Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add kangarooking/duan-yongping-skill --skill dcf-valuationgit clone --depth 1 https://github.com/kangarooking/duan-yongping-skillWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/kangarooking/duan-yongping-skill/dcf-valuation)<a href="https://agentmods.dev/skills/kangarooking/duan-yongping-skill/dcf-valuation"><img src="https://agentmods.dev/badge/skills/kangarooking/duan-yongping-skill/dcf-valuation/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/kangarooking/duan-yongping-skill/dcf-valuation"><img src="https://agentmods.dev/badge/skills/kangarooking/duan-yongping-skill/dcf-valuation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00201 | $0.02984 |
| Opus 5 | $0.00101 | $0.01492 |
| Sonnet 5 | $0.00040 | $0.00597 |
| Haiku 4.5 | $0.00020 | $0.00298 |
Grade A, and why
dcf-valuation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
DCF思维估值法(未来现金流折现思维方式,含毛估估+封仓十年)
R — 原文 (Reading)
买股票就是买公司,买公司就是买公司的未来现金流折现,句号!未来现金流折现只是一种思维方式,只有在自己的能力圈范围内的公司,投资人才能毛估估看明白。没人真用公式的,至少剩者都是不用公式的。再次强调:未来现金流折现指的是一种思维方式,想用公式的请到学校去用哈。
— 段永平,第一章 投资的信仰 / 第五章 估值逻辑
I — 方法论骨架 (Interpretation)
- DCF是思维方式,不是公式。 估值的本质是回答"这家公司未来整个生命周期里能赚多少钱",而不是打开Excel建模型、调参数。芒格说从未见过巴菲特算过DCF,巴菲特自己也说没有计算内在价值的公式。
- 毛估估——"300斤的胖子不用秤"。 如果你需要按计算器才能算出便宜,那就不够便宜。估值只需"一眼看过去明显便宜"——姚明走进来,不用尺子就知道他很高。毛估估当然要考虑成长性,折现本身就是考虑成长性以后的结果。
- 封仓十年——用时间维度检验理解深度。 买入前问自己:如果股市关闭10年,你还愿意持有吗?"不打算拿10年的股票为什么要拿10天"不是真的要拿10年,而是检验你是否真正理解这家公司的未来。
- PE是倒后镜,E/E更诚实。 PE的分母是历史利润,不反映负债。通用汽车PE只有5倍却破产了。E/E(Enterprise Value / Earnings = 市值+负债-现金 / 利润)让投资者看到买下整家公司真正要花的钱。
- 估值是"功夫"——需要多年积累。 巴菲特5分钟决定投高盛,背后是50年理解的积累。估值能力等于对企业的了解深度,没有捷径。
A1 — 书中的应用 (Past Application)
案例 1: Yahoo DCF教学案例(分部估值法)
- 问题: Yahoo股价低迷,市场忽视其持有的大量资产(Yahoo日本、阿里巴巴集团股份)
- 方法论的使用: 段永平用"毛估估"分部加总:现金3 + 上市资产6.7 + Yahoo自身业务9.6(给12倍PE)= 每股约19.3美元。再加上"白送"的淘宝+支付宝(估500亿),Yahoo明显便宜。实际只花70亿就买到了整个Yahoo(扣除上市资产后)
- 结论: "怎么看都值30块钱",而当时价格远低于此
- 结果: 段永平大量买入Yahoo,后续阿里巴巴上市验证了判断
案例 2: 苹果估值(猜5年后利润500亿)
- 问题: 苹果2011年市值约3000亿,很多人觉得"涨太多了"不敢买
- 方法论的使用: 不看过去股价、不看PE,只问"苹果未来能赚多少钱"。判断苹果可能是地球上年利润最先过500亿美元的公司,5000亿市值非常合理。不看苹果曾经50亿的市值,只看"现在的盈利、账上的现金以及未来可能的盈利"
- 结论: "我觉得我买的价钱还很便宜"
- 结果: 2015年苹果净利润达534亿美元,验证了毛估估判断。段永平继续持有并预判10年内利润过1000亿
案例 3: 网易(没认真估值但一眼便宜)
- 问题: 网易2001年股价跌至不到1美元,处于低谷期
- 方法论的使用: "有个300斤的胖子走进来,不用秤就知道他很胖。" 段永平凭游戏行业经验,判断网易市值不到2000万美元却拥有庞大用户群和现金流潜力,一眼就看出便宜。"我买网易时可真没认真估过值"
- 结论: 不需要精确计算,明显便宜就买
- 结果: 持有8-9年,平均买入价约0.25(拆股后),大部分在30-35卖出,回报超100倍
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 正在用PE/PB等指标判断一只股票贵不贵,却越算越困惑——比如"PE只有8倍是不是很便宜"或"PE=50是不是太贵了"
- 试图建立DCF模型精算企业价值,纠结折现率和增长率的参数选取——打开了Excel却不知道填什么数字
- 面对一家理解其业务的公司,犹豫当前价格是否值得买入——"这家公司我看得懂,但不知道现在这个价格能不能买"
语言信号 (用户的话里出现这些就应激活)
- "这个PE多少倍,能不能买"
- "我算了一下DCF模型/现金流折现,结果是……"
- "这家公司便不便宜/值多少钱/怎么估值"
与相邻 skill 的区分
- 与
good-business(好生意识别法)的区别: 好生意识别判断的是"这是不是好生意"(定性),DCF思维估值判断的是"这个价格便不便宜"(定价)。先用good-business确认好公司,再用DCF思维判断价格。 - 与
opportunity-cost(机会成本决策框架)的区别: 机会成本解决的是"买了A还是买B"的比较问题,DCF思维解决的是"A本身值不值这个价"的绝对判断问题。DCF是机会成本的输入——你必须先知道A值多少钱,才能和替代选项比较。 - 与
capability-circle(能力圈决策框架)的区别: 能力圈判断的是"你能不能看懂这家公司",DCF思维要求你已经在能力圈内才能"毛估估"。看不懂的公司无法估值,直接跳过。
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 146 lines · 201 tokens per session scan A 55e35a236e15
dcf-valuation is a skill published in the GitHub repository kangarooking/duan-yongping-skill (48 stars, last pushed 4mo ago), licensed MIT. It adds 201 tokens to every session and 2,984 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
wealth-structure
A framework for thinking about wealth through ownership, responsibility, leverage, and avoiding risks that could end your progress.
dcf-valuation
Build Discounted Cash Flow (DCF) valuation models. Calculate intrinsic value with customizable assumptions. Generate professional valuation reports.
equity-valuation
A framework for creating a stock valuation workbook in Excel, the spreadsheet program used for financial models. It combines data checks, several valuation methods, company-quality scoring, risk analysis, and an investment conclusion.
cangjie-skill
A process for turning a book, course, podcast, interview, long video, or other long material into reusable instructions for an AI agent. It extracts methods and principles, checks them, and packages them as skills.
equity-deep-dive
A thorough single-equity deep dive — read the recent qualitative picture from the web, then ground it in fundamentals and health ratios, an intrinsic DCF with a sensitivity range, a comparable-company cross-check, and the analyst-consensus view.
dcf-valuation
Estimate a public equity's intrinsic value with a discounted-cash-flow model — pull fundamentals, set a discount rate via CAPM/WACC, project free cash flow, and discount it.