AI Teacher & Tutor Agent Skill

Transforms provided documents and materials into personalized, step-by-step learning curricula with diagnostics and teaching style mimicry.

Context cost
71.6k tokensestimated from the bundle, loaded when it triggers
Bundle
48 files · 361.8 kB7 scripts among them — read before you run
Licence
MITthe author’s own terms
Last change
—v2.7.0
Servers it uses
Noneruns standalone

What it does

AI老师:给定文档/书籍/课程资料后,像老师一样教会用户理解内容。 先诊断学习能力(强/中/弱),再用通俗易懂的方式一步步教学。 支持模仿名师教学风格——用户提供课程字幕或视频链接,AI 提取并复刻其说话方式。 当用户说"教我"、"帮我学"、"帮我理解"、"模仿XX老师的教学风格"或上传资料要求学习时触发。 不要在用户只是问一个简单问题时触发——只在涉及系统性学习/教学时激活。

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

documentation

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md11.8 kB · preview
--- name: teacher argument-hint: "[topic or paste materials]" version: 2.7.0 user-invocable: true allowed-tools: Read, Write, Edit, Bash triggers: - "教我" - "帮我学" - "我想学" - "帮我理解" - "读懂这份" - "学会这个" - "模仿" - "像XX一样教我" - "用XX的风格" - "teach me" - "help me learn" - "help me understand" - "mimic" - "style of" ---
30# 语言规则
31自动检测用户第一条消息的语言。整个会话过程中始终使用该语言。如果用户中途切换语言,跟随用户切换。
32
33---
34
35# 你是谁
36你是一位耐心、通俗、因材施教的 AI 老师。
37
38你的核心使命只有一个:**确保用户真正理解给定的资料内容**,而不是死记硬背。
39
40你的教学原则:
41- 通俗易懂:用生活中的类比和例子解释抽象概念,避免堆砌术语
42- 循序渐进:从简单到复杂,每一步都确保用户跟上
43- 因材施教:根据用户的学习能力(强/中/弱)调整教学方式
44- 确认理解:每个知识点讲完后都检查用户是否真的懂了
45- 不跳步骤:宁可慢一点,也不要假设用户"应该知道"
46
47---
48
This is a preview of SKILL.md. Download or install the skill to get the whole thing.
In the file
SKILL.md744 words
Files48
LicenceMIT
Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈140
always loaded
The name and description, so the model knows the skill exists and when to reach for it.
71,485
on trigger
The instruction body and 47 supporting files, read only when the skill fires.
35.8%
of a 200k window
Ten skills this size would not fit in the window together.
050k100k150k200k context window

71.6k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

It asks the agent to write files, using whatever file access your client already has. Whether it reaches the network is not declared.

What it asks for
Writes filesyes
Network accessnot declared

Read from the allowed-tools line of this skill’s own SKILL.md. It also asks for Bash, which could do either, so what is not named there is not ruled out. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

What is in the bundle

48 files, 361.8 kB on disk. Mostly text — the instructions the model reads — with 7 scripts in it that your client would run only if the instructions tell it to. 1 file of its source is not in the download — listed after these, with why.

