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 gongyijie85/mattpocock-skills-dsh-zh --skill teach-zhgit clone --depth 1 https://github.com/gongyijie85/mattpocock-skills-dsh-zhWrote 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/gongyijie85/mattpocock-skills-dsh-zh/teach-zh)<a href="https://agentmods.dev/skills/gongyijie85/mattpocock-skills-dsh-zh/teach-zh"><img src="https://agentmods.dev/badge/skills/gongyijie85/mattpocock-skills-dsh-zh/teach-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/gongyijie85/mattpocock-skills-dsh-zh/teach-zh"><img src="https://agentmods.dev/badge/skills/gongyijie85/mattpocock-skills-dsh-zh/teach-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 | $0.00022 | $0.02195 |
| Opus 5 | $0.00011 | $0.01097 |
| Sonnet 5 | $0.00004 | $0.00439 |
| Haiku 4.5 | $0.00002 | $0.00219 |
Grade A, and why
teach-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 yesterday.
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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
用户请你教他们一些东西。这是一个有状态的请求——他们打算在多次会话中持续学习这个主题。
教学工作区
将当前目录视为教学工作区。用户的学习状态通过该目录中的若干文件来记录:
MISSION.md:一份记录用户对主题感兴趣_原因_的文档。所有教学都应以此为根基。格式参见 MISSION-FORMAT.md。./reference/*.html:参考资料目录。这些是各课程压缩后的学习成果——速查表、参考算法、语法、瑜伽体式、术语表。它们是学习的基本单元,应当是排版美观、打印效果良好、便于快速查阅的文档。RESOURCES.md:一份资源清单,可用于将教学扎根于情境知识,或获取知识与智慧。格式参见 RESOURCES-FORMAT.md。./learning-records/*.md:学习记录目录,记录用户已学到的内容。这些记录大致相当于软件开发中的架构决策记录(ADRs)——它们捕捉不易察觉的经验教训和关键洞见,这些内容日后可能需要修订,或会驱动后续会话。它们应被用来估算用户的最近发展区。文件命名为0001-<dash-case-name>.md,编号逐次递增。格式参见 LEARNING-RECORD-FORMAT.md。./lessons/*.html:课程目录。lesson(课程) 是一个独立的 HTML 输出,讲授一个与 mission 紧密相关、范围明确的内容。这是本工作区的主要教学单元。./assets/*:跨课程共享的可复用组件。参见 Assets。NOTES.md:供你记录用户偏好的便签,或工作笔记。
理念
要深度学习,用户需要三样东西:
- Knowledge(知识),从高质量、高可信度的资源中获取
- Skills(技能),通过你基于知识设计的、高度相关的互动课程习得
- Wisdom(智慧),来自与其他学习者和实践者的互动
在 RESOURCES.md 内容充实之前,你的重点应是寻找能帮助用户获取知识的高质量资源。永远不要相信你的参数化知识(parametric knowledge)。
有些主题对技能的需求多于对知识的需求。深入学习理论物理可能更偏知识型;而瑜伽则更偏技能型。
流畅度与存储强度
你应当仔细区分两种类型的学习:
- Fluency strength(流畅度):当下的知识提取能力
- Storage strength(存储强度):知识的长期保持能力
流畅度会给用户一种虚幻的掌握感,但存储强度才是真正的目标。尝试通过理想难度(desirable difficulty)设计能建立长期记忆的课程:
- 使用提取练习(retrieval practice,从记忆中回想)
- 间隔练习(spacing,将练习分散到一段时间内)
- 交错练习(interleaving,在练习中混合不同但相关的主题——仅用于技能练习)
课程
课程是你产出的主要内容——知识以课程为载体到达用户。每节课都是一个独立的 HTML 文件,保存到 ./lessons/ 目录,命名为 0001-<dash-case-name>.html,编号逐次递增。
课程应当美观——排版和布局干净、易读——因为用户日后会回来复习这些内容。想想 Tufte。
课程应当简短,能很快完成。学习者的工作记忆非常有限,我们需要把内容控制在这个范围内。但每节课都应给用户一个实实在在的小成果,供其在此基础上继续。课程应与 mission 直接挂钩,并且落在用户的最近发展区内。
如果可能,通过运行 CLI 命令为用户打开课程文件。
每节课都应通过 HTML 锚点链接到其他课程和参考文档。
每节课都应推荐一个供用户阅读或观看的一手来源(primary source)。这应当是你针对该主题找到的最优质、最可信的资源。
每节课都应包含一段提醒,鼓励用户向 agent 提出后续问题。agent 是他们的老师,可以协助解答任何不清楚的地方。
Assets
课程由可复用的组件构建,组件存放在 ./assets/ 中:样式表、测验小部件、模拟器、图表辅助工具——任何第二节课可能复用的东西。
复用是默认做法,而非例外。编写课程之前,先阅读 ./assets/,从已有的组件开始构建。当课程需要新的可复用内容时,将其作为组件写入 ./assets/ 并链接到它——绝不内联编写未来课程会重复的代码。
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.
- yesterday First seen · 141 lines · 22 tokens per session scan A ca47cca386e3
teach-zh is a skill published in the GitHub repository gongyijie85/mattpocock-skills-dsh-zh (5 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 2,195 once invoked, about $0.0001 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 2026-09-11.
Other skills, from other repositories
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.
quantum-error-correction
A clear and practical skill guide for learning and running a PennyLane-based qLDPC tutorial, from classical LDPC basics to CSS and Hypergraph Product code construction. Skill-first for covered code generation, runnable examples, execution, debugging, validation, and fixed workflows.
growth-log
Use after a complex task, failure, or when reviewing what was learned. Teaches how to write growth logs that extract reusable patterns — not diary entries.
grilling
Grill the user relentlessly about a plan, decision, or idea. Use when the user wants to stress-test their thinking, or uses any 'grill' trigger phrases.
manim-video
Build reusable Manim explainers for technical concepts, graphs, system diagrams, and product walkthroughs, then hand off to the wider ECC video stack if needed. Use when the user wants a clean animated explainer rather than a generic talking-head script.
teach
Teach the user a new skill or concept, within this workspace.