Agent skill

Circle Of Competence

by kangarooking in kangarooking/buffett-letters-skill

用户在做决策时不确定自己是否真的理解某个领域,或准备进入一个看似熟悉但缺乏验证记录的领域时. An agent skill from kangarooking/buffett-letters-skill.

MITAuto-check passed

Install Circle Of Competence

skills CLI
$ npx skills add kangarooking/buffett-letters-skill --skill circle-of-competence -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kangarooking/buffett-letters-skill circle-of-competence --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kangarooking/buffett-letters-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/circle-of-competence .claude/skills/circle-of-competence && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
circle-of-competence
GitHub stars
102
Token cost
~693 tokens
SKILL.md length
180 words
Files
2
Skills in repo
12
Repo updated
First seen
Licence
MIT

At a glance

用户在做决策时不确定自己是否真的理解某个领域,或准备进入一个看似熟悉但缺乏验证记录的领域时. An agent skill from kangarooking/buffett-letters-skill.

  • Works in 5 steps: 每个人都有一个"能力圈"——你能在其中做出比市场更准确判断的领域 → 能力圈的大小不重要,重要的是知道边界在哪 → 能力圈由"历史判断准确率"定义,而非"熟悉程度"或"自信程度" → …
  • SKILL.md covers R — 原文 (Reading), I — 方法论骨架 (Interpretation), A1 — 书中的应用 (Past Application) and A2 — 触发场景 (Future Trigger) ★, plus 4 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Circle Of Competence is an agent skill from kangarooking/buffett-letters-skill. 用户在做决策时不确定自己是否真的理解某个领域,或准备进入一个看似熟悉但缺乏验证记录的领域时。 语言信号:"我觉得我懂这个行业"/"这个看起来很简单"/"别人都在投这个"/"我来研究一下这个新领域" 不适用于:纯信息查询、日常琐事选择、用户已有充分专业知识的领域。

Its SKILL.md is about 690 tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `test-prompts.json`).

The repository describes itself as: An AI skill pack for value investing, capital allocation, and behavioral discipline, distilled from Warren Buffett's 60+ years of shareholder letters. The licence is MIT.

Example prompts

  • “我觉得我懂这个行业”
  • “这个看起来很简单”
  • “别人都在投这个”
  • “/circle-of-competence”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. 每个人都有一个"能力圈"——你能在其中做出比市场更准确判断的领域
  2. 能力圈的大小不重要,重要的是知道边界在哪
  3. 能力圈由"历史判断准确率"定义,而非"熟悉程度"或"自信程度"
  4. 在圈内犯错只是普通错误;在圈外犯错可能是灾难性的
  5. 能力圈可以扩展,但只能通过长期积累而非突然突破

What it can do on your machine

Read from SKILL.md and the folder at commit 5b1fbe1. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Circle Of Competence loads about 693 tokens when it runs. Until then it costs about 38 tokens; SKILL.md has 180 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~38
When it runs · the whole SKILL.md, loaded when a task matches
~693

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from kangarooking/buffett-letters-skill at commit 5b1fbe1, republished under its MIT licence (© kangarooking). 180 words, ~693 tokens.

Download SKILL.mdSave it as .claude/skills/circle-of-competence/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
circle-of-competence
description
用户在做决策时不确定自己是否真的理解某个领域,或准备进入一个看似熟悉但缺乏验证记录的领域时。 语言信号:"我觉得我懂这个行业"/"这个看起来很简单"/"别人都在投这个"/"我来研究一下这个新领域" 不适用于:纯信息查询、日常琐事选择、用户已有充分专业知识的领域。
source_book
《巴菲特致股东的信》 沃伦·巴菲特
source_chapter
1999年信 / 2014年信
tags
decision, circle-of-competence, boundary, self-awareness
related_skills
economic-moat, aesop-three-questions, margin-of-safety, business-picker, real-conservatism

能力圈判断

R — 原文 (Reading)

"If we have a strength, it is in recognizing when we are operating well within our circle of competence and when we are approaching the perimeter. Predicting the long-term economics of companies that operate in fast-changing industries is simply far beyond our perimeter."

— Warren Buffett, 1999年信


I — 方法论骨架 (Interpretation)

能力圈是一个关于自我认知的决策框架。核心逻辑:

  1. 每个人都有一个"能力圈"——你能在其中做出比市场更准确判断的领域
  2. 能力圈的大小不重要,重要的是知道边界在哪
  3. 能力圈由"历史判断准确率"定义,而非"熟悉程度"或"自信程度"
  4. 在圈内犯错只是普通错误;在圈外犯错可能是灾难性的
  5. 能力圈可以扩展,但只能通过长期积累而非突然突破

关键区分:熟悉 ≠ 能做准确判断。你可以在某个行业工作20年但仍然无法预测其经济走势。


A1 — 书中的应用 (Past Application)

