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 muyuhill/100books-to-skills --skill lean-startupgit clone --depth 1 https://github.com/muyuhill/100books-to-skillsWrote 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/muyuhill/100books-to-skills/lean-startup)<a href="https://agentmods.dev/skills/muyuhill/100books-to-skills/lean-startup"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/lean-startup/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/muyuhill/100books-to-skills/lean-startup"><img src="https://agentmods.dev/badge/skills/muyuhill/100books-to-skills/lean-startup.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 | $0.00056 | $0.03463 |
| Opus 5 | $0.00028 | $0.01732 |
| Sonnet 5 | $0.00011 | $0.00693 |
| Haiku 4.5 | $0.00006 | $0.00346 |
Grade A, and why
精益创业-lean-startup 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 12d 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 — 276 lines — stays where its author put it; the contents beside it link to each section on GitHub.
《精益创业》—— 用科学方法创业,而不是赌运气
创业不是建一座城堡然后请人来看——是开着一辆能跑的车在迷雾里找路。方向比速度重要,数据比直觉可靠。
埃里克·莱斯的核心主张:创业是一场科学实验,不是一场赌博。 你不能靠「我觉得会成功」——你得用最小的代价快速验证假设,然后根据真实数据调整方向。
一个核心循环:Build → Measure → Learn
┌─────────────────────────────────────┐
│ │
│ Ideas ──→ BUILD ──→ Product │
│ ↑ │ │
│ │ ↓ │
│ LEARN ←── MEASURE ←── Data │
│ │
└──────── 越快完成一圈,浪费越少 ────┘
这不是「先想好再做」
传统做法:花半年写商业计划书 → 花一年开发产品 → 上线发现没人要。
精益做法:两周内做出一个粗糙版本 → 扔给真实用户 → 听他们说什么 → 调整 → 再来一圈。
关键是速度:每一圈的目的不是为了把产品做完美,而是为了更快地发现「什么值得做」。
三个步骤拆解
| 步骤 | 做什么 | 常见错误 |
|---|---|---|
| Build | 用最少资源做一个能测试假设的东西 | 做太多、做太精、舍不得砍功能 |
| Measure | 收集用户真实行为数据(不是问卷) | 看虚荣指标、只看正面数据 |
| Learn | 判断:继续还是转向? | 「我们学到了很多」但没有数据支撑 |
一句话:你的任务不是建造东西——你的任务是尽可能快地走完这个循环,找到可行的商业模式。
MVP:最小可行产品
MVP 不是半成品
MVP 不是「砍掉一半功能的正式产品」——它是一个实验工具。目的不是卖出去,是学到东西。
| ❌ 不是 MVP | ✅ 是 MVP | |
|---|---|---|
| 定义 | 简陋版产品 | 用最少资源验证最关键假设的实验 |
| 目标 | 上线、有用户 | 拿到数据、验证或推翻假设 |
| 标准 | 好不好看、功能全不全 | 能不能让我学到东西 |
| 心态 | 「先把产品做出来」 | 「先看看这个假设对不对」 |
四种 MVP 形式
-
视频 MVP:做一个产品演示视频,看有没有人点「想要」。Dropbox 就是这么起步的——一个 3 分钟视频,注册量从 5000 飙到 75000。
-
礼宾式 MVP (Concierge MVP):人工手动完成服务,假装有自动化产品。不是用软件做——是你自己动手帮用户做,看看他们到底需要什么。
-
绿野仙踪 MVP (Wizard of Oz):用户以为他们用的是自动化产品,但实际上是你(或团队)在后台手动操作。Zappos 创始人就是去鞋店拍照片放到网上,有人下单了再去店里买来寄——没有库存、没有系统。
-
单功能 MVP:只做一个功能。不是做很多功能然后看用户用哪个——是只做一个,看它是不是真的解决了问题。
MVP 的本质问题
不是「我能做出来吗?」而是「我应该做出来吗?」
每做一个 MVP 之前,明确写下来:
- 我们在测试什么假设?
- 什么数据能证明这个假设是对的?
- 什么数据代表我们错了?
验证式学习 (Validated Learning)
学习了 ≠ 验证了
| 一般「学习」 | 验证式学习 |
|---|---|
| 「我们了解到用户喜欢这个功能」 | 「A/B 测试显示使用率提升了 27%,p<0.05」 |
| 「市场调研说很多人有兴趣」 | 「落地页 300 人访问,23 人留下了邮箱,5 人付了钱」 |
| 「我们觉得方向是对的」 | 「关键指标在过去 3 周持续上升」 |
| 「会上大家一致认为……」 | 「数据表明……所以结论是……」 |
验证式学习 = 假设 + 实验 + 数据 + 结论。缺任何一个环节,都不叫验证式学习。
如何做验证式学习
- 明确假设:「我们相信,[某类用户] 有 [某个问题],他们会用 [某种方式] 解决它。」
- 设计实验:什么是最小的、能测出这个假设对错的动作?
- 收集数据:不是「有没有人点」,而是「多少人点、多少人走、多少人付钱」。
- 得出结论:假设成立 → 继续。假设不成立 → 转型。
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.
- 12d ago First seen · 276 lines · 56 tokens per session scan A b54421d309bf
精益创业-lean-startup is a skill published in the GitHub repository muyuhill/100books-to-skills (12 stars, last pushed 2mo ago), licensed MIT. It adds 56 tokens to every session and 3,463 once invoked, about $0.0003 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
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…