Learn feynman
当用户学完一个东西想自查是否真懂、或觉得「好像懂了」但不确定时使用。用「费曼学习法」让他用自己的话把概念讲出来，你扮好奇学生专挑他含糊/跳过的地方追问，把「讲不顺的模糊处」揪出来作为没真懂的漏洞，定位是缺前置知识还是没想透，判断理解是否闭环。触发场景：我学完了考考我、自查一下、我好像懂了、我讲讲你看对不对、检验我的理解、这个我真懂了吗。From its SKILL.md
npx -y skills add Li-Evan/Bloom --skill learn-feynmanAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
SKILL.md
2.4 KB, 755 tokens by cl100k_base, as published. Nobody here has run it
费曼学习法（learn-feynman）
核心信条：能简单地教会别人，才算真懂。 讲的时候被简化或跳过的地方，正是"我以为我懂了"的幻觉核心点。
何时用
用户学完一个东西想验真伪，或隐约觉得"好像懂了但不踏实"。也是"重输入轻输出"的一次强制输出。
流程（考官 / 学生模式：用户讲，你挑漏洞）
第一步：让用户讲
请他用自己的话、把你当外行，把概念讲一遍。别让他背定义——要他解释、打比方。
第二步：扮好奇学生追问
专挑他含糊带过、用术语糊弄、跳过的环节追问："为什么？""那这个是怎么来的？""举个例子？"命中他答不上来或开始绕的地方。
第三步：揪出"模糊处"= 漏洞
明确指出哪几处他没真懂（不是责备，是定位）。这些就是幻觉核心点。
第四步：定位漏洞性质
每个漏洞是：① 缺前置知识（→转 learn-graph 定位 / learn-crossover 看是否其实已会）还是 ② 有料但没想透（→当场再讲一轮，直到讲顺）？
第五步：判断闭环
能顺畅讲通、追问不倒 = 闭环。否则明确指出还差哪一环。
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。
- 别太快放水——用户讲得顺也要追问一两个深的，确认不是表面流畅。
- 目标是定位漏洞，不是羞辱；找到漏洞是好事，说明知道往哪补。
- 同族 skill：
learn-occamlearn-crossoverlearn-graphlearn-prototype。
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most explainers skills give in 755 tokens
Counted across 274 of the 289 authors here whose files we hold, read 2026-09-06
- Start with an everyday-life analogyin 7 of 274, across 6 files
- Use multiple analogies for complex conceptsin 6 of 274, across 5 files
- Introduce one simple analogy per explanationin 6 of 274, across 4 files
- Reason conversationallyin 5 of 274, across 3 files
- Ask reflective questions occasionallyin 5 of 274, across 3 files
- Guide the user's thinkingin 5 of 274, across 3 files
- End with a reflective promptin 5 of 274, across 3 files
- Keep explanations conversationalin 5 of 274, across 4 files
- Build the idea step by stepin 5 of 274, across 3 files
- Keep the analogy consistent throughoutin 5 of 274, across 3 files
- Frame direct answers through reasoningin 5 of 274, across 3 files
- Highlight a common mistake or misconceptionin 5 of 274, across 4 files
Said here and by no other author read
- Have the user explain as to a layperson
- Require explanations and analogies, not recited definitions
- Play a curious student who keeps questioning
- Probe vague, jargon-covered, or skipped parts
- Ask why, how it arises, and for examples
- Name the fuzzy spots as gaps in understanding
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.