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 Liuziyu77/gene-skill --skill feynman-explainer-toolgit clone --depth 1 https://github.com/Liuziyu77/gene-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/liuziyu77/gene-skill/feynman-explainer-tool)<a href="https://agentmods.dev/skills/liuziyu77/gene-skill/feynman-explainer-tool"><img src="https://agentmods.dev/badge/skills/liuziyu77/gene-skill/feynman-explainer-tool/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/liuziyu77/gene-skill/feynman-explainer-tool"><img src="https://agentmods.dev/badge/skills/liuziyu77/gene-skill/feynman-explainer-tool.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00160 | $0.01816 |
| Opus 5 | $0.00080 | $0.00908 |
| Sonnet 5 | $0.00032 | $0.00363 |
| Haiku 4.5 | $0.00016 | $0.00182 |
Grade A, and why
feynman-explainer-tool 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 9d 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 — 161 lines — stays where its author put it; the contents beside it link to each section on GitHub.
费曼讲解器
「如果你不能简单地解释它,你就没有真正理解它。」
这个 Skill 不是帮你给复杂概念配上漂亮的 PPT——它帮你搞清楚你是否真的理解了你要讲的东西,然后再让你讲给别人听。
触发条件
- 需要向非专业受众解释复杂概念
- 需要为演讲/文章/教程构建解释框架
- 用户怀疑自己「以为懂了但其实没懂」
- 需要把技术文档/论文翻译成可理解的语言
核心工作流(T1)
Phase 0:理解深度自测(费曼先行)
在讲解之前,先测试讲解者的理解深度。
向用户提出以下问题(选最难的一个):
- 「用一个 12 岁孩子能理解的比喻,解释这个概念的核心机制」
- 「这个概念在什么情况下会失效或失准?」
- 「如果你只能用三个词描述这个概念的本质,是哪三个词?」
评估结果:
- 用户能回答 → 说明理解有基础,进入 Phase 1 构建讲解
- 用户答不上来 → 启动「苏格拉底追问模式」(突变基因 M1),先帮用户理解,再讲解
Phase 1:受众定位(工具纪律)
明确两件事(不超过 2 个问题):
- 目标受众:他们已经知道什么?不知道什么?(决定从哪里「接入」)
- 讲解目的:让他们「听懂了点头」还是「能自己解释给别人」?(决定深度)
Phase 2:费曼式结构构建
黄金路径(费曼,显性):从已知到未知,每一步只引入一个新概念。
步骤 A:找「接入点」
受众已知的最相关概念是什么?从这里出发,而不是从定义出发。
步骤 B:一个类比
找到一个目标受众生活经验中的具体类比。
类比必须在核心机制上准确,可以在细节上不完整。
[测试:如果用类比来理解,会产生哪些误导?提前说清楚。]
步骤 C:揭示差异
「和你熟悉的 X 一样,但有一个关键的不同:____」
这是建立准确理解的核心步骤。
步骤 D:后果推导
从这个理解出发,能推导出哪些结论?
让受众自己推导,比直接告诉他们更有记忆效果。
工具纪律补充(explainer-skill,显性):
- 每个 section 不超过 3 个核心概念
- 有「检查理解」节点(提问)
- 结尾有「如果你真的理解了,你应该能回答:____」
Phase 3:质量验证(费曼标准)
完成草稿后,执行三项检查:
检查一:术语清单 列出讲解中用到的所有专业术语,逐一检查:是否每个都被解释过,且解释不依赖其他专业术语?
检查二:类比反测 列出所有类比,逐一检查:使用这个类比会产生哪些误导?是否在讲解中已经指出?
检查三:最难问题 想象一个聪明但完全不了解背景的人,他会问什么让你无法回答的问题?如果想不出来,说明你的讲解过于简化,遗漏了真正困难的部分。
突变基因(M1):苏格拉底追问模式
来自:定向突变(用户不理解时主动追问帮助理解)
触发:Phase 0 评估发现用户理解不足时,或用户主动说「我不太理解这个概念」。
操作:
不直接给出解释,而是先问:
Q1: 「你目前对这个概念的理解是什么?哪怕不完整也说说看」
Q2: 「你觉得哪里最难理解?」
Q3: 「你能想到任何和它相似的东西吗?」
根据用户回答,识别「理解的断点」:
→ 找到断点后,针对断点构建最小解释(而非全面解释)
→ 解释完成后再问「现在你觉得哪里还不通?」
→ 循环,直到用户能自己给出一个粗糙但方向正确的类比
苏格拉底模式的原则:
- 不做长篇讲解,每次只解释一个「断点」
- 始终以用户的回答为下一步的起点
- 目标:用户自己说出答案,而不是被动接受讲解
激活条件:用户无法回答 Phase 0 的自测问题,或主动要求「帮我搞懂」。 不激活条件:用户已经理解,只需要帮忙组织讲解给他人。
表达 DNA(来自费曼,显性)
| 维度 | 合成体表达方式 |
|---|---|
| 起点 | 永远从受众「已知的」出发,不从定义出发 |
| 类比密度 | 高——每个核心概念至少一个类比 |
| 确定性 | 对能解释清楚的:自信。对解释不了的:直接说「这部分我也没想清楚」 |
| 禁忌 | 「显而易见」「众所周知」「如你所知」——如果这些词后面的内容真的显而易见,就不需要讲了 |
诚实边界
- 适合「可用类比解释的」概念;某些极度抽象的数学对象(如高维拓扑)类比效果有限
- 苏格拉底追问模式需要用户愿意配合,不适合只想要「快速答案」的场景
- 工具不能替代讲解者对领域的真实理解——如果讲解者本身不理解,工具也无法凭空生成准确的解释
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.
- 9d ago First seen · 161 lines · 160 tokens per session scan A da0ec7364558
feynman-explainer-tool is a skill published in the GitHub repository Liuziyu77/gene-skill (56 stars, last pushed 4mo ago), licensed MIT. It adds 160 tokens to every session and 1,816 once invoked, about $0.0008 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.