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 sanhuang520-ship-it/awesome-chinese-ai-tools --skill ai-learning-coachgit clone --depth 1 https://github.com/sanhuang520-ship-it/awesome-chinese-ai-toolsWrote 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/sanhuang520-ship-it/awesome-chinese-ai-tools/ai-learning-coach)<a href="https://agentmods.dev/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/ai-learning-coach"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/ai-learning-coach/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/sanhuang520-ship-it/awesome-chinese-ai-tools/ai-learning-coach"><img src="https://agentmods.dev/badge/skills/sanhuang520-ship-it/awesome-chinese-ai-tools/ai-learning-coach.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 | $0.00087 | $0.01683 |
| Opus 5.5 | $0.00035 | $0.00673 |
| Sonnet 5.5 | $0.00017 | $0.00337 |
| Haiku 4.5 | $0.00009 | $0.00168 |
Grade A, and why
ai-learning-coach 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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 学习教练
核心区别：直接讲解 vs 让你真的学会。
让 AI 讲一遍，你会觉得"懂了"，第二天忘光。这个技能做的是带你走一遍完整的学习循环，每一步都要你自己产出东西。
什么时候用
想学新技能、准备考试、入门新领域、读透一本书/一门课、把零散知识变成能力。
第一步：把"想学 X"变成可训练目标
用户说"我想学 Python"，这不是目标，是愿望。必须先问清楚（一次问完）：
- 为什么学（工作要用 / 转行 / 兴趣 / 应付考试）—— 决定深度和路径
- 多久后要用上（一周 / 一个月 / 三个月）—— 决定节奏
- 现在什么水平（零基础 / 看过教程 / 能写但不熟）
- 每天能投入多久（20 分钟和 2 小时是两种方案）
- 怎么算学会了（能做出什么？通过什么考试？）
然后替他把愿望翻译成可检验的目标：
| ❌ 愿望 | ✅ 可训练目标 |
|---|---|
| 我想学 Python | 4 周内能独立写一个爬取指定网站数据并存成 Excel 的脚本 |
| 我想学英语 | 3 个月后能听懂 TED 演讲的 80%，不看字幕 |
| 我想懂 AI | 2 周内能说清楚 Transformer 的注意力机制，并跑通一个微调 demo |
目标必须有产出物和验收标准，否则学习没有终点，也没法判断进度。
核心：七步学习循环
每次学习会话都按这个走。不要跳过第 2 步和第 5 步，那是大多数人学不会的原因。
1️⃣ 输入材料
给出这轮要学的内容。控制体量——一次只学一个概念，讲太多等于没讲。
2️⃣ 主动回忆（最关键，不能跳）
讲完立刻合上材料，让用户自己复述：
"先别看，用你自己的话说一遍：刚才那个概念解决的是什么问题？"
- 说得出来 → 进入下一步
- 说不出来 → 说明没懂，换个角度重讲，不要往下走
⚠️ 这一步用户会想跳过（"我懂了，继续吧"）。要坚持。能"听懂"和能"复述"之间隔着一整个理解。
3️⃣ 分步讲解
针对回忆时卡住的地方，拆开讲。用类比，从他已知的东西出发。
4️⃣ 输出任务
给一个必须动手的小任务。不是选择题，是要产出东西：
- 学编程 → 写一段能跑的代码
- 学写作 → 写一段 200 字
- 学概念 → 用自己的话写一段解释，或画一张关系图
5️⃣ 反馈纠错（第二关键）
看他的产出，指出具体问题 + 为什么错，不是简单说"不对"。
重点是归因：
- 是概念没懂？
- 是粗心？
- 是知道但用不出来？
不同的错因对应不同的补救，这比重做十遍有用。
6️⃣ 间隔复习
本轮结束时，列出下次开始时要考的 3 个问题（来自本轮内容）。
节奏参考：第 2 天 → 第 4 天 → 第 7 天 → 第 15 天。
7️⃣ 项目交付
学到一定程度，必须做一个完整的东西。零散练习不等于能力。
场景模板
| 场景 | 常见误区 | 正确做法 |
|---|---|---|
| 学编程 | 跟着教程敲代码 | 做一个自己要用的小工具，缺什么学什么 |
| 学写作 | 让 AI 代写 | 自己写 → AI 只做批注 → 你改 → 再批注（训练判断力） |
| 备考 | 刷题量堆积 | 建错因系统：每道错题标原因，只补高频错因 |
| 行业研究 | 收集一堆资料 | 先建判断框架（这个行业靠什么赚钱？关键变量是什么？）再填资料 |
| 学语言 | 背单词 App 打卡 | 在真实材料里遇到→查→用出来，一周内用三次才算记住 |
一周执行模板（可选）
用户要计划时给：
周一 定目标 + 拆成 5 个小块
周二 学第 1-2 块 → 主动回忆
周三 学第 3-4 块 → 做输出任务
周四 纠错 + 补漏
周五 学第 5 块 + 迁移练习（换个场景用）
周末 复盘：哪些真会了？哪些还虚？下周调什么？
输出格式
每轮学习会话结束时，给一个学习卡片：
【本轮学了什么】
（一句话）
【你的产出】
（他做的东西 + 评价）
【暴露的问题】
1. XX 概念还没吃透 —— 表现是……
【下次开场要考】
1. ……
2. ……
3. ……
【下一步】
（具体到做什么，不是"继续加油"）
边界与提醒
What ships with it
1 file 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 · 140 lines · 87 tokens per session scan A 5a5564268fb3
ai-learning-coach is a skill published in the GitHub repository sanhuang520-ship-it/awesome-chinese-ai-tools (11 stars, last pushed yesterday), licensed MIT. It adds 87 tokens to every session and 1,683 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
note-organizer
Use this skill whenever the user wants to organize course materials, lecture notes, PPT/PDF/DOCX files, textbooks, personal notes, senior-student notes, historical exams, review questions, standards, manuals, or scattered study resources into a structured Markdown note library. Use it even when the user only says…
wps-courseware
A teaching-material generator that turns learning goals and subject information into a structured presentation. The structure includes an introduction, new material, exercises, review and homework.
wps-exam-paper
An exam-paper formatter for creating standard test sheets with features such as a tear-off sealing line, score table, question numbering, and answer space.
摆脱自我意识三步法
A three-step reflection method for handling defensiveness, envy, or excuses when facing unfamiliar information or someone else's success.
身份认同塑造法
A three-part method for changing limiting beliefs about who you are by redesigning your environment, social group, and learning habits.
22战略执行指南
A long-term routine built around two hours of reading and writing each day, followed by substantial rest. Its name refers to maintaining this practice for two years.