Berkshire
AI Berkshire — 基于巴菲特、芒格、段永平、李录四位价值投资大师方法论的投资研究 Skill 合集。提供五种研究工作流:深度综合分析、多Agent并行团队、买入前Checklist、行业产业链扫描、未上市公司研究。Triggers: investment research, stock analysis, value investing, 投资研究, 价值投资, 巴菲特, 行业研究, 未上市公司From its SKILL.md
npx -y skills add asong56/skills --skill berkshireAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 23 days oldThe repository was created 23 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
2.1 KB, 624 tokens by cl100k_base, as published. Nobody here has run it
Berkshire — AI 价值投资研究框架
五种投研工作流,每个都是独立的提示词文件,位于 skills/ 目录。使用时将对应文件内容作为指令,将公司/行业名替换 $ARGUMENTS。
工作流
| 文件 | 用途 | 适合场景 |
|---|---|---|
skills/investment-research.md | 四大师综合深度分析 | 对单个上市公司全方位研究(最全面) |
skills/investment-team.md | 多Agent并行投研团队 | 需要快速、多角度同时分析 |
skills/investment-checklist.md | 巴菲特买入前Checklist | 快速筛选,决定是否值得深入研究 |
skills/industry-research.md | 产业链全景扫描 | 研究一个行业/主题的所有投资机会 |
skills/private-company-research.md | 未上市公司深度研究 | 研究蚂蚁、SpaceX等未上市公司 |
选择指南
- 第一次接触一家公司 →
investment-checklist.md(快速判断值不值得深入) - 决定深入研究 →
investment-research.md(单Agent全面分析)或investment-team.md(多Agent并行,更快) - 研究一个行业而非单股 →
industry-research.md - 目标公司未上市 →
private-company-research.md
核心原则(所有工作流共享)
所有工作流都内置 AI研究偏见自觉:
- 资料多 ≠ 确定性高;资料少 ≠ 不好
- 信息丰富度分A/B/C级,影响研究策略
- 推算数据必须标注置信度,区分事实与推理
- 目标是识别好生意,不是填满报告模板
使用方法
1. 打开对应的 .md 文件
2. 将 $ARGUMENTS 替换为公司名/行业名
3. 将全文作为指令发送给 Claude
What ships with it: 5 files
52.6 KB alongside SKILL.md
skills/
- industry-research.md8.5 KB
- investment-checklist.md9.0 KB
- investment-research.md8.4 KB
- investment-team.md7.8 KB
- private-company-research.md18.9 KB