Description

当用户纠结要不要学某个东西、学到什么程度，或在做时间/精力/项目取舍时使用。用「简易策略」先逼问要解决的既定问题，检验现有知识能否搞定，评估知识贬值速度与 ROI，用「探索 vs 应用」判断该学新的还是用现有的，给出「学 / 不学 / 只学最小够用」的结论，避免囤积会贬值的知识。触发场景：要不要学 X、值不值得深...

README (SKILL.md)

简易策略（learn-occam）

Name: Learn Occam
Author: li-evan

核心信条：这世界最有价值的不是知识，是你的时间。 能用现有知识解决的就别学新的；以后要用的，以后再学。

何时用

用户在纠结"要不要学 X / 学到什么程度 / 精力往哪放"。这是"广度优先、兴趣队列过长"倾向的刹车。

流程

第一步：先找"既定问题"

逼问一句：你要解决的具体问题是什么？ 没有具体问题、纯"感觉该学 / 别人都在学"→ 直接进"以后再学"队列，不占当下精力。理解知识的作用，重于知识本身。

第二步：现有知识能不能搞定

问清用户已经会什么——能解决就别学新的。拿不准"是不是其实已经会了"就配合 learn-crossover。

第三步：贬值速度 + ROI

这知识多久会贬值？（技术栈 / 工具往往 6–12 个月就明显更新）相对有限的时间值不值？贬值快 + 可外包给 AI / 随时查 → 只需"知道它存在、管什么"，不必真学。

第四步：探索 vs 应用（N 臂老虎机）

现在该"探索"（学新）还是"应用"（用现有）？探索成本越高 → 越该偏应用。只有目标够难、现有知识确实够不着时，简易策略才督促你学。

第五步：给结论

明确三选一：① 学（值得且现有搞不定）/ ② 不学（入"以后再学"队列）/ ③ 只学最小够用的那一块（点明是哪一小块）。要深挖就转 learn-graph 建路径。

注意

⚠️ 铁律·只用确证的已会知识：判断用户「已经会什么」只能用他确证学过的知识（亲口确认或可靠背景）；严禁把「正在讲的材料 / 文章作者背景 / 对话里别人的知识」当成用户会的。拿不准 → 直接问「⚠️ 你学过 ___ 吗？」，绝不替他假设。

简易策略不是"少学"，是"让问题决定你学什么"。
它的缺点是易陷局部最优——拿不准"是不是缺前置知识"时转 learn-graph。
同族 skill：learn-crossover(已会什么) learn-graph(系统建图) learn-prototype(动手迭代) learn-feynman(自查)。

Usage Guidance

Install this if you want an opinionated assistant strategy for deciding what is worth learning now. It may push conversations toward time, ROI, and minimal-useful-learning decisions, but it does not add code execution, persistence, credentials, or sensitive data access.

Capability Assessment

✓ Purpose & Capability

The skill's stated purpose is to help users decide whether to learn something, how deeply to learn it, or where to spend time and effort; the instructions match that purpose.

ℹ Instruction Scope

The trigger language is somewhat broad and opinionated, so it may steer loosely related learning conversations into its ROI-focused decision framework, but this is disclosed and limited to conversational guidance.

✓ Install Mechanism

The package contains only a SKILL.md markdown file and declares no dependencies, scripts, or API key requirements.

✓ Credentials

No file access, network use, command execution, credential handling, or data mutation is requested, which is proportionate for a conversational coaching skill.

✓ Persistence & Privilege

The artifact does not request persistence, background execution, privilege escalation, memory storage, or access to user profiles or sessions.

Version History

v1.0.0

Version 1.0.0 of learn-occam - initial release. - Provides a practical decision process for whether and how much to learn something, focused on ROI and minimizing wasted effort. - Emphasizes starting from specific problems and assessing if current knowledge is sufficient before investing time in new learning. - Includes guidance for evaluating knowledge obsolescence and using "explore vs. exploit" strategies. - Offers clear conclusions: learn, don’t learn, or learn the minimal useful subset. - Highlights the importance of only relying on knowledge the user has confirmed they possess. - Integrates with related skills like learn-crossover, learn-graph, and others for a comprehensive knowledge management approach.

Metadata

Slug learn-occam

Version 1.0.0

License MIT-0

All-time Installs 0

Active Installs 0

Total Versions 1

Frequently Asked Questions

What is Learn Occam?

当用户纠结要不要学某个东西、学到什么程度，或在做时间/精力/项目取舍时使用。用「简易策略」先逼问要解决的既定问题，检验现有知识能否搞定，评估知识贬值速度与 ROI，用「探索 vs 应用」判断该学新的还是用现有的，给出「学 / 不学 / 只学最小够用」的结论，避免囤积会贬值的知识。触发场景：要不要学 X、值不值得深... It is an AI Agent Skill for Claude Code / OpenClaw, with 42 downloads so far.

How do I install Learn Occam?

Run "/install learn-occam" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Learn Occam free?

Yes, Learn Occam is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Learn Occam support?

Learn Occam is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Learn Occam?

It is built and maintained by Evan (@li-evan); the current version is v1.0.0.

More Skills

Learn Occam