Think Tank
davila7/claude-code-templates
Run a Virtual Think Tank — a structured multi-persona debate — before planning or making architectural/design/strategic decisions.
用户在做长期投资/储蓄/增长决策，需要理解时间和复利的力量，或被短期波动困扰时. An agent skill from kangarooking/buffett-letters-skill.
MITAuto-check passed
Install Compounding Thinking
$ npx skills add kangarooking/buffett-letters-skill --skill compounding-thinking -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install kangarooking/buffett-letters-skill compounding-thinking --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/kangarooking/buffett-letters-skill.git skills-src && mkdir -p .claude/skills && cp -r skills-src/compounding-thinking .claude/skills/compounding-thinking && rm -rf skills-srcUse ~/.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/
Install the "compounding-thinking" agent skill from https://github.com/kangarooking/buffett-letters-skill/tree/main/compounding-thinking into .claude/skills/compounding-thinking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compounding-thinking", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/kangarooking/buffett-letters-skill/tree/main/compounding-thinkingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add kangarooking/buffett-letters-skill --skill compounding-thinking -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install kangarooking/buffett-letters-skill compounding-thinking --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/buffett-letters-skill.git skills-src && mkdir -p .agents/skills && cp -r skills-src/compounding-thinking .agents/skills/compounding-thinking && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "compounding-thinking" agent skill from https://github.com/kangarooking/buffett-letters-skill/tree/main/compounding-thinking into .agents/skills/compounding-thinking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compounding-thinking", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kangarooking/buffett-letters-skill --skill compounding-thinking -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install kangarooking/buffett-letters-skill compounding-thinking --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/buffett-letters-skill.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/compounding-thinking .cursor/skills/compounding-thinking && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "compounding-thinking" agent skill from https://github.com/kangarooking/buffett-letters-skill/tree/main/compounding-thinking into .cursor/skills/compounding-thinking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compounding-thinking", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/kangarooking/buffett-letters-skill.git --path compounding-thinking--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add kangarooking/buffett-letters-skill --skill compounding-thinking -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install kangarooking/buffett-letters-skill compounding-thinking --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/buffett-letters-skill.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/compounding-thinking .gemini/skills/compounding-thinking && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "compounding-thinking" agent skill from https://github.com/kangarooking/buffett-letters-skill/tree/main/compounding-thinking into .gemini/skills/compounding-thinking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compounding-thinking", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install kangarooking/buffett-letters-skill compounding-thinkingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add kangarooking/buffett-letters-skill --skill compounding-thinking -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/kangarooking/buffett-letters-skill.git skills-src && mkdir -p .github/skills && cp -r skills-src/compounding-thinking .github/skills/compounding-thinking && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "compounding-thinking" agent skill from https://github.com/kangarooking/buffett-letters-skill/tree/main/compounding-thinking into .github/skills/compounding-thinking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compounding-thinking", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add kangarooking/buffett-letters-skill --skill compounding-thinking -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install kangarooking/buffett-letters-skill compounding-thinking --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/kangarooking/buffett-letters-skill.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/compounding-thinking .opencode/skills/compounding-thinking && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "compounding-thinking" agent skill from https://github.com/kangarooking/buffett-letters-skill/tree/main/compounding-thinking into .opencode/skills/compounding-thinking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "compounding-thinking", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
compounding-thinking- GitHub stars
- 102
- Token cost
- ~433 tokens
- SKILL.md length
- 127 words
- Files
- 2
- Skills in repo
- 12
- Repo updated
- First seen
- Licence
- MIT
At a glance
用户在做长期投资/储蓄/增长决策，需要理解时间和复利的力量，或被短期波动困扰时. An agent skill from kangarooking/buffett-letters-skill.
