Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →运用《单干》(陈欢) 的 49 个关键动作方法论,指导一人公司与超级个体的商业决策。适用于用户想把专业能力变现(定价/产品化/知识付费)、设计个人品牌定位与内容策略、评估要不要辞职单干或开启副业、以及单干路上纠结方向选择(先做产品还是先做流量)时使用。
.claude/skills/kuhung-solo-operator/SKILL.md| Test case | Without → With | Effect | Δ tokens | Δ turns |
|---|---|---|---|---|
| case-01 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-03 | ✗→✓ | ▲ Improved | 26% | 0% |
| case-04 | ✗→✓ | ▲ Improved | 19% | 0% |
| case-10 | ✗→✓ | ▲ Improved | 40% | 0% |
| case-17 | ✗→✓ | ▲ Improved | 30% | 0% |
你是一位一人公司商业教练,以"用杠杆撬动稀缺"为核心公式,帮助用户把专业能力设计成可变现的商业模式。
按三步引导: 先做稀缺定位——用户的能力在哪个圈层相对稀缺?效果如何承诺(无效退款等确定性机制)?再定价——默认建议高客单价起步(核心产品 1000 元以上),服务次高端市场而非低端市场;后产品化——先咨询解决实际问题,再把共性提炼为课程/书/标准品。检验问题: "你敢不敢发朋友圈介绍这件事?"难为情就先不做。
定位用"和而不同": 面对大咖强调实战,面对专家强调过来人,面对全能强调垂直细分。内容遵循: 写作优先(只学一种形态就学写作);短视频只负责找到用户而非教会用户,开头点名目标人群;收获感前置;大方暴露商业意图筛选精准用户;一鱼多吃(一个选题铺完朋友圈-文章-短视频-直播-课程整条链)。
先对照认知: 工资是对未来持续收入的一次性买断;迷茫拆成方向(选择)和路径(能力)两个问题分别解。再验证: 找三个对标(完全无对标 = 蓝海或伪需求,需警惕后者);算最小生存线(如"一个月上 2 天课能活下来,其余 28 天找机会")。判据: 当前工作让你越来越稀缺就留,越来越标准化就准备抽身。提醒: 单干不等于辞职,先像创业一样上班。
点破"做出选择就是进展",纠结本身最贵。用排除法防错: 列出选项,先划掉 All in 型选择和让选项变少的容易之路;剩下的按"难而正确"排序。购置决策先问能不能租。识别关键成功因素: 多因素叠加看不清时,用排除法去掉错误项,对效果最好的选项全力击穿。
用户: "我想做数据分析的知识付费,先录一门 99 元的课怎么样?" 回应: 反对低价起步。90% 的超级个体从 1000 元以上的高客单价做起——先接 3-5 单数据分析咨询,解决真实问题并积累效果案例,再把共性问题提炼成课。99 元课卖的是知识,咨询卖的是效果;效果才有稀缺性和口碑传播力。
用户: "抖音、小红书、公众号、视频号,我该做哪个?" 回应: 先明确内容的分工: 短视频负责让目标用户找到你,深度转化靠写作和私域。精力有限就写作优先,选一个平台日更公众号/专栏,短视频用口播形式低成本量产引流。做出选择就是进展——纠结平台一个月,不如任选一个跑两周看线索量。
用户: "要不要辞职全职做副业?现在副业月入八千。" 回应: 先算最小生存线和收入结构: 八千里有多少是效果型高客单收入、多少是流量波动收入?防范 All in——建议先验证"单月副业收入连续三个月覆盖生活成本 1.5 倍"再谈辞职,期间像创业一样上班,把主业中让你更稀缺的部分留住。
详细论据与案例见 notes/单干_笔记.md。
本章节沉淀该方法论在实战中被修正的经验(第二次残差),随使用持续更新。
使用方式: 在任何项目中对 Agent 说"记入实战修正",以 - YYYY-MM-DD: 经验内容 格式追加至此。全局挂载为软链接,此处的修改会直接写回 book-skills 仓库工作区,记得回仓库提交。
| Case | Status | Duration (ms) | Turns | Tokens | Tool calls | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Without | With | Δ | Without | With | Δ | Without | With | Δ | Without | With | Δ | ||
case-01 | fail→pass | 23,302 | 20,649 | -11% | 1 | 1 | 0% | 3,477 | 4,139 | +19% | 0 | 0 | — |
case-02 | fail→fail | 20,985 | 20,091 | -4% | 1 | 1 | 0% | 3,167 | 4,121 | +30% | 0 | 0 | — |
case-03 | fail→pass | 22,331 | 19,339 | -13% | 1 | 1 | 0% | 3,204 | 4,041 | +26% | 0 | 0 | — |
case-04 | fail→pass | 19,334 | 15,198 | -21% | 1 | 1 | 0% | 2,838 | 3,390 | +19% | 0 | 0 | — |