案例1: 科技行业的回避
  • 问题: 1990s科技股暴涨,是否应该投资?
  • 方法论的使用: 巴菲特承认科技行业的长期经济前景"完全超出了我们的能力圈边界"
  • 结论: 不投资,即使这意味着错过短期巨大收益
  • 结果: 成功避开了2000年互联网泡沫的崩盘
案例2: 可口可乐的投资
  • 问题: 如何判断一个投资是否在能力圈内?
  • 方法论的使用: 可口可乐的商业模式——卖糖水——是巴菲特能理解和预测的
  • 结论: 大量投资$13亿
  • 结果: 28年后价值$250亿,年股息$7亿

A2 — 触发场景 (Future Trigger) ★

用户会在什么情境下需要这个 skill?
  1. 准备投资或进入一个"看起来很熟悉"的领域
  2. 在某个领域有几次成功经历后想扩大范围
  3. 别人都在谈论某个热门领域,产生了FOMO
  4. 需要评估自己是否真的"懂"某个行业/公司/技术
  5. 面对一个"看似简单"的商业机会
语言信号
  • "我觉得我理解这个行业"
  • "这个商业模式看起来很简单"
  • "大家都在投这个领域"
  • "我研究了一周,感觉已经看懂了"
  • "凭我在X领域的经验,Y应该也差不多"
与相邻 skill 的区分
  • 与 margin-of-safety 的区别:安全边际问的是"价格够不够低",能力圈问的是"我能不能判断价值"
  • 与 real-conservatism 的区别:保守≠传统是关于不盲从,能力圈是关于不越界

E — 可执行步骤 (Execution)

  1. 列出历史判断记录

    • 完成标准:写出了过去5-10年在该领域的判断及其结果(对/错/不确定)
  2. 检验准确率是否超过随机水平

    • 完成标准:用具体数据证明你在该领域的判断准确率确实高于"抛硬币"
    • 判停条件:如果无法证明准确率高于随机 → 回答"这在我的能力圈之外",停止
  3. 识别边界信号

    • 完成标准:列出了3个"我可能已经越界"的预警信号(如:需要用术语解释而非自己的话;无法简单描述商业模式;说不清竞争对手的优势来源)
  4. 做出决策

    • 完成标准:明确回答"在圈内"或"在圈外",并给出具体理由

B — 边界 (Boundary)

不要在以下情况使用此 skill
  • 当你已经拥有经过验证的专业知识时(过度谦虚也是一种错误)
  • 当决策的时间窗口极短且不需要深度分析时
作者在书中警告的失败模式
  • 把"熟悉"等同于"理解"——在一个行业工作不代表能判断其经济前景
  • 把"自信"等同于"能力"——自信感是最不可靠的能力圈指标
  • 能力圈不扩展却以为在扩展——真正的扩展需要多年的学习和小规模测试
作者的盲点 / 时代局限
  • 巴菲特用能力圈避开了科技行业,但也因此错过了亚马逊和谷歌——能力圈可能成为不学习的借口
  • "快速变化的行业"不等于"不可预测"——巴菲特的判断可能反映了代际认知局限而非行业本质
  • 后期通过Apple投资弥补,说明能力圈确实可以扩展,但代价是不小的机会成本
容易混淆的邻近方法论
  • 不是"风险厌恶"——你可以在能力圈内承担巨大的集中风险
  • 不是"不学习新东西"——巴菲特本人也在不断学习新行业(如后来的Apple)

相关 skills (阶段 3 填充)

  • depends-on: (无,这是最基础的)
  • contrasts-with: (无)
  • composes-with: margin-of-safety, aesop-three-questions

审计信息

  • 验证通过: V1 ✓ / V2 ✓ / V3 ✓
  • 测试通过率: 待阶段 4 验证
  • 蒸馏时间: 2026-04-16

© kangarooking, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file in circle-of-competence of kangarooking/buffett-letters-skill.

  • SKILL.md
  • test-prompts.json

Open the folder on GitHubat commit 5b1fbe1

Compare with similar skills

Circle Of Competence next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Circle Of Competence compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Circle Of Competence this skillkangarooking/buffett-letters-skill102—~693Automated safety check: PassMIT
Thinking Circle Of Competencetjboudreaux/cc-thinking-skills1.6k—~733Automated safety check: PassMIT
Competency Matrixsickn33/agentic-awesome-skills47k1 repos~3.7kAutomated safety check: PassMIT
CirclesNethereum/Nethereum2.3k—~1kAutomated safety check: PassMIT
Circles ProtocolBitterbot-AI/bitterbot-desktop2.5k—~403Automated safety check: PassMIT
Crest Competejeremylongshore/tons-of-skills-marketplace2.8k—~1.8kAutomated safety check: NotesMIT

Similar skills

  • Thinking Circle Of Competence

    tjboudreaux/cc-thinking-skills

    A skill your agent uses when a specific claim may lack grounding.

    1.6k GitHub stars~733 tokensUpdated 2 mo ago
    Auto-check passed
  • Competency Matrix

    sickn33/agentic-awesome-skills

    Competency matrix of expected proficiency by job title and grade, with assessment method and linked skill area.

    47k GitHub starsUsed in 1 repo~3.7k tokens
    Auto-check passed
  • Circles

    Nethereum/Nethereum

    Interact with the Circles UBI protocol using Nethereum (.NET/C).

