执行六关 Checklist

对每家已上市公司,依次过六关:


第一关:我能理解这门生意吗(能力圈)

必须回答:

  • 能用一句话说清楚这家公司靠什么赚钱吗?
  • 10年后大概率还在做什么生意?
  • 哪些关键变量决定成败?
  • 对这个行业的认知是来自深度研究还是道听途说?

评分标准(★1-5):

  • ★★★★★:商业模式极其简单清晰,10年确定性高(如茅台:酿酒卖酒)
  • ★★★★☆:模式清晰但有技术门槛,需要一定专业知识理解
  • ★★★☆☆:模式可理解但10年确定性不高,行业变化快
  • ★★☆☆☆:业务线复杂或行业剧变中,难以预判未来
  • ★☆☆☆☆:完全不在能力圈内

硬性否决:如果连赚钱方式都说不清,直接标记为"不在能力圈,不做分析"。


第二关:这是一门好生意吗(经济特征)

用数据说话,关键指标必须通过工具精确计算

bash
python3 tools/financial_rigor.py verify-valuation \
  --price {股价} --eps {EPS} --bvps {每股净资产} --fcf-per-share {每股FCF} --dividend {每股股息}
指标该公司数值参考标准判断
ROE(5年均值)>15%优秀, >20%卓越
毛利率>40%暗示定价权
自由现金流持续为正、≈净利润
资本开支强度轻资产优于重资产
负债水平有息负债/净利润<3年

评分标准(★1-5):

  • ★★★★★:ROE>25%、高毛利、强FCF、轻资产、低负债(全部达标)
  • ★★★★☆:4项达标
  • ★★★☆☆:3项达标
  • ★★☆☆☆:2项达标或趋势恶化
  • ★☆☆☆☆:多数不达标或FCF持续为负

第三关:护城河够不够深(竞争优势)

逐项检查:

护城河类型是否具备具体证据变宽还是变窄?
品牌/定价权
转换成本
网络效应
成本/规模优势
技术/专利壁垒

追加检验:如果给竞争对手100亿,能否复制这门生意?

评分标准(★1-5):

  • ★★★★★:多重护城河叠加且在变宽
  • ★★★★☆:至少一条强护城河且稳定
  • ★★★☆☆:有护城河但不够深,或趋势不明
  • ★★☆☆☆:护城河正在被侵蚀
  • ★☆☆☆☆:无明显护城河

第四关:管理层是否值得信任(人的因素)
检查项评估
诚实度(承诺vs交付)
资本配置能力(回购/分红/并购记录)
股东利益导向(持股、薪酬)
所有者心态(创始人 vs 职业经理人)
公司治理(关联交易、商誉、审计)
CEO离开后能否照常运转?

评分标准(★1-5):

  • ★★★★★:创始人掌舵、资本配置卓越、利益完全一致
  • ★★★★☆:管理层优秀但有小瑕疵
  • ★★★☆☆:管理层合格但有治理隐患
  • ★★☆☆☆:有诚信或治理问题
  • ★☆☆☆☆:严重诚信问题(→硬性否决)

第五关:价格是否足够便宜(安全边际)
指标数值历史分位判断
PE (TTM)
前瞻PE
PB
股息率
FCF Yield

追加检验(必须通过工具精确计算,禁止心算):

bash
python3 tools/financial_rigor.py three-scenario \
  --price {股价} --eps {EPS} --shares {股本亿} \
  --growth {乐观} {中性} {悲观} --pe {乐观PE} {中性PE} {悲观PE} --currency {币种}
  • 三情景下的估值区间(取工具输出结果)
  • 如果判断有误,在当前价格买入最多亏多少?
  • 股价腰斩你敢加仓吗?

评分标准(★1-5):

  • ★★★★★:相对内在价值打5折以下,极端安全边际
  • ★★★★☆:打7折,有良好安全边际
  • ★★★☆☆:合理估值,安全边际一般
  • ★★☆☆☆:偏贵,安全边际不足
  • ★☆☆☆☆:严重高估

第六关:仓位与决策纪律(防止情绪失控)

检查以下情绪信号:

  • 是否因为FOMO想买?
  • 是否因为别人推荐才想买?
  • 如果停牌5年你能接受吗?
  • 买入论述能否用200字以内写清楚?

第四步:镜子测试

对每家公司写出镜子测试语句:

"我以 ___元 买入 ___公司,因为:

  1. 这门生意的本质是___,我理解它;
  2. 它的护城河是___,而且在变宽/变窄;
  3. 管理层___,值得/不值得信赖;
  4. 当前价格相当于内在价值的___折,有/无足够安全边际;
  5. 即使我错了,下行风险可控/不可控,因为___。"

5句话说不完整 = 不买。 明确标注"通过"或"未通过"。


第五步:快速否决清单

对每家公司逐条检查,触发任何一条直接标注为"否决":

  • 说不清楚这家公司怎么赚钱
  • 连续3年自由现金流为负且看不到改善
  • 管理层有诚信污点
  • 竞争优势正在被不可逆侵蚀
  • 需要靠"下一个接盘者出更高价"来赚钱(博傻)
  • 无法承受这笔投资归零的后果
  • 买入理由主要是"别人都在买"或"最近涨得好"
  • 无法用200字以内写清楚买入理由

第六步:输出总览对比表(多公司时必须输出)

当分析多家公司时,必须生成对比总览表:

公司Checklist通过?能力圈好生意护城河管理层安全边际核心结论
★☆☆☆☆★☆☆☆☆★☆☆☆☆★☆☆☆☆★☆☆☆☆

第七步:最终结论与写入文件

对每家公司给出明确结论(不回避):

  • 通过 Checklist(X/6关)— 可以进入深度研究阶段
  • 未通过 Checklist — 说明哪条红线被触发
  • 灰色地带 — 说明关键争议点是什么,投资者需要自行判断什么
  • N/A — 未上市/无法买入

将完整报告写入 ~/巴菲特Checklist-[公司名或"多公司对比"].md

输出格式要求

  1. 每家公司独立成章,包含:六关评分表 + 核心数据表 + 关键风险(3-5条)+ 镜子测试 + 明确结论
  2. 多公司时在最后附总览对比表
  3. 所有评分必须使用★符号(★1-5),不含半星
  4. 数据必须标注来源时间,估计值必须注明"估计"
  5. 文末附结语,呼应巴菲特名言:"投资的第一条规则是不要亏损"
  6. 语言风格:直接、犀利、不说废话。用巴菲特/芒格/段永平的语录穿插点评

关键原则

  • 宁可错过,不可做错:Checklist的目标是排除坏选择,不是找到最好的
  • 诚实面对能力圈:看不懂就说看不懂,不要勉强分析
  • 安全边际是生命线:好公司买贵了也会亏钱
  • 镜子测试不可跳过:说不清楚理由就不买,没有例外

Frequently asked questions

What does the Investment Checklist AI skill do?

AI Berkshire skill: 巴菲特价值投资买入前 Checklist. Source: skills/investment-checklist.md.

Why use Investment Checklist on TypingMind?

Because you install it once and use it with any model. Investment Checklist 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 Investment Checklist in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/xbtlin/ai-berkshire/tree/main/codex-skills/investment-checklist. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Investment Checklist?

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 Investment Checklist?

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

Is the Investment Checklist AI skill free?

Yes. It is published on GitHub by xbtlin 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

Set up your own AI workspace now

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