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 | $0.00044 | $0.00842 |
| Sonnet 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 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 — 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.
- 12d 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 (10 stars, last pushed 8d ago), licensed MIT. It adds 87 tokens to every session and 1,683 once invoked, about $0.0004 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
explain-this
Explain whatever the user is pointing at right now in plain language: a pending question, a piece of code, an error, a command output, or an artifact like a plan or findings report. Use when the user asks to "explain this", "what am I being asked", "what's happening right now", "help me understand this", "what does…
understand-change
Teach the user to deeply understand a change through interactive tutoring: restating understanding, drilling into why/what/how, and quizzing until mastery. The active counterpart to a one-shot explanation. Use when the user asks to "understand this change", "teach me this change", "help me understand what changed"…
master
Turn reference docs into active mastery through retrieval practice, case binding, and scenario simulation. Combines Skycak (learning science) and Chin (expertise acceleration) frameworks. Use when you want to deeply learn material, not just read it.
upskilling-coach
Expert coach for learning, mastering, and upskilling in any domain. Use when the user wants to learn, master, improve, upskill, get better at, or get coached on any topic. Helps build consistent practice habits, identify prerequisites, design efficient learning loops, avoid common pitfalls, maintain discipline, and…
learning
A learning workflow for turning outside material, articles, repositories, and code-review lessons into knowledge that can be used in a workspace. It also supports processing a queue of learning tasks and setting up a daily scanner.
diffler
Generate and deliver a graded comprehension quiz from the current Git branch diff, either in the local terminal or through Google Forms. Use when a user asks to prove, test, or verify understanding of branch changes, a feature branch, or a pull request.