🧪
AI EngineeringPython

Prototype Learning

by Li-Evan

Prototype Learning is an AI Engineering skill for Claude Code, published by Li-Evan in Bloom.

248 stars39 forkson Li-Evan/BloomAdded 2026/09/02+3% in starsRepository updated 2026/06/23
adaptive-learningagent-skillsai-agentai-tutorbloom-2-sigmachineseclaude-codeclaude-skilledtecheducationfastapilearningllmpersonalized-learningreactself-hostedsocratic-methodstudy-tool
Install in seconds
Install Prototype Learning
Copy Prototype Learning into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/Li-Evan/Bloom/tree/main/skills/learn-prototype ~/.claude/skills/learn-prototype

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/Li-Evan/Bloom.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/learn-prototype/SKILL.md in Li-Evan/Bloom
Installs to
~/.claude/skills/learn-prototype
Collection
One of 7 skills cataloged from this repository
Category
AI Engineering2631 skills

What Prototype Learning does

Prototype Learning helps users start with a minimal version of a task, identify what is wrong with it, and improve through repeated hypothesis and testing. Use it when someone wants to make, study, or improve something and needs a structured way to begin.

Prototype Learning is cataloged under AI Engineering on DirSkills. Prototype Learning comes from a repository tagged adaptive-learning, agent-skills, ai-agent, ai-tutor and bloom-2-sigma.

Documentation

README

改良主义学习法(learn-prototype)

核心信条:洞察缺陷 > 如何优化 > 最终答案。 试图洞察缺陷、自己提出问题,永远不要害怕问题多简单。学习要努力,但要做有效的努力

何时用

用户要动手做 / 研究一个东西,或想把某个已有产出改得更好。这是"重输入、轻输出"短板的解药——逼用户从输入切到输出。

流程(教练模式:引导用户做和提问,不替他做)

第一步:先做最垃圾的原型

别追求完美,先有一个能跑 / 能看的最小版本。卡在"还没准备好"就是没进改良主义。

第二步:引导用户自己洞察缺陷

关键且不能代劳:问他"这哪里不好?为什么不好?"哪怕问题很简单。把"自己提问"的动作交给用户——这是能力泛化的来源。你可以追问、补他没看到的角度,但先让他提

第三步:提改良假说 → 实践 → 检验

针对缺陷提一个改良策略(视为假说,可对可错),动手改,看效果。错了也有用——错误暴露后,下次自动规避这个方向。

第四步:迭代 / 推翻

循环②③,直到无法再优化 → 推翻重做。允许"不正确但有用的版本"——能解决当前问题就够了,不必一开始追求完美架构。

第五步:沉淀方法论

把"这次怎么从 A 改到 B"的方法本身记一笔(每个解决的问题都成为后续的法则)。改得越多,方法越泛化,提问越准。

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。

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Prototype Learning

  • What else does Li-Evan publish alongside Prototype Learning?

    Prototype Learning is one of 7 skills that DirSkills catalogs from Li-Evan/Bloom, the repository it ships in. Its siblings there include Bloom Tutor, Cross-Learning and Feynman Learning. Each one is a separate skill with its own page in this directory, installs the same way Prototype Learning does, and is maintained by Li-Evan in that same repository. The rest of the collection is listed on the Li-Evan/Bloom page.

  • How does Prototype Learning compare to other AI Engineering skills?

    Prototype Learning ranks #2323 by stars among the 2631 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Prototype Learning against them. Open each page to compare what they document and how they install.

More from Li-Evan/Bloom

Prototype Learning is one of 7 skills cataloged on DirSkills from Li-Evan/Bloom.

See all 7 skills
📚
1h ago

Bloom Tutor

Bloom Tutor uses a Chinese, one-on-one Socratic learning flow to study a topic through generated lesson files, feedback, and learning logs. Use it when starting a new subject, continuing a course, or reviewing progress.
AI Engineering
24839
🧠
1h ago

Cross-Learning

Cross-Learning helps explain a new concept by linking it to knowledge the user already has. It is used when something feels unfamiliar or hard, to map it to known structures, analogies, and underlying patterns.
AI Engineering
24839
🧠
1h ago

Feynman Learning

Feynman Learning helps users test whether they really understand a concept by explaining it in their own words and answering follow-up questions. Use it when someone says they “kind of get it” and wants to find the gaps.
AI Engineering
24839
🧠
1h ago

Knowledge Graph Learning

Knowledge Graph Learning helps you build a concept-and-relationship map for a new field so you can learn it systematically. It is used when you need a starting point, a learning path, or a clear answer to how much is enough.
AI Engineering
24839
🧠
1h ago

Learn Deep

Learn Deep helps a user understand a new concept from multiple angles: prior knowledge, depth, knowledge map, prototype, and Feynman-style checks. Use it when someone wants to learn, understand, or explain a concept before choosing a deeper direction.
AI Engineering
24839
🧠
1h ago

Learn Occam

Learn Occam helps decide whether to learn something, how far to go, or whether to use existing knowledge instead. It asks for the concrete problem, checks what is already known, and returns learn, don't learn, or learn the minimum needed.
AI Engineering
24839