xbtlin/ai-berkshire: README-based editorial guide

xbtlin/ai-berkshire describes itself in the README as "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.". This article keeps to facts that can be checked in the repository. Stars, forks, and promotional badges are signals of attention, not proof of quality. Under "AI Berkshire - AI 时代的价值投资研究框架", the README says: > "Price is what you pay, value is what you get." , Warren Buffett > > 用 AI 重新定义投资研究的深度与效率。. That establishes the project's stated boundary, not a production test.

The README's "整体架构" section gives a useful starting point for deciding whether the project fits: Agent 层：团队型 skill（如 /investment-team、/earnings-team）由 Team Lead 并行调度 4 个大师视角 Agent,,各自独立搜索、独立判断、互相挑战，最后综合研判；轻量 skill 不经过这一层，直连工具快进快出. If that problem is not yours, popularity is a poor reason to adopt it. Project names, commands, and component names are kept as written so a reader can return to the primary source without guessing at terminology. Another checkable README item is: Skill 层：把"你要做什么"抽象成 20 个明确入口,,深度研究、财报分析、行业筛选、持仓管理、思维工具，按场景选用. It can shape a first test, but it does not replace testing in the intended environment.

The operating model is spread across sections such as "AI Berkshire - AI 时代的价值投资研究框架". The source evidence includes: > 📮 仓库是全量框架，公众号是精选。 真正值得深研的公司，加上报告之外我自己的判断与取舍，都在微信公众号「复利炼丹炉」,,扫码关注 ↓. This article does not turn missing architecture, performance, or security details into claims. A real deployment still needs a look at the repository layout, configuration files, and release history.

Start installation from the README's documented entry point. A command that can be checked in the source is: npm install -g @anthropic-ai/claude-code When the README contains no runnable command, this article does not invent one. Open its "Real Track Record" section and confirm system dependencies, default ports, and first-run initialization before using a public server.