  • SKILL.md11.8 kB
  • LICENSE1.1 kB
  • README.md18.5 kB
  • README_EN.md16.5 kB
  • adapters/trae-teacher.md0.5 kB
  • config/skill-config.json3.1 kB
  • prompts/correction_handler.md5.3 kB
  • prompts/intake.md3.4 kB
  • prompts/merger.md4.1 kB
  • prompts/style-extractor.md6.2 kB
  • prompts/style-profile-template.md4.5 kB
  • prompts/teaching_analyzer.md6.5 kB
  • prompts/teaching_builder.md11.1 kB
  • ref/cross-disciplinary-thinking.md12.7 kB
  • ref/deliberate-practice-research.md6.0 kB
  • ref/extraction-framework.md7.0 kB
  • ref/forgetting-curve-research.md5.8 kB
  • ref/improvement-roadmap.md6.6 kB
  • ref/learner-diagnosis.md7.4 kB
  • ref/management-commands.md2.7 kB
  • ref/nuwa-absorption.md4.8 kB
  • ref/question-templates.md4.3 kB
  • ref/reverse-distillation-report.md12.6 kB
  • ref/skill-to-curriculum-guide.md8.6 kB
  • ref/teaching-sop.md21.3 kB
  • ref/teaching-strategies.md9.7 kB
  • ref/teaching-techniques.md8.4 kB
  • ref/unified-extraction-research.md7.3 kB
  • ref/verification-framework.md6.6 kB
  • scripts/evaluate_answer.py5.7 kB
  • scripts/extract_subtitle.py8.5 kB
  • scripts/generate_quiz.py6.9 kB
  • scripts/learning_state.py7.2 kB
  • scripts/reverse_distill.py13.8 kB
  • scripts/skill_writer.py24.9 kB
  • scripts/track_progress.py8.3 kB
  • subjects/_template-SKILL.md1.8 kB
  • subjects/ai-teacher-SKILL.md7.1 kB
  • subjects/biology-teacher-SKILL.md4.5 kB
  • subjects/chemistry-teacher-SKILL.md4.4 kB
  • subjects/chinese-teacher-SKILL.md4.0 kB
  • subjects/english-teacher-SKILL.md4.5 kB
  • subjects/feynman-teacher-SKILL.md19.1 kB
  • subjects/history-teacher-SKILL.md4.7 kB
  • subjects/math-teacher-SKILL.md3.3 kB
  • subjects/physics-teacher-SKILL.md4.5 kB
  • subjects/programming-teacher-SKILL.md3.6 kB
  • .github/workflows/pylint.yml0.6 kB

Not in the download

Not carried is a type a skill download does not hold. Take it from its source.

  • .gitignorenot carried
What is not in it

A skill installs nothing and depends on nothing: it is a folder your client reads. This one carries 7 scripts beside the text, so the download is 48 files — not the whole of its source: 1 file is left out. It is listed under the files, with why. The MIT licence covers the templates and examples as well as the instructions.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# AI Teacher & Tutor · 71.6k tokens when loaded · macOS, Linux mkdir -p .claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/ai-teacher-tutor/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/ai-teacher-tutor" ] && { [ ! -e .claude/skills/ai-teacher-tutor ] || { mv .claude/skills/ai-teacher-tutor "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/ai-teacher-tutor" .claude/skills/ && echo "Installed .claude/skills/ai-teacher-tutor"
On Windows, or any OS with Node 20+
npx mcprush@latest skill add chentao326/ai-teacher-tutor

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/ai-teacher-tutor/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/ai-teacher-tutor/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/ai-teacher-tutor" ] && { [ ! -e ~/.claude/skills/ai-teacher-tutor ] || { mv ~/.claude/skills/ai-teacher-tutor "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/ai-teacher-tutor" ~/.claude/skills/ && echo "Installed ~/.claude/skills/ai-teacher-tutor" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/ai-teacher-tutor/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where. It appears as teacher in Gemini CLI, Codex, Copilot and Grok (its own name); Claude Code lists it by the folder name, ai-teacher-tutor. Not in this download: 1 file of its source (which one, and why). Take it from its source.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/
Claude DesktopCustomize › Skills
ChatGPTSkills › Create › Upload
Cursor.cursor/skills/
VS Code.github/skills/
Codex CLI.agents/skills/
Gemini CLI.gemini/skills/
Grok Build.grok/skills/
Microsoft CopilotSkills › Upload a skill
PerplexityComputer › Skills › Upload a skill
DeepSeek Harness.dsh/skills/
Zed.agents/skills/
Devin Desktop.devin/skills/
Windsurf (legacy).windsurf/skills/
OpenAI Agents SDKInstructions or sandbox Skills
HTTP / APIa request parameter
This release
Version2.7.0
Publishedno release date on file
PriceFree
Referencechentao326/ai-teacher-tutor

Versions

v2.7.0 is what is on the shelf; no release here carries a date. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

v2.7.0
  • No earlier releases have been published to the marketplace.
Pinning

The install command always fetches the release that is current the day you run it — v2.7.0 today — and cannot ask for an earlier one. The copy on your disk does not change until you run it again.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Sign in
Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

CH
chentao326

Publishes on mcprush.

0 servers listed1 skill listednot claimed
Profile
Publisher
Servers0
Claim this skill