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/feynman-learning-skillnpx skills add peterfei/forge-skill --skill feynman-learning-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/feynman-learning-skill)<a href="https://agentmods.dev/skills/peterfei/forge-skill/feynman-learning-skill"><img src="https://agentmods.dev/badge/skills/peterfei/forge-skill/feynman-learning-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 | $0.00094 | $0.03037 |
| Opus 5 | $0.00047 | $0.01519 |
| Sonnet 5 | $0.00019 | $0.00607 |
| Haiku 4.5 | $0.00009 | $0.00304 |
Grade A, and why
feynman-learning-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 — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.
费曼学习法 · 思维工具
"If you can't explain it simply, you don't understand it well enough." — Richard Feynman
激活条件与触发词
- 直接调用：「用费曼学习法」「按费曼的方式学...」
- 语义触发：用户说"学不会""讲不明白""以为自己懂了但不会用""知识卡壳"
- 组合调用：「先用费曼学习法吃透概念，再用第一性原理分析」
方法框架概览
费曼学习法的核心是以教代学暴露理解缺口，它通过尝试教授发现知识漏洞、简化表达检验理解深度、类比构建桥接认知来将浅层记忆转化为深层理解。
核心原理（3-7个，每个须附 ≥2 个跨域证据）
原理 1: 用教代学暴露知识缺口（Teaching Exposes Knowledge Gaps）
一句话定义：当你尝试将一个概念教给他人时，你会立即发现哪些地方自己其实不懂。
跨域证据：
- 物理学教学：Feynman 本人在准备 Caltech 物理学讲义时发现多个他以为懂的概念其实理解浅薄（来源：Feynman, Surely You're Joking, 1985）
- 现代学习实践：Scott Young 用"教给想象中的学生"完成 MIT 4 年计算机课程只用了 12 个月（来源：Young, Ultralearning, 2019）
应用方式：面对任何想学的内容，拿出一张白纸，假装给一个 12 岁的孩子讲解。在讲不下去的地方标记——这就是你的知识缺口。
局限：不适用于纯身体技能（如游泳、骑自行车）。适合概念性知识的学习。
原理 2: 简化是理解的终极检验（Simplification as Ultimate Test）
一句话定义：如果你不能用一个简单的比喻或平实的语言解释一个概念，说明你没有真正理解它。
跨域证据：
- 教育技术：Khan Academy 创始人 Sal Khan 的核心教学原则是"用最简单的话解释最难的概念"（来源：Khan, The One World Schoolhouse, 2012）
- 物理学：Einstein 说"如果你不能把它解释给你的祖母听，你就没理解"（来源：引用自 Einstein 相关资料）
应用方式：当你讲完后，检查你的解释中是否包含自己不理解的术语。如果有，回去重新学习那个术语直到能用平实语言解释为止。
局限：某些高度技术化或数学化概念（如量子场论）无法完全用日常生活语言表达而不丢失精度。
原理 3: 类比构建桥接认知（Analogies Bridge Cognitive Gaps）
一句话定义：将新概念与已知的概念类比，利用已有认知结构理解新事物。
跨域证据：
- 物理学教学：Feynman 用"水流"类比"电流"讲解电学基础，使得没有物理背景的学生也能理解基本概念（来源：Feynman, The Feynman Lectures on Physics, 1963）
- 计算机科学：数据结构教材用"图书馆书架"类比"数组"、"排队买票"类比"队列"（来源：众多 CS 教材实践）
应用方式：对每个新概念问"这个概念最像我已经懂的什么？"但必须同时标注这个类比在哪一点失效。
局限：不准确的类比比没有类比更糟。每个类比必须标注失效边界。
原理 4: 主动检索强于被动复习（Active Recall Over Passive Review）
一句话定义：大脑不是硬盘——回忆比反复阅读更有效地强化记忆。
跨域证据：
- 认知科学：Roediger & Karpicke (2006) 实验证明主动检索组 1 周后记忆保持率是重复阅读组的 2 倍（来源：Roediger & Karpicke, Psychological Science, 2006）
- 语言学习：间隔重复系统（如 Anki）基于 Ebbinghaus 遗忘曲线，用主动回忆卡而非多次阅读（来源：Ebbinghaus, Memory: A Contribution to Experimental Psychology, 1885）
应用方式：学完后合上书本，在白纸上写出你记得的所有内容。然后对照原文检查遗漏了什么。
局限：主动检索需要更多认知努力，学习者可能倾向于偷懒选择重复阅读。
操作协议（Agentic Protocol）
Step 1: 问题分类 — 判断该方法是否适用于当前问题
适用信号：
- 用户学习新概念但感到模糊和不确定
- 用户以为自己懂了但无法用自己的话解释
- 用户需要在短时间内深度掌握一个主题
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 · 181 lines · 94 tokens per session scan A bba4e2cdf8be
feynman-learning-skill is a skill published in the GitHub repository peterfei/forge-skill (13 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 3,037 once invoked, about $0.0005 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
omh-curriculum-design
This is a Hermes-native curriculum-design workflow skill.
learn
Guided, hands-on course teaching architects how to use Codex or Claude Code — six short modules, each built around an exercise on a bundled sandbox project (a fictional Brooklyn art museum expansion). Resumable across sessions via PROGRESS.md. Use when the user runs $learn or /as:learn, says they're new to AI-assisted…
memory-protocol
Universal protocol for total-agent-memory MCP server. Activate at session start, before any non-trivial task, after every significant action, on errors, and at session end. Relevant whenever the user mentions: memory, recall, past context, decisions history, conventions, lessons learned, "продолжаем", "сохранись"…
new-feedback
Log a harness lesson / post-incident so the SYSTEM improves, not just this one bug — fires on "log a harness lesson", "post-incident", "we should make this less likely", System-Evolution moments. Part of the Agentsmith harness; scaffolds a numbered docs/feedback/NNNN-.md with the five-stage template (R9 — numbers are…
memory
Activate this skill when starting a new session, beginning a new task, saving knowledge, recalling past decisions, or after completing significant work. Also activate on errors to log them for pattern analysis. Relevant when the user asks about memory, past context, lessons learned, decisions history, project…
beamer-academic
Generate high-quality academic Beamer slides from a thesis/paper (PDF, Word, or LaTeX source). Compatible with Claude Code and Codex. Supports thesis defense, proposal presentations, and conference talks. Built-in layout library with 13 professional page types, 5 color schemes, and interactive editing loop. Use when…