ai-berkshire

View on GitHub

AI 时代的伯克希尔：基于 Claude Code / Codex 的价值投资研究框架。巴菲特·芒格·段永平·李录四大师方法论 + 多Agent并行研究。| AI-era Berkshire: a value investing research framework built for Claude Code / Codex. 4 masters' methodologies + multi-agent adversarial analysis.

★ 16K2,460 forksHTMLMITxbtlin

A pack of 20 Claude Code / Codex skills that turns a coding agent into a value-investing research team: four-master methodologies (Buffett, Munger, Duan Yongping, Li Lu), multi-agent parallel and adversarial analysis, financial-data verification tools, and reproducible report workflows.

Use Cases

Deep single-company investment research with multi-agent parallel analysisReading and analyzing earnings reports from primary filingsScreening industries or indices with funnel and quality filtersPortfolio construction, concentration and rebalancing reviewTracking whether an investment thesis has been invalidated or driftedExplaining sharp stock price moves within minutesResearching private/unlisted companies with scarce dataCross-verifying market cap and financial figures with Python scriptsGenerating publishable investment research articlesApplying Buffett/Munger/Duan Yongping/Li Lu mental models to any business question

Built With

Language: HTML
Frameworks: Claude Code · OpenAI Codex · MCP · Python

ai-berkshire

Use Cases

Built With

Tags