    2.3k GitHub stars~1k tokensUpdated 6 days ago
    Backend & APIsAuto-check passed
  • Circles Protocol

    Bitterbot-AI/bitterbot-desktop

    Use before calling the circles tool, when the user asks about their circles (connections, presence, messages, tab, briefing, asks) or wants to write to one.

    2.5k GitHub stars~403 tokensUpdated today
    Auto-check passed
  • Crest Compete

    jeremylongshore/tons-of-skills-marketplace

    Competitive analysis ending in a clear positioning call — where to play, how to win.

    2.8k GitHub stars~1.8k tokensUpdated yesterday
    Marketing & SEOAuto-check: notes
  • Competency Unpacker

    GarethManning/education-agent-skills

    Unpack a broad standard or competency descriptor into specific, assessable success criteria and sub-skills.

    840 GitHub stars~4.5k tokensUpdated 1 mo ago
    EducationAuto-check passed

More from kangarooking/buffett-letters-skill

All 12 skills in this repo
  • Aesop Three Questions

    kangarooking/buffett-letters-skill

    用户需要评估一个资产/投资/项目的价值,或纠结某个东西"值不值"时。适用于任何能产生(或不产生)现金流的资产评估. An agent skill from kangarooking/buffett-letters-skill.

    102 GitHub stars~645 tokensUpdated 5 mo ago
    Auto-check passed
  • Cigar Butt Vs Great Business

    kangarooking/buffett-letters-skill

    用户在选择投资标的或商业模式时,纠结于"便宜买差企业"还是"合理价买好企业". An agent skill from kangarooking/buffett-letters-skill.

    102 GitHub stars~481 tokensUpdated 5 mo ago
    Auto-check passed
  • Economic Moat

    kangarooking/buffett-letters-skill

    用户需要评估一个企业的长期竞争力和定价权——它能否在极少额外资本下持续增长利润. An agent skill from kangarooking/buffett-letters-skill.

    102 GitHub stars~502 tokensUpdated 5 mo ago
    Auto-check passed
  • Fear And Greed

    kangarooking/buffett-letters-skill

    用户面对市场极端情绪时需要做出逆向来决策。当所有人都在买入/卖出、市场处于极端乐观/悲观时. An agent skill from kangarooking/buffett-letters-skill.

    102 GitHub stars~493 tokensUpdated 5 mo ago
    Auto-check passed
  • Mr Market

    kangarooking/buffett-letters-skill

    用户在市场波动中情绪受到影响,或试图从市场价格变动中获取信息而非从企业分析中获取信息时. An agent skill from kangarooking/buffett-letters-skill.

    102 GitHub stars~714 tokensUpdated 5 mo ago
    Auto-check passed
  • Business Picker

    kangarooking/buffett-letters-skill

    用户在分析股票或投资机会时,需要用"买企业"而非"买股票"的视角来评估. An agent skill from kangarooking/buffett-letters-skill.

    102 GitHub stars~441 tokensUpdated 5 mo ago
    Auto-check passed

Questions about Circle Of Competence

What does Circle Of Competence do?

用户在做决策时不确定自己是否真的理解某个领域,或准备进入一个看似熟悉但缺乏验证记录的领域时. An agent skill from kangarooking/buffett-letters-skill. Circle Of Competence is an agent skill from kangarooking/buffett-letters-skill.

How do I install Circle Of Competence in Claude Code?

Run `npx skills add kangarooking/buffett-letters-skill --skill circle-of-competence -a claude-code`. Or copy the skill folder (circle-of-competence in kangarooking/buffett-letters-skill) into .claude/skills/circle-of-competence in your project. Claude Code loads it when a task matches its description.

How do I install Circle Of Competence in Codex?

Run `npx skills add kangarooking/buffett-letters-skill --skill circle-of-competence -a codex`. Or copy the skill folder (circle-of-competence in kangarooking/buffett-letters-skill) into .agents/skills/circle-of-competence in your project. Codex loads it when a task matches its description.

Can I use Circle Of Competence in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add kangarooking/buffett-letters-skill --skill circle-of-competence -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/circle-of-competence, .gemini/skills/circle-of-competence, .github/skills/circle-of-competence and .opencode/skills/circle-of-competence in your project.

What does Circle Of Competence need to run?

SKILL.md names no scripts, command-line tools or credentials: Circle Of Competence is instructions for the agent only.

Does Circle Of Competence access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Circle Of Competence safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Circle Of Competence use?

Circle Of Competence is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Circle Of Competence use?

About 693 tokens (SKILL.md is roughly 2.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Circle Of Competence?

Skills that share tags, products or a category with Circle Of Competence: Thinking Circle Of Competence (tjboudreaux/cc-thinking-skills, 1.6k stars), Competency Matrix (sickn33/agentic-awesome-skills, 47k stars), Circles (Nethereum/Nethereum, 2.3k stars) and Circles Protocol (Bitterbot-AI/bitterbot-desktop, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Circle Of Competence?

kangarooking (a GitHub user) maintains it in kangarooking/buffett-letters-skill, which has 102 GitHub stars. The repository holds 12 skills in this directory. The repository was last updated on April 17, 2026.

Source: kangarooking/buffett-letters-skill on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.