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 renky1025/agent-skills --skill teach-eli5git clone --depth 1 https://github.com/renky1025/agent-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/renky1025/agent-skills/teach-eli5)<a href="https://agentmods.dev/skills/renky1025/agent-skills/teach-eli5"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/teach-eli5/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/renky1025/agent-skills/teach-eli5"><img src="https://agentmods.dev/badge/skills/renky1025/agent-skills/teach-eli5.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 | $0.00179 | $0.02127 |
| Opus 5 | $0.00089 | $0.01064 |
| Sonnet 5 | $0.00036 | $0.00425 |
| Haiku 4.5 | $0.00018 | $0.00213 |
Grade A, and why
teach-eli5 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
teach-eli5 —— 给小白讲明白的教学引擎
把任何复杂主题,拆成「图多、字少、类比先行」的自包含教学 HTML,让零基础的人看图就能懂。
本技能融合了 mattpocock teach 的方法论(状态化、以目标锚定、最小可教学单元、复用组件、沉淀术语)与 eli5 的小白约束(不用术语、先类比、后精确)。
哲学一句话:先让用户"啊哈"一下,再让他"记住"。 前者靠类比和图,后者靠重复和可回看的精美页面。
教学工作区(状态保存位置)
把当前目录当作教学工作区。用户的学习状态用几个文件持久化,跨会话累积:
MISSION.md:用户为什么想懂这个主题(所有教学决策的锚点)。格式见 references/MISSION-FORMAT.md。./lessons/*.html:每一课是一个自包含 HTML 教学页。这是教学的主单元。命名0001-<slug>.html递增。./assets/:可复用组件(共享样式表、类比卡片模板、图示 helper、quiz widget)。见 Assets。./references/glossary.md:术语表,本工作区的"官方语言"。一旦建立,每课都遵守。./learning-records/*.md:学习记录(类似软件开发的 ADR),记录用户已搞懂的非显然结论。命名0001-<slug>.md递增。NOTES.md:你的草稿本,记用户偏好与工作备忘。
流程
第 0 步:定锚(Mission)
如果用户没说清为什么想懂这个,或 MISSION.md 还没写,先访谈再动笔。
含糊的目标会产出抽象的课。用 MISSION-FORMAT 的格式记录。
用户的"想搞懂"常是表层,要往下挖一层真实诉求("想给客户解释""想面试""想修自家水管")。
若用户只是随口要一个一次性讲解(如
/eli5 黑洞),可直接进入第 2 步产单课,不强制建全工作区;但仍建议顺手写一句 MISSION。
第 1 步:判定起点(ZPD,最近发展区)
每课都要让用户感到"刚好有点挑战"。读 learning-records/ 和 NOTES.md,判断:
- 用户已知什么(别重复教)
- 当前最该懂的"下一个最小知识点"是什么
- 这个知识点是否直接服务于 MISSION
小白优先用生活类比搭桥,再引入精确概念。例子:讲"API"→先"餐厅里服务员帮你传菜",再"程序之间传数据的约定"。
第 2 步:产出一课(Lesson = 自包含 HTML)
每一课是一个 ./lessons/000N-<slug>.html,小白友好是硬约束:
- 图多字少:核心机制用 SVG 图示 / 类比图表达,正文克制。每屏只讲一件事。
- 先类比,后精确:先用生活类比让人"啊哈",再给一句精确表述(精确句可折叠或放最后)。
- 禁用行话(除非已进 glossary 且本页首次出现时就地解释)。用词对齐
references/glossary.md。 - 一个可带走的小收获:每课结束时用户应能复述一个要点。
- Tufte 式排版:干净、可读、留白足;这是用户会回头复习的页,不是一次性聊天。
- 紧扣 MISSION:说明"懂这个对你那个目标有什么用"。
- 一句提醒:页尾提示"有不懂的随时问,我可以接着讲"——你是老师,不是一次性生成器。
版面规范见 references/LESSON-FORMAT.md。每课链接到其它课与 reference 文档(HTML 锚点)。 如环境允许,用 CLI 命令打开该 HTML 给用户看。
第 3 步:沉淀(每次产课顺手做)
- 术语:出现且用户已理解的词,加进
references/glossary.md(定义一两句,列出"避免混用的说法")。 - 学习记录:用户展现了真理解(答对了 / 说清了 / 纠正了误区),写一条
./learning-records/000N-<slug>.md。仅记"决策级洞见",不写流水账。格式见 references/LEARNING-RECORD-FORMAT.md。 - 复用组件:本课用到的新可复用部件(图示模板、quiz),写成
./assets/下的组件并链接,别内联到单课里(assets/base.css是首个该有的共享样式)。
What ships with it
5 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 · 101 lines · 179 tokens per session scan A 29bff3feec98
teach-eli5 is a skill published in the GitHub repository renky1025/agent-skills (11 stars, last pushed 2d ago), licensed MIT. It adds 179 tokens to every session and 2,127 once invoked, about $0.0009 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 2026-08-31.
Other skills, from other repositories
mindos
MindOS: local knowledge assistant & shared KB. Keeps decisions, notes, SOPs, debugging lessons, research findings, preferences across sessions/agents. Core: save notes, search KB, organize files, run workflows, review, append CSV, hand off context, distill lessons. NOT for app source or paths outside KB. Triggers…
hidden-talents
Interview you in depth to surface overlooked or suppressed talents and write your Personal Talent Manual.
socratic
Diagnose a confusion Socratically, one question at a time, until the question actually worth answering surfaces — then answer that one.
two-layer-explain
Explain a concept twice — for a newcomer and for an expert — then bridge the two layers, flag the likely misunderstandings, and set three check questions.
deconstruct
Reverse-engineer why a finished piece of work succeeds and extract what transfers to your own — rules, a checklist, and a first exercise.
newbie-guide
A Chinese-language guide for beginners who have an unclear goal or do not know how to break a task into steps.