
Partner With Admired
- 44 installs
- 65 repo stars
- Updated April 17, 2026
- kangarooking/buffett-letters-skill
Helps with ai & agent building tasks.
About
partner-with-admired is a Claude Code skill for ai & agent building. It helps solo builders move faster with AI-assisted development.
- partner-with-admired
- AI & Agent Building
- AI-coding skill
Partner With Admired by the numbers
- 44 all-time installs (skills.sh)
- +1 installs in the week ending Aug 2, 2026 (Skillselion tracking)
- Ranked #7,851 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/kangarooking/buffett-letters-skill --skill partner-with-admiredAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 44 |
|---|---|
| repo stars | ★ 65 |
| Last updated | April 17, 2026 |
| Repository | kangarooking/buffett-letters-skill ↗ |
What it does
Helps with ai & agent building tasks.
Files
只与喜欢和钦佩的人合作(含吃自己的饭)
R — 原文 (Reading)
"We would rather achieve a return of X while associating with people whom we strongly like and admire than realize 110% of X by making a sour or unpleasant relationship." (1987)
"We eat our own cooking." (1983)
I — 方法论骨架
两个合并的原则: 1. 只与喜欢的人合作:宁取100%X配好关系,不要110%X配差关系。因为差关系会在你最意想不到的时候伤害你 2. 吃自己的饭:验证信任的终极方法——看管理者是否把自己的钱也投进去
为什么重要:你无法改变别人的品格。短期回报差异远小于长期信任的价值。差的管理者会在顺境时拿走功劳,在逆境时背叛你。
A1 — 书中的应用
案例: TTI / Paul Andrews
- 问题: 为什么选择卖给伯克希尔而非竞争对手或PE?
- 使用: 竞争对手会裁人,PE关注"退出策略"——只有伯克希尔承诺永远持有
- 结果: 收购后收益增长673%,Paul Andrews继续热爱他的工作
案例: Mrs. B / Nebraska Furniture Mart
- 使用: "给了Mrs. B一张$5500万的支票,她给了我们她的承诺——这是一笔公平交易"
- 结果: 无需审计的信任创造了非凡回报
A2 — 触发场景
1. 选择投资目标时评估管理层 2. 选择商业合作伙伴 3. 决定是否信任某个人的承诺 4. 两个机会选一个(回报vs关系质量)
语言信号
- "这个管理层可不可信?"
- "应该和这个人合作吗?"
- "两个机会怎么选?"
- "怎么验证一个人的诚信?"
E — 可执行步骤
1. 检验"吃自己的饭"
- 完成标准:管理者是否将自己的大部分财富投在了同一个地方?
2. 做"钦佩测试"
- 完成标准:你愿意你的子女为这个人工作吗?如果不愿意 → 不合作
3. 计算"关系折价"
- 完成标准:即使回报低10-20%,好关系是否仍然值得?如果是 → 选择好关系
B — 边界
- "喜欢"不等于"软弱"——巴菲特也解雇过不称职的管理者
- 在某些市场(如高频交易),关系不重要
- 作者盲点:巴菲特有选择权——他可以等待好的伙伴出现;小投资者可能没有这个选择
---
相关 skills (阶段 3 填充)
- composes-with: business-picker, hold-forever
审计信息
- 验证通过: V1 ✓ / V2 ✓ / V3 ✓
- 蒸馏时间: 2026-04-16
{
"skill": "partner-with-admired",
"version": "0.1.0",
"source_book": "《巴菲特致股东的信》 — 沃伦·巴菲特",
"darwin_compatible": true,
"test_cases": [
{
"id": "should-trigger-01",
"type": "should_trigger",
"prompt": "这个投资机会回报很高但管理层口碑不好,要不要投",
"expected_behavior": "应激活 partner-with-admired,指出差关系会在你最意想不到的时候伤害你",
"notes": "回报vs关系的经典权衡"
},
{
"id": "should-trigger-02",
"type": "should_trigger",
"prompt": "怎么判断一个CEO值不值得信任",
"expected_behavior": "应激活 partner-with-admired,用'吃自己的饭'和'钦佩测试'两个工具评估",
"notes": "信任验证方法"
},
{
"id": "should-trigger-03",
"type": "should_trigger",
"prompt": "两个合作机会,一个回报高但关系差,怎么选",
"expected_behavior": "应激活 partner-with-admired,宁取100%X配好关系,不要110%X配差关系",
"notes": "回报与关系质量的选择"
},
{
"id": "should-not-trigger-01",
"type": "should_not_trigger",
"prompt": "帮我分析这只股票的估值",
"expected_behavior": "不应激活本skill,这是纯估值请求",
"notes": "诱饵:估值≠关系评估"
},
{
"id": "should-not-trigger-02",
"type": "should_not_trigger",
"prompt": "这个行业的竞争格局怎么样",
"expected_behavior": "不应激活本skill,这是行业分析",
"notes": "诱饵:行业分析≠伙伴选择"
},
{
"id": "edge-01",
"type": "edge_case",
"prompt": "管理层很好但业务一般",
"expected_behavior": "应指出好管理层不能拯救差业务——关系质量和业务质量需要同时满足",
"notes": "边界:好关系≠好投资"
}
],
"minimum_pass_rate": 0.8
}
Related skills
AI & Agent Buildingagents