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 Job-Yang/jobbyang-ai-skills --skill feynman-explainergit clone --depth 1 https://github.com/Job-Yang/jobbyang-ai-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/job-yang/jobbyang-ai-skills/feynman-explainer)<a href="https://agentmods.dev/skills/job-yang/jobbyang-ai-skills/feynman-explainer"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/feynman-explainer/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/job-yang/jobbyang-ai-skills/feynman-explainer"><img src="https://agentmods.dev/badge/skills/job-yang/jobbyang-ai-skills/feynman-explainer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00284 | $0.04666 |
| Opus 5 | $0.00142 | $0.02333 |
| Sonnet 5 | $0.00057 | $0.00933 |
| Haiku 4.5 | $0.00028 | $0.00467 |
Grade A, and why
feynman-explainer 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 12d 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Feynman Explainer · 费曼讲透法
唯一目标：能把一个东西讲到外行也能听懂，才算真懂。 这个技能强制用费曼技巧组织「总结 / 调研 / 解读」类输出，杜绝「术语糊弄、看着懂实则没懂」。
本技能是一套风格与结构的强约束，不绑定任何具体主题。命中即按本文规则改造输出，
正反例和比喻库见 references/style-examples.md（动手前先 Read 一遍）。
⚠️ 两条最高铁律（先读这两条，违反任一条 = 用错了本技能）：
铁律一 · 逻辑链，不是要点清单：费曼讲透 = 用一条逻辑链把一个问题层层推导通， 不是把内容切成一堆并列要点。若你在写「要点 1 / 要点 2 / 要点 3」这种平铺清单，就是错的。
铁律二 · 脚手架要拆，不要留在成品上：费曼五步、比喻、难理解点、费曼检验、难度分层—— 这些全是我用来组织思路的内部脚手架，不是要打印在成品上的标签。楼盖好了脚手架要拆掉。 成品必须读起来是一篇行文流畅的文章：比喻自然融进句子，难点在讲解中自然点破， 绝不出现「💭 费曼比喻：」「🤔 难理解点在哪？」「要点 X」「【P0】」这类结构外露的牌子。 详见 §1、§2。
0. 触发判断（先想清楚要不要用）
| 场景 | 启用 |
|---|---|
| 「总结一下这篇文档/论文/方案」 | ✅ |
| 「调研一下 XX 技术/产品/概念」 | ✅ |
| 「讲透 / 讲明白 / 帮我搞懂 XX」 | ✅ |
| 「XX 的原理是什么」且想真正理解 | ✅ |
| 解读源码 / 黑盒机制 / 硬核技术 | ✅ |
| 「一句话告诉我 XX 是啥」 | ❌ 直接答 |
| 纯创作 / 翻译 / 润色 | ❌ |
| 「简单说就行，别展开」 | ❌ 尊重用户 |
| 要把内容写成一篇对外发布的文章 / 公众号稿 | ❌ 输出型，交给 tangshan-style（汤山体）。费曼只管"我自己看懂"，不管"写给别人看" |
拿不准时：先给一句话核心，再问「要不要我用费曼方式讲透？」不要默认长篇大论。
⚠️ 和汤山体的分工：费曼 = 输入型（我要看懂，调研/总结/搞懂）；汤山体 = 输出型（写成发出去的文章）。 握手是单向的：汤山体写文章遇到硬概念时会来调费曼把那段讲白；费曼绝不反向调用汤山体——费曼产出永远是"讲透"，不是"成稿"。
1. 费曼五步（这是我脑子里的施工流程，不是成品的排版模板）
这五步不是五个并列的动作，而是一条推进链：前一步的答案是后一步的起点。 注意：五步是"我怎么想"，不是"成品怎么排版"——成品里看不到这五步的名字，只看到它们的效果。
- 先讲问题，不讲术语 —— 开头永远用大白话说清「这事到底在解决什么问题 / 为什么反直觉」， 严禁上来甩名词。这是整条链的第一个扣子。
- 顺着问题往下追 —— 讲机制时始终问「那接下来呢 / 那为什么不行 / 那怎么办」，让每一段都 是上一段的自然结果，而不是另起炉灶的新条目。抽象概念必须落到生活场景。
- 把难点讲化开，而不是挂个牌子 —— 遇到硬核转折，直接在正文里用一句话点破新手最容易
误解的地方（「你可能以为是 A，其实是 B」），然后展开。不要写一行
🤔 难理解点在哪？当小标题——那是脚手架，要拆。 - 费曼检验是自检，不是给读者的字幕 —— 我在心里问「这段能不能 30 秒讲给外行」， 过不了就重写。成品里不要出现「费曼检验：……」这行字。
- 收口 —— 结尾用一两句话把整条链复述一遍，让人合上文档也能转述。速查表 / 口诀 仅在内容确实复杂、值得一张总览表时才用，且是自然的收尾，不是套模板。
2. 标准输出结构：逻辑链，不是要点清单（强制套用）
2.1 核心原则：讲一条链，不摆一堆点
费曼讲透的骨架是一条因果推导链，不是并列的知识条目。 一个主题应该像剥洋葱、 像追问一个侦探问题那样，一层推出下一层：
这东西想解决什么问题？
→ 最朴素的做法是什么？为什么它不够用？ （制造张力）
→ 于是真正的做法是什么？它怎么解决了上面的问题？ （给出机制）
→ 但这么做又带来什么新麻烦 / 反直觉的地方？ （深入）
→ 所以最终是怎么收口的？我该记住什么？ （闭环）
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 12d ago First seen · 222 lines · 284 tokens per session scan A 88e064f6dde8
feynman-explainer is a skill published in the GitHub repository Job-Yang/jobbyang-ai-skills (65 stars, last pushed 8d ago), licensed MIT. It adds 284 tokens to every session and 4,666 once invoked, about $0.0014 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
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.