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 capability-circlegit 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/capability-circle)<a href="https://agentmods.dev/skills/kangarooking/duan-yongping-skill/capability-circle"><img src="https://agentmods.dev/badge/skills/kangarooking/duan-yongping-skill/capability-circle/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/capability-circle"><img src="https://agentmods.dev/badge/skills/kangarooking/duan-yongping-skill/capability-circle.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 | $0.00168 | $0.02989 |
| Opus 5 | $0.00084 | $0.01494 |
| Sonnet 5 | $0.00034 | $0.00598 |
| Haiku 4.5 | $0.00017 | $0.00299 |
Grade A, and why
capability-circle 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 9d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
能力圈决策框架(含安全边际=理解度)
R — 原文 (Reading)
"能力圈"的意思就是你能够判断未来现金流折现的范围。知道自己的"能力圈"有多大比"能力圈"本身有多大要重要的多。 我觉得 margin of safety 实际上应该指的是能力圈而不仅仅是价格。 能力圈是:诚实对自己,知之为知之,不知为不知。有这样的态度,然后如果能看懂一个东西,那它就是在我能力圈内,否则就不是。
— 段永平, 第一章 投资理念 / 第三章 谈能力圈与原则
I — 方法论骨架 (Interpretation)
能力圈不是"熟悉的行业"——它是你能判断一家公司未来 5-10 年现金流的大致范围。行业经验不等于能力圈:医生懂药理不等于能判断创新药的商业前景。
段永平对安全边际做了一个根本性的重新定义:安全边际不是价格折扣(买得够便宜),而是你对这家公司商业模式的理解深度。从 10 年角度看,买入价比最低点贵 30% 影响不大,但如果看错了公司,亏的是 100%。因此仓位大小应反映理解度,而非价格便宜程度。
知道能力圈的边界比能力圈本身的大小更重要。不知道边界的人在能力圈外操作,却不自知——这比能力圈小但边界清晰的人惨得多。
判断是否在能力圈内的唯一标准是:你能用一句话说清这家公司未来靠什么赚钱、赚多少钱、为什么竞争对手抢不走吗?说不清就不在圈内。
能力圈很难靠读书扩大。搞懂一个生意往往需要很多年。扩大能力圈未必是明智的——在自己懂的范围内,机会已经足够多。
A1 — 书中的应用 (Past Application)
案例 1: 网易(能力圈内 — 100 倍回报)
- 问题: 2001-2002 年网易股价跌至 0.8-1 美元,市场普遍不看好游戏行业前景
- 方法论的使用: 段永平在做小霸王游戏机时积累了十几年对游戏的理解——他不需要看财报,而是自己玩网易的游戏来验证判断。他知道游戏市场远比市场预期大,对别人不确定的事对自己很确定
- 结论: 网易在他的能力圈内,理解度足够高,可以重仓
- 结果: 从 0.8 美元买入,大部分持有到 120-140 美元才卖出,获得 100 倍以上回报。能拿住的根本原因是真正理解生意,而非意志力
案例 2: FRNT 航空 + UNG 天然气 ETF(能力圈外 — 重大亏损)
- 问题: 手握大量现金,看到"便宜"机会想出手
- 方法论的使用(失败): FRNT——买了石油会跌、航空公司会受益的"逻辑",但不懂航空公司的信用风险和管理层行为。UNG——知道天然气价格低于长期成本,但不懂 ETF 的结构损耗和时间衰减
- 结论: 两个标的都不在能力圈内。看似有逻辑,实际是"以为自己懂了,其实还不知道自己不知道什么"
- 结果: FRNT 因 CEO 突然申请破产而亏损离场;UNG 亏损后继续持有想回本,最终止损时亏损扩大近 4 倍。天然气后来涨了 50%,但 UNG 的结构性缺陷让持有者依然亏钱。段永平坦承:亏掉的钱数以亿计,每一笔都是违背"不做不懂的东西"亏的
A2 — 触发场景 (Future Trigger) ★
用户会在什么情境下需要这个 skill?
- 用行业经验替代商业判断 — 用户是某个行业的从业者(医生、程序员、工程师),认为"我懂这个行业所以能投这个行业",但实际只能判断技术/专业层面,无法判断 5-10 年商业前景(定价权、竞争格局、盈利模式)
- 研究了一段时间后想下手 — 用户花了几周研究某个标的,列出了若干正面理由,但被问到"这家公司 5 年后靠什么赚钱、赚多少"时答不上来,或回答只能复述研报内容而非自己的判断
- 因为"便宜"而想买不懂的东西 — 用户发现某个标的 PE 很低或价格跌了很多,觉得"安全边际很大"应该买入,但说不清这家公司的商业模式和未来现金流
语言信号 (用户的话里出现这些就应激活)
- "我在这个行业干了 X 年,应该能看懂"
- "研究了半个月,感觉挺懂了,准备下手"
- "这个 PE 才 8 / 跌了 60%,安全边际很大"
与相邻 skill 的区分
- 与
stop-doing-list的区别: SDL 是"不做什么"的负面清单(不做空、不用 margin),能力圈是"在什么范围内可以做什么"的正面界定。SDL 是外围防线,能力圈是内核定位 - 与
good-business-identifier的区别: 好生意识别法判断的是"这个生意好不好"(商业模式护城河),能力圈判断的是"我有没有资格判断这个生意好不好"(认知边界)。先过能力圈这一关,再用好生意框架分析 - 与
dcf-thinking的区别: DCF 思维是估值工具(毛估估未来现金流),能力圈是使用 DCF 的前提——只有能力圈内的公司,你才有资格做 DCF 判断
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.
- 9d ago First seen · 139 lines · 168 tokens per session scan A b409bd63a66c
capability-circle is a skill published in the GitHub repository kangarooking/duan-yongping-skill (48 stars, last pushed 4mo ago), licensed MIT. It adds 168 tokens to every session and 2,989 once invoked, about $0.0008 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.
identity-work
A guided reflection skill for recognising when personal labels or fixed positions are distorting judgement, then using a new self-image to support behaviour change.
monkey-mind-meditation
A meditation and reflection guide for a busy or anxious mind. It treats recurring thoughts as something to observe and examine, while noting that acute serious mental-health problems need professional care.
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.
naval-almanack
A reference guide for applying ideas from The Almanack of Naval Ravikant, a book about wealth, work, happiness, judgment, and long-term thinking. It routes questions to the relevant topic guidance and notes when professional help is needed.
productize-yourself
A Chinese-language coaching framework for finding a distinctive career, side business, or freelance direction. It combines personal strengths that are hard to teach with ways to turn them into repeatable products or content.