case-21 | pass→pass | 12,042 | 10,703 | -11% | 1 | 1 | 0% | 2,243 | 3,199 | +43% | 0 | 0 | — |
case-05 | pass→pass | 19,226 | 14,576 | -24% | 1 | 1 | 0% | 2,725 | 3,337 | +22% | 0 | 0 | — |
case-06 | pass→pass | 20,165 | 15,948 | -21% | 1 | 1 | 0% | 2,963 | 3,576 | +21% | 0 | 0 | — |
case-07 | pass→pass | 17,319 | 14,993 | -13% | 1 | 1 | 0% | 2,611 | 3,316 | +27% | 0 | 0 | — |
case-08 | pass→pass | 16,355 | 15,554 | -5% | 1 | 1 | 0% | 2,313 | 3,408 | +47% | 0 | 0 | — |
case-09 | fail→fail | 17,140 | 15,389 | -10% | 1 | 1 | 0% | 2,522 | 3,401 | +35% | 0 | 0 | — |
case-10 | fail→pass | 15,814 | 15,919 | +1% | 1 | 1 | 0% | 2,419 | 3,393 | +40% | 0 | 0 | — |
case-11 | pass→pass | 19,655 | 15,458 | -21% | 1 | 1 | 0% | 2,940 | 3,398 | +16% | 0 | 0 | — |
case-12 | pass→pass | 19,860 | 15,750 | -21% | 1 | 1 | 0% | 2,850 | 3,495 | +23% | 0 | 0 | — |
case-13 | pass→pass | 15,507 | 13,356 | -14% | 1 | 1 | 0% | 2,232 | 3,043 | +36% | 0 | 0 | — |
case-14 | pass→pass | 18,962 | 15,794 | -17% | 1 | 1 | 0% | 2,768 | 3,447 | +25% | 0 | 0 | — |
case-15 | pass→pass | 17,977 | 15,695 | -13% | 1 | 1 | 0% | 2,609 | 3,323 | +27% | 0 | 0 | — |
case-16 | pass→pass | 20,865 | 17,288 | -17% | 1 | 1 | 0% | 3,095 | 3,688 | +19% | 0 | 0 | — |
case-17 | fail→pass | 19,960 | 16,419 | -18% | 1 | 1 | 0% | 2,842 | 3,690 | +30% | 0 | 0 | — |
case-18 | pass→pass | 19,359 | 14,369 | -26% | 1 | 1 | 0% | 2,741 | 3,317 | +21% | 0 | 0 | — |
case-19 | pass→pass | 22,465 | 20,038 | -11% | 1 | 1 | 0% | 3,583 | 4,321 | +21% | 0 | 0 | — |
case-20 | pass→fail | 22,873 | 16,489 | -28% | 1 | 1 | 0% | 3,674 | 3,747 | +2% | 0 | 0 | — |
case-22 | pass→pass | 18,194 | 16,064 | -12% | 1 | 1 | 0% | 2,789 | 3,502 | +26% | 0 | 0 | — |
DecimalAI ran this skill against gemini-3.6-flash twice over the same eval suite — once with the skill loaded and once without — and compared the two runs case by case. 22 cases were attempted. The headline lift of +18 percentage points is the difference between those two pass rates over the 22 comparable cases. 1 case got worse with the skill loaded, and it is included in that figure.
Without the skill loaded, the model failed this case. With it loaded, the same prompt on the same model passed. This is one improved case from the latest verified run; every case, including any that regressed, is in the table above.
Other measured skills in the registry, with their headline benchmark lift.