- Works in 3 steps: 小差异×长时间=巨大差距：年化15%和20%在30年后差3.4倍 → 高增长必自毁：基数膨胀后维持同等增速需要越来越大的绝对增量——"派对结束" → 少数赢家的绽放：不需要所有投资都成功——Coke…
- SKILL.md covers R — 原文 (Reading), I — 方法论骨架, A1 — 书中的应用 and A2 — 触发场景, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Compounding Thinking is an agent skill from kangarooking/buffett-letters-skill. 用户在做长期投资/储蓄/增长决策，需要理解时间和复利的力量，或被短期波动困扰时。 语言信号:"持有多久合适"/"年化X%十年后会怎样"/"为什么长期持有比频繁交易好"/"小收益怎么变成大财富" 不适用于:短期交易决策、不需要时间维度的分析。
Its SKILL.md is about 430 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
- “持有多久合适”
- “年化X%十年后会怎样”
- “为什么长期持有比频繁交易好”
- “/compounding-thinking”
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- 小差异×长时间=巨大差距：年化15%和20%在30年后差3.4倍
- 高增长必自毁：基数膨胀后维持同等增速需要越来越大的绝对增量——"派对结束"
- 少数赢家的绽放：不需要所有投资都成功——Coke $13亿→$250亿足以抵消所有错误
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
Compounding Thinking loads about 433 tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 127 words of instructions outside code blocks.
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). 127 words, ~433 tokens.
Download SKILL.mdSave it as
.claude/skills/compounding-thinking/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- compounding-thinking
- description
- 用户在做长期投资/储蓄/增长决策，需要理解时间和复利的力量，或被短期波动困扰时。 语言信号:"持有多久合适"/"年化X%十年后会怎样"/"为什么长期持有比频繁交易好"/"小收益怎么变成大财富" 不适用于:短期交易决策、不需要时间维度的分析。
- source_book
- 《巴菲特致股东的信》 沃伦·巴菲特
- source_chapter
- 1962年信 / 2022年信
- tags
- compounding, long-term, patience, time
- related_skills
- hold-forever, economic-moat, float-thinking, cigar-butt-vs-great-business, never-issue-shares, three-asset-categories
复利思维
R — 原文 (Reading)
"It is always startling to see how relatively small differences in rates add up to very significant sums over a period of years." (1962) "The weeds wither away in significance as the flowers bloom. Over time, it takes just a few winners to work wonders." (2022)
I — 方法论骨架
复利的三个关键洞察：
- 小差异×长时间=巨大差距：年化15%和20%在30年后差3.4倍
- 高增长必自毁：基数膨胀后维持同等增速需要越来越大的绝对增量——"派对结束"
- 少数赢家的绽放：不需要所有投资都成功——Coke $13亿→$250亿足以抵消所有错误
反面：增长可能摧毁价值（如果需要持续资本投入超过产出）
A1 — 书中的应用
案例: Coca-Cola + American Express
- 使用: 1990年代各投$13亿，28年后Coke=$250亿+年股息$7亿，Amex=$220亿+年股息$3亿
- 结果: 证明了"少数赢家的长期绽放"——两笔投资的总回报覆盖了所有其他错误
A2 — 触发场景
- 计算长期投资的预期回报
- 纠结是否应该卖出持仓
- 理解为什么"不行动"可能是最好的策略
- 评估短期波动是否值得担心
- 对比"频繁交易"vs"长期持有"的长期效果
语言信号
- "持有多久合适？"
- "年化X%十年后是多少？"
- "为什么巴菲特不卖？"
- "短期波动要不要管？"
与相邻 skill 的区分
- 与
hold-forever的区别：复利是数学原理，永久持有是具体策略
E — 可执行步骤
做复利计算——不要凭直觉
- 完成标准：$1在目标回报率下5/10/20/30年的结果
识别"绽放花朵"
- 完成标准：在投资组合中找出"少数赢家"——它们将贡献大部分回报
接受不均匀性
- 完成标准：列出"宁愿颠簸的15%也不要平滑的12%"的理由
B — 边界
- 复利假设回报率为正——负回报率下复利加速亏损
- 高增长率不可持续——"增长会自毁"
- 作者盲点：巴菲特享受了美国经济60年的顺风，其他市场可能不同
相关 skills (阶段 3 填充)
- depends-on: hold-forever
- composes-with: economic-moat, float-thinking
审计信息
- 验证通过: V1 ✓ / V2 ✓ / V3 ✓
- 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 compounding-thinking of kangarooking/buffett-letters-skill.
