{"skill":{"slug":"think-like-warren-buffett","displayName":"Warren Buffet's Brain","summary":"Point-in-time Buffett-style company analysis for stocks, Berkshire case studies, and BUY/PASS verdicts. Use when the user wants a Buffett/Graham underwriting...","tags":{"buffet":"1.0.0","finance":"1.0.0","investing":"1.0.0","latest":"1.0.0","research":"1.0.0","warren":"1.0.0"},"stats":{"comments":1,"downloads":154,"installsAllTime":0,"installsCurrent":0,"stars":0,"versions":1},"createdAt":1775749828711,"updatedAt":1775750809508},"latestVersion":{"version":"1.0.0","createdAt":1775749828711,"changelog":"别再看一堆情绪流研报了。Buffett Oracle 做的是更狠也更干净的事: 先判断这到底是投资、投机，还是 TOO HARD，再用 Buffett + Graham 框架把公司一层层拆开。过不了硬门槛，直接 PASS；真有护城河，才继续往下看。\nStop drowning in hype, hot takes, and “maybe” calls. Buffett Oracle starts by asking the question most investors skip: is this actually an investment, a speculation, or just TOO HARD? Then it runs a strict Buffett + Graham workflow that filters weak businesses fast and only goes deeper when the company earns it.\n\n它不是只会讲故事。它会检查 7 个 hard gates，做护城河判断，要求安全边际写成数字，还会强制拿两个同业对照组出来打擂台。最重要的是，它遵守 point-in-time discipline: 只用当时公开的信息做结论，不拿后来的结果倒推装聪明。\nThis is not “story stock” analysis. It runs 7 hard gates, pressure-tests the moat, forces the margin of safety into numbers, and compares the company against two same-era controls. Most importantly, it follows strict point-in-time discipline: the verdict must be based only on what was public at the time, not hindsight cosplay.\n\n如果你想要的不是“哪只票会飞”，而是一套能长期复用、能解释、能审计、还能让 AI 少胡扯的研究系统，这就是那个包。少一点 hopium，多一点 underwriting。\nIf you want less “what moon next?” and more durable, reusable, auditable research logic, this is the package. Less hopium, more underwriting.","license":"MIT-0"},"metadata":{"os":null,"systems":null},"owner":{"handle":"yixiao1032-publish","userId":"s17cs8xqw468czzyyeckjaztds83y4sn","displayName":"yixiao1032-publish","image":"https://avatars.githubusercontent.com/u/269425625?v=4"},"moderation":null}