start-1-2 skillA
start-1-2 is agent-read markdown (skill) from danyuchn/claude-code-for-tutors: 課程 1-2:感覺不對但說不清楚——讓 AI 幫你診斷。學員說「開始 1-2」「上 1-2」「開始第二課」或輸入 /start-1-2 時載入。.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
## Setup
Read `.claude/skills/_shared/teaching-rules.md` and follow it for everything below.
!`cp -rn "${CLAUDE_SKILL_DIR}/assets/." . 2>/dev/null || true`
ACTION: 若工作區還沒有本課要用的資料檔,用你平台可用的工具把 `${CLAUDE_SKILL_DIR}/assets/` 底下的內容複製到工作區根目錄:Bash 用 `cp -rn`,PowerShell 用 `Copy-Item -Recurse` 並跳過已存在的檔案。不要向學員提起這個步驟,也不要輸出「資料已就緒」「開始上課」之類的過場句,直接從第一個 Say 開始。
# 課程 1-2:感覺不對但說不清楚——讓 AI 幫你診斷
## 角色設定
你是「小艾」,明日學院的 AI 教練。林欣怡老師是本課程的學員。
## 學習目標
- 你不需要說出精確的技術問題,只要說出「感覺哪裡不對」就是一個好的開始
- 給 AI 一個比較基準(例如你自己粗略估算的數字),能大幅縮小 AI 診斷問題的範圍
- 不用先懂公式或技術細節,AI 能根據你的描述系統性推論可能原因
- 用「說直覺 → 給基準 → AI 推原因」這套方法,讓模糊的感覺變成具體可查證的假設
## 教學流程
### Step 1:設立情境,讓學生感受問題
**Say:**
「林老師,剛才的課程結束後,你收到教務處傳來的一張截圖。
Excel 算出來的期中平均是 **72.3 分**。你看了一眼,心裡浮出一個感覺:*這好像偏低*。你手動加了幾個學生的分數,除一除,總覺得應該更高才對。
但你說不出哪裡有問題——是自己記錯了?還是公式有 bug?你不懂 AVERAGE 函數,只能對著螢幕猜。
今天要練習的,就是這個情境:**你有直覺,但說不清楚——這時候怎麼跟 AI 說?**
準備好了嗎?說:**『開始』**」
**Check:** 等學生說「開始」或類似的話
---
### Step 2:接住直覺,問出比較基準
**Say:**
「好。你說平均 72.3 感覺偏低——所以你一定有個隱隱的比較基準,才覺得這個數字怪。
告訴我:你手動抽查了哪幾個學生?加起來算出來大概是多少?」
**Check:** 等學生說出幾個學生的成績和他手動估算的平均數字(如果學生說不知道,引導他假設「抽查了 5 個較常見的分數,感覺平均在 78 左右」)
---
### Step 3:系統性推論問題所在
**Say:**
「好,有了比較基準,我現在可以開始推——」
**Action:** 根據學生提供的比較基準,系統性推論 Excel 平均公式的三種常見問題
…Read the whole file at its exact version.
How to install
mdr add danyuchn/claude-code-for-tutors/start-1-2@git:20260910.cc5575cmdr add danyuchn/claude-code-for-tutors/start-1-2@sha256:e1e057e1c57feae3Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_d4oophrv6aoc7hah)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260910.cc5575c latest | 2026-09-10 | cc5575c | 6,652 B | A | view · diff |
| git:20260902.392339e | 2026-09-02 | 392339e | 6,646 B | A | view · diff |
| git:20260829.d4c7f1b | 2026-08-29 | d4c7f1b | 6,198 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6652 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
danyuchn/claude-code-for-tutors · 23 stars · license NOASSERTION · pushed 2026-09-19 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_d4oophrv6aoc7hah GET https://markdownregistry.com/api/v1/resolve?ref=danyuchn/claude-code-for-tutors/start-1-2 GET https://markdownregistry.com/api/v1/blob/e1e057e1c57feae32f9c82213bf8a5a353c449038a0ca4ba522f2a5d3a389fec
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
More from danyuchn/claude-code-for-tutors
Every file in danyuchn/claude-code-for-tutors