← ClaudeAtlas

moat-funnellisted

A gated, moat-first pipeline for judging whether a company is worth investing in as a long-term holding. Use it WHENEVER the user wants to screen, evaluate, vet, or research a specific company or stock for investment quality — e.g. "帮我看看这家公司值不值得投", "分析一下 X 的护城河", "这个标的能不能投", "screen this stock", "is X a good business", "run X through the funnel", or when they name a company and ask for an investment-quality judgment. Trigger even without the words "skill" or "funnel". It is NOT a research-report generator or buy/sell recommender — it runs a fixed nine-gate elimination funnel in strict order, HALTS at the first failed gate, and refuses to look at valuation until quality is proven. Do NOT trigger for simple factual or transactional queries — a stock price, a news headline, an earnings date, "what does X do" — those get a normal direct answer, not the funnel.
zhouwen-ai/moat-funnel · ★ 0 · Data & Documents · score 62
Install: claude install-skill zhouwen-ai/moat-funnel
# Moat-Funnel — 优秀公司筛选管线 (v2) ## What this skill is (and is not) This skill enforces **a single, non-reorderable elimination pipeline** for judging business quality. Its entire value is *discipline*: it makes you kill a candidate at the first failed gate and forbids you from rescuing a low-quality business with a cheap price, a strong management team, or any other unrelated strength. - It is **a decision-discipline executor**, not a research-report writer. - It outputs **a per-gate verdict**, not a balanced two-sided essay. - It produces **"passes / eliminated at stage N" judgments against a fixed rubric**, NOT buy/sell advice. State this boundary when relevant. The final call always belongs to the user; note you are not a licensed advisor. The methodology distills the shared core of Chris Hohn (TCI: moat-first, order locked), Buffett (circle of competence, margin of safety, owner mindset), and Duan Yongping (business model, 本分/integrity, punch-card concentration). **Four-master lens (mapped onto the sequential gates).** Each gate is voiced by a master, and the masters are designed to *conflict* — that tension is the anti-blind-spot mechanism: - **段永平** — 商业模式与本质 (gates 1–2): "这是不是一门对的生意?" - **巴菲特** — 护城河、管理层、安全边际 (gates 2, 5, 7): "壁垒深不深? 人可不可信? 够不够便宜?" - **芒格** — 逆向与颠覆 (gate 6): "它会怎么死?" - **李录** — 十年确���性与范式 (gate 6, and the trend field throughout): "十年后它还在吗?" Unlike a parallel scoring panel, moat-funnel runs these **sequentially and gates** rather than averaging them