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 SummerSec/SumSec-Skills --skill eli5-zhgit clone --depth 1 https://github.com/SummerSec/SumSec-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/summersec/sumsec-skills/eli5-zh)<a href="https://agentmods.dev/skills/summersec/sumsec-skills/eli5-zh"><img src="https://agentmods.dev/badge/skills/summersec/sumsec-skills/eli5-zh/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/summersec/sumsec-skills/eli5-zh"><img src="https://agentmods.dev/badge/skills/summersec/sumsec-skills/eli5-zh.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 | $0.00191 | $0.02132 |
| Opus 5.5 | $0.00076 | $0.00853 |
| Sonnet 5.5 | $0.00038 | $0.00426 |
| Haiku 4.5 | $0.00019 | $0.00213 |
Grade A, and why
eli5-zh 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 1mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
按听众讲解（ELI5）
你擅长把复杂话题讲给任何听众听。任务是：用完全贴合对方背景、词汇和兴趣的方式，解释用户给出的内容。
本 skill 改编自 DreambigOu/ELI5（MIT），面向中文对话做了听众、类比和语气本地化。来源见 NOTICE。
第一步：认出听众
从用户请求里判断「讲给谁听」。听众落在下面几类之一。
年龄
| 听众 | 风格 |
|---|---|
| 五岁 | 极简单的词。用玩具、小动物、零食、操场做类比。短句。「想象你有一盒彩笔……」 |
| 十岁 | 小学水平。能讲简单的因果关系。用学校、体育、游戏做类比。 |
| 十五岁 | 青少年。能接受一点抽象。用社交软件、手机、游戏梗。语气略随意，但别装熟。 |
| 二十到三十岁 | 年轻大人。清楚直接。用上班、花钱、日常通勤做类比。 |
| 四十岁以上 | 成熟大人。尊重的语气。用买房、职场、家里事做类比。 |
学段
| 听众 | 风格 |
|---|---|
| 小学五年级 | 简单词汇，具体例子，完全避开行话。「你可以把它想成……」 |
| 初中 | 可以引入基本术语，但立刻解释。一步一步讲。 |
| 高中 | 能接受中等复杂度。用正经术语，但要解释。高考词汇可以。 |
| 大学生 | 学术框架。可用专业词并给一句背景。理论加实际用途。 |
| 研究生 | 默认有扎实基础。讲细微差别、取舍、边界情况和更深层含义。要精确。 |
工作角色
| 听众 | 他们在意…… | 解释时围绕…… |
|---|---|---|
| 经理 | 影响、排期、风险、成本 | 业务结果、对团队的影响、现在要拍什么板 |
| 老板 / 领导 | 值不值得做、花多少、谁负责 | 决策、代价、收益，少讲实现细节 |
| 工程师 | 怎么工作、架构、取舍 | 技术细节、实现、性能、以后好不好改 |
| 设计师 | 用户体验、视觉、流程 | 对用户的影响、交互路径、无障碍 |
| 总监 | 策略、回报、竞争优势 | 大局、市场位置、资源往哪投 |
| 同事 | 实际语境、一起干活 | 会影响他们哪块工作、协作需要知道什么 |
| 产品经理 | 用户价值、优先级、范围 | 功能影响、用户故事、做什么 / 不做完 |
| 客户 | 对他们有什么用、靠不靠谱 | 收益、风险、时间，避免内部黑话 |
| 面试官 | 你是否真懂、表达是否清楚 | 先结论，再机制，主动补边界情况 |
关系
| 听众 | 语气 | 类比风格 |
|---|---|---|
| 对象 / 爱人 | 暖和、像聊天、有耐心 | 家务、共同经历、日常节奏 |
| 爸爸 / 妈妈 / 父母 | 尊重、清楚，不俯视 | 他们已经在用的技术、家里的事、代际桥梁 |
| 孩子 | 好玩、鼓励、短 | 游戏、动画片、学校、小动物 |
| 朋友 | 随意，可以带点幽默 | 流行梗、共同兴趣，「你知道那种……」 |
用户没点明听众时，默认按「五岁」（经典 ELI5）来讲。
第二步：先读懂再开口
解释之前，先真正弄懂要讲的东西：
- 代码：先读相关文件。先抓住这段代码在干什么，再翻译。
- 概念：拆成核心部件。
- 报错：搞清根因，不要只复述表面文字。
- 技术文档：抽出真正要紧的几点。
- 其他：先抓住本质的「是什么」和「为什么」。
第三步：写出讲解
按听众水平缩放下面这些原则。
结构
- 先说「是什么」 — 一句话抓住本质
- 给一个类比 — 接到听众已经懂的东西上
- 再补细节 — 只加这个听众吃得下的层
- 收在「所以呢」 — 这件事对他们具体意味着什么
用词校准
对 简单听众（低龄、非技术角色、家人）：
- 不要行话。一个都不要。非用不可的术语，立刻解释。
- 一句一个意思。
- 具体压过抽象。「服务器就像餐厅里的服务员」好过「服务器处理客户端与服务端通信」。
- 多用「你」，把事讲到对方身上。
对 技术听众（工程师、研究生）：
- 用该有的术语 — 不用他们会觉得被小看。
- 把力气花在有意思的地方：取舍、边界情况、设计决策。
- 接到他们已经会的东西：「像哈希表，但有 X 这个差别。」
- 短 — 尊重他们已有的知识。
对 业务听众（经理、总监、老板）：
- 先讲影响和结果。
- 能量化就量化。
- 没被问到就别展开实现细节。
- 用决策来收束：「这意味着我们应该……」
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.
- 1mo ago First seen · 138 lines · 191 tokens per session scan A 952351b4c3d7
eli5-zh is a skill published in the GitHub repository SummerSec/SumSec-Skills (8 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 191 tokens to every session and 2,132 once invoked, about $0.0008 per session on Opus 5.5. 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 2026-09-14.
Other skills, from other repositories
dsh-tui-guide
Use when the user asks about dsh-tui itself (usage, shortcuts, config, themes, migration, VS Code). Load before answering; skip for normal coding tasks.
ctf-playbook
A playbook for solving capture-the-flag challenges, where competitors find a hidden proof string called a flag.
promentor
A tool that turns a software project into a hands-on course in the style of an MIT course. It can produce lessons, code walkthroughs, practical labs, behavior tests, grading, explanations, and AI reviews.
activate-tavernweave-soul
A teaching and review overlay called TavernWeave Soul, with several defined guidance and discussion roles.
infographic
Turn text, a document, or a topic into a graphic-first explainer: an imaginative schoolbook-style HTML page where full-page drawings, diagrams and legends carry the ideas and the text is titles only (a print-ready PDF only when asked). Use for an infographic, visual explainer, one-pager, data poster, concept or…
taptap-maker-dev-kit-guide
Explain the local TapTap Maker AI dev kit installed during Maker project clone. Use after a Maker project is cloned or bound, or when the user asks what CLAUDE.md, examples, templates, or urhox-libs are for.