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 R2h1/my-book-skills --skill v25git clone --depth 1 https://github.com/R2h1/my-book-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/r2h1/my-book-skills/v25)<a href="https://agentmods.dev/skills/r2h1/my-book-skills/v25"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v25/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/r2h1/my-book-skills/v25"><img src="https://agentmods.dev/badge/skills/r2h1/my-book-skills/v25.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 | $0.00058 | $0.01554 |
| Opus 5 | $0.00029 | $0.00777 |
| Sonnet 5 | $0.00012 | $0.00311 |
| Haiku 4.5 | $0.00006 | $0.00155 |
Grade A, and why
v25-三条高速快车道选择 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 11d 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 — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
三条高速快车道选择：互联网、创新与分发
R — 原文 (Reading)
通往快车道的道路不是只有一条，而是有三条主要大道：互联网生意、创新产品或服务、以及创造规模效应。每条大道都有不同的要求、风险和杠杆，但都必须满足5条戒律。
— MJ·德马科, 第35章
I — 方法论骨架 (Interpretation)
三条高速快车道是经过NEEDS检查验证的具体创业路径，每条路径的侧重点不同：
-
互联网生意：订阅服务、内容系统、中介平台、广告支持、电商
- 优势：进入成本低、全球规模、被动性高
- 挑战：竞争激烈、技术门槛（或需要外包）
- 典型满足的戒律：S（规模）、T（时间）
-
创新产品或服务：专利发明、新产品、改进现有产品
- 优势：进入壁垒高、利润率高、品牌差异化
- 挑战：研发投入大、市场验证周期长、失败率高
- 典型满足的戒律：E（进入壁垒）、N（需求）
-
分发/规模效应：连锁、加盟、特许经营、网络营销、电视购物
- 优势：复制已验证的模式、市场扩张快
- 挑战：运营复杂度高、人力资源管理、控制权问题
- 典型满足的戒律：S（规模）、D（需求）
选择原则：没有"最好"的路，只有"最适合你资源和性格"的路。选择标准包括：你的技能组合、风险承受能力、启动资金、期望的参与程度。
A1 — 书中的应用 (Past Application)
德马科的选择（互联网）：他选择了互联网生意，因为他有编程技能，没有大量启动资金，而且互联网生意满足全部5条戒律。他的网站85%被动收入，可以全球服务，技术壁垒保护了他。
能量棒改进者（创新）：有人改进了一种能量棒，以1.92亿美元出售。这是创新路线的典型——在已有品类中做出显著改进，通过专利建立壁垒。
更好的拖把（创新+分发）：有人发明了更好的拖把，通过电视购物卖出5万把。结合了创新产品和分发渠道。
莱斯丽的路径：她先建立了一个互联网生意（快车道），再用赚来的钱实现梦想（流浪狗庇护所）。她选择互联网是因为它满足时间戒律——可以在她追求梦想的同时自动运转。
A2 — 触发场景 (Future Trigger)
触发场景：
- 你已经决定创业但不确定走哪条路时
- 你在互联网生意和实体生意之间犹豫时
- 你有一个发明/改进的想法时
- 你在考虑加盟还是自创品牌时
语言信号：
- "我应该做线上还是线下？"
- "互联网太竞争了，我想做实体"
- "我有一个产品创意……"
- "要不要加盟XX品牌？"
与相邻技能的区分：
- vs v04（NEEDS检查）：v04验证一个生意是否值得做，v25帮你选择"走哪条路去做"。
- vs v23（摇钱树分类）：v23关注生意的被动性结构，v25关注路径选择——先选路，再看这条路能长出哪种摇钱树。
E — 可执行步骤 (Execution)
- 自我评估：列出你的技能、资金、时间、风险承受能力——三条路对资源的要求不同。
- 检查NEEDS：用五条戒律评估每条路在你手上的可行性——不是评估路本身，而是评估"你走这条路"的可行性。
- 计算进入成本：每条路需要多少启动资金和时间？互联网可能最低，创新可能最高。
- 评估被动性潜力：你希望生意最终多"自动"？互联网和内容系统的被动性最高，分发的被动性较低。
- 选择"最不坏"的路径：没有完美路径，选择那个你最愿意持续投入3-5年的方向。
- 设定检验节点：无论选哪条路，设定3个月和6个月的检验点——如果核心指标未达到，及时调整或切换。
B — 边界 (Boundary)
不适用场景：
- 还没决定是否创业的人：先做v01（路线图诊断）和v05（生产者vs消费者思维转换）。
- 已经在一个路径上深耕的人：不要频繁切换路径——每条路都需要时间积累。
失败模式：
- 路径跳跃症：在三条路之间反复横跳，每条路都没坚持到产生结果。
- 高估自身能力：选择了资金/技术要求超出自己能力的路径。
- 低估执行难度：以为选对了路就自动成功——每条路都需要长期高强度执行。
作者盲点：
- 三条路是基于2011年的商业环境总结的，今天的内容创作者经济、AI工具、跨境电商业态已大幅改变创业图谱。
- 三条路的分类可能遗漏了"混合路径"——如互联网+分发（DTC品牌）、创新+互联网（SaaS产品）。
- 低估了"资本路径"——通过收购已有业务来快速进入快车道。
审计信息
验证通过: V1 ✓ / V2 ✓ / V3 ✓
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.
- 11d ago First seen · 95 lines · 58 tokens per session scan A 4ab62abaf901
v25-三条高速快车道选择 is a skill published in the GitHub repository R2h1/my-book-skills (2 stars, last pushed 26d ago), licensed MIT. It adds 58 tokens to every session and 1,554 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 2026-08-31.
Other skills, from other repositories
en-zh-translation-polish
An English-to-Chinese translation and editing process focused on natural Chinese rather than word-for-word wording.
shortfilm-prompt
Generate cinematic AI shortfilm prompts (works with Seedance 2.0, Xiaoyunque, Sora, Kling, Jimeng, Veo) using the 5-stage structure from Mx-Shell's Zombie Scavenger. Trigger when the user wants transformation sequences, multi-shot narrative shorts, weapon-charge/combat segments, emotional family/pet/farewell…
multi-agent-cn
A Chinese-language system design that makes one main agent assign tasks to five persistent subagents instead of doing the work itself.
gpt-image-2-prompt-engine
A structured prompt-writing tool for GPT-Image-2, using reusable JSON templates and a four-step workflow. It is designed for controlled commercial images such as product photos, posters, infographics, brand visuals, UI screenshots, and character designs.
simp
A relationship-advice skill that helps interpret signals, plan respectful approaches, and write sincere messages for someone you like.
chinese-write-checker
A Chinese-language review process for checking an article from an editor's, reader's, writer's, and publishing platform's viewpoints.