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 agentmods add skills/peterfei/forge-skill/lean-startup-skillnpx skills add peterfei/forge-skill --skill lean-startup-skillgit clone --depth 1 https://github.com/peterfei/forge-skillWrote 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/peterfei/forge-skill/lean-startup-skill)<a href="https://agentmods.dev/skills/peterfei/forge-skill/lean-startup-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/lean-startup-skill.svg" alt="Measured on agentmods" 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 | $0.00084 | $0.02693 |
| Opus 5 | $0.00042 | $0.01347 |
| Sonnet 5 | $0.00017 | $0.00539 |
| Haiku 4.5 | $0.00008 | $0.00269 |
Grade A, and why
lean-startup-skill 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 4d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
精益创业 · 思维工具
"A startup is a human institution designed to create a new product or service under conditions of extreme uncertainty." — Eric Ries
激活条件与触发词
- 直接调用:「用精益创业分析...」「设计MVP」「验证这个方向」
- 语义触发:创业/新产品想法但不确定方向,想快速验证
- 组合调用:「先用精益创业验证,再用增长黑客放大」
方法框架概览
精益创业的核心是在极端不确定中用最小成本快速学习,它通过 Build-Measure-Learn 循环、可证伪假设、MVP 作为学习工具、转型而非失败的思维来避免在错误方向浪费资源。
核心原理(3-7个,每个须附 ≥2 个跨域证据)
原理 1: 构建测量学习循环(Build-Measure-Learn Loop)
一句话定义:不猜测,从真实的用户行为数据中学习。
跨域证据:
- 电商:Zappos 创始人去鞋店拍照放网上,有人下单再去买,验证了"人在网上买鞋"(来源:Hsieh, Delivering Happiness, 2010)
- 社交工具:Buffer 用两个着陆页(免费/付费)验证"有人愿意为社交媒体排期付费"(来源:Buffer Blog, 2010)
应用方式:每个关键不确定点设计一个最小实验,测量用户行为而非他们说什么。
局限:某些产品(如 Tesla)需要巨额前期投入,不能用快速 MVP 验证。
原理 2: 假设必须可证伪
一句话定义:如果不能设计实验来证明假设错误,就不是科学假设。
跨域证据:
- 哲学:Popper 提出科学与伪科学的区分是可证伪性(来源:Popper, The Logic of Scientific Discovery, 1934)
- 投资:Naval Ravikant 强调好的创业假设应在 2 周内能被数据推翻(来源:Naval, The Angel Philosopher, 2015)
应用方式:每个关键假设写成"如果X成立应看到Y数据。如果2周内看不到,X不成立。"
局限:某些价值假设(如"用户会喜欢这款设计")难以纯数据证伪,需定性反馈补充。
原理 3: MVP 是学习工具,不是产品
一句话定义:MVP 的目标是最大化单位时间学习量,不是产品销量。
跨域证据:
- 云存储:Dropbox 用 3 分钟视频演示验证需求,5万人注册等待列表(来源:Houston, Dropbox MVP Story, 2010)
- 音乐流媒体:Spotify 用极小内测版验证无限流媒体音乐需求(来源:Ek, Spotify Origin Story, 2010)
应用方式:设计 MVP 时问"不做这个功能会阻碍我学到最关键的东西吗?"
局限:某些领域 MVP 质量太差会永久失去用户信任(如金融、医疗)。
原理 4: 转型是进步而非失败
一句话定义:当数据不支持当前方向时,改变方向是科学方法的核心。
跨域证据:
- 电商:Groupon 从公益众筹平台转型团购商(来源:Mason, How I Built This, 2014)
- 协作工具:Slack 从游戏公司转型企业通讯工具(来源:Butterfield, Slack Origin Story, 2013)
应用方式:每月一次 Pivot/Persevere 会议,数据支持继续吗?不支撑该往哪转?
局限:频繁 Pivot 消耗团队士气。Pivot 前必须有清晰的决策框架。
原理 5: 创新核算(Innovation Accounting)
一句话定义:用可操作指标替代虚荣指标衡量真正进展。
跨域证据:
- 即时通讯:IMVU 发现注册用户数是虚荣指标,活跃付费用户增长曲线才是真进展(来源:Ries, The Lean Startup, 2011)
- 制造:Toyota 用"每小时产生的问题数"而非总产量衡量改善(来源:Ohno, Toyota Production System, 1988)
应用方式:定义 3 个核心指标(获客、激活、收入),用曲线趋势代替总用户数。
局限:过度关注可量化指标会忽略重要但不可量化的维度(如用户情感连接)。
操作协议(Agentic Protocol)
Step 1: 问题分类
适用信号:
- 创业初期高度不确定性
- 有多个方向但资源只够验证少数
- 需要把产品想法转化为可验证假设
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.
- 4d ago First seen · 194 lines · 84 tokens per session scan A 52c649fa939c
lean-startup-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 84 tokens to every session and 2,693 once invoked, about $0.0004 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
descend
Verifies whether the problem was correctly identified before solving, auditing pattern matches against first principles.
fundraising-narrative
This skill should be used when the user asks about "pitch deck", "fundraising story", "investor pitch", "VC narrative", "pitch narrative", "fundraising deck", "pitch structure", "Sequoia format", "why now slide", "market size slide", "TAM SAM SOM", "earned secret", "value hypothesis", "product-market fit"…
investor-relations
This skill should be used when the user asks about "investor update", "board deck", "board meeting", "investor communication", "monthly update", "quarterly update", "investor email", "bad news investors", "pivot communication", "crisis communication investors", "investor ask", "warm intro", "VC relationship"…
ux-principles
User research, usability heuristics, user psychology, accessibility, inclusive design, user testing, and UX metrics.
opencli-sitemap-author
Use when creating or maintaining OpenCLI site sitemaps: agent-facing navigation, page-state, action, workflow, API-reference, pitfall, and fallback knowledge for a website. Use after browser exploration discovers durable site context, when a sitemap is stale, or when promoting local site knowledge into the repo.
golden-rss
Use when testing the rss golden build.