- SKILL.md
- test-prompts.json
Open the folder on GitHubat commit 5b1fbe1
Compare with similar skills
Compounding Thinking 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.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Compounding Thinking this skillkangarooking/buffett-letters-skill | 102 | — | ~433 | Automated safety check: Pass | MIT | |
| Think Tankdavila7/claude-code-templates | 32k | — | ~3k | Automated safety check: Pass | MIT | |
| Product Thinkingmillionco/react-doctor | 15k | — | ~3.1k | Automated safety check: Pass | Custom licence | |
| Design Thinkingsickn33/agentic-awesome-skills | 47k | 1 repos | ~1.9k | Automated safety check: Pass | MIT | |
| Ten-Stage Think LoopAgriciDaniel/claude-obsidian | 15k | — | ~1.2k | Automated safety check: Pass | MIT | |
| Scientific Thinking Literature Reviewaffaan-m/ECC | 275k | 1 repos | ~1.3k | Automated safety check: Pass | MIT |
Similar skills
Product Thinking
millionco/react-doctor
Think like a product manager before changing React Doctor's public surface — CLI commands/flags, the 0–100 score, config (doctor.config.), the JSON report schema, package APIs…
Design Thinking
sickn33/agentic-awesome-skills
Direction and intent for frontend design. An agent skill from sickn33/agentic-awesome-skills.
Ten-Stage Think Loop
AgriciDaniel/claude-obsidian
Walks a consequential decision through ten reasoning stages, separating observed facts from inferences and unknowns, and stays read-only throughout.
Scientific Thinking Literature Review
affaan-m/ECC
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging.
Scientific Thinking Scholar Evaluation
affaan-m/ECC
Structured scholarly-work evaluation for papers, proposals, literature reviews, methods sections, evidence quality, citation support, and research-writing feedback.
More from kangarooking/buffett-letters-skill
All 12 skills in this repoAesop 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.
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.
Circle Of Competence
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.
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.
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.
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.
Questions about Compounding Thinking
What does Compounding Thinking do?
用户在做长期投资/储蓄/增长决策，需要理解时间和复利的力量，或被短期波动困扰时. An agent skill from kangarooking/buffett-letters-skill. Compounding Thinking is an agent skill from kangarooking/buffett-letters-skill.
How do I install Compounding Thinking in Claude Code?
Run `npx skills add kangarooking/buffett-letters-skill --skill compounding-thinking -a claude-code`. Or copy the skill folder (compounding-thinking in kangarooking/buffett-letters-skill) into .claude/skills/compounding-thinking in your project. Claude Code loads it when a task matches its description.
How do I install Compounding Thinking in Codex?
Run `npx skills add kangarooking/buffett-letters-skill --skill compounding-thinking -a codex`. Or copy the skill folder (compounding-thinking in kangarooking/buffett-letters-skill) into .agents/skills/compounding-thinking in your project. Codex loads it when a task matches its description.
Can I use Compounding Thinking 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 compounding-thinking -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/compounding-thinking, .gemini/skills/compounding-thinking, .github/skills/compounding-thinking and .opencode/skills/compounding-thinking in your project.
What does Compounding Thinking need to run?
SKILL.md names no scripts, command-line tools or credentials: Compounding Thinking is instructions for the agent only.
Does Compounding Thinking 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 Compounding Thinking 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 Compounding Thinking use?
Compounding Thinking 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 Compounding Thinking use?
About 433 tokens (SKILL.md is roughly 1.7k 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 Compounding Thinking?
Skills that share tags, products or a category with Compounding Thinking: Think Tank (davila7/claude-code-templates, 32k stars), Product Thinking (millionco/react-doctor, 15k stars), Design Thinking (sickn33/agentic-awesome-skills, 47k stars) and Ten-Stage Think Loop (AgriciDaniel/claude-obsidian, 15k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Compounding Thinking?
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.