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 unbias38/my-claude-skills --skill course-handoutgit clone --depth 1 https://github.com/unbias38/my-claude-skillsWrote 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/unbias38/my-claude-skills/course-handout)<a href="https://agentmods.dev/skills/unbias38/my-claude-skills/course-handout"><img src="https://agentmods.dev/badge/skills/unbias38/my-claude-skills/course-handout/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/unbias38/my-claude-skills/course-handout"><img src="https://agentmods.dev/badge/skills/unbias38/my-claude-skills/course-handout.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 | $0.00217 | $0.02390 |
| Opus 5 | $0.00109 | $0.01195 |
| Sonnet 5 | $0.00043 | $0.00478 |
| Haiku 4.5 | $0.00022 | $0.00239 |
Grade A, and why
course-handout 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 — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
互動課程講義網頁
把一門「跟著做」的實作課程，做成講師可投影講解、學員可跟著操作的單檔 HTML 講義， 發布為 Artifact。機制固定、內容抽換——不要重新發明機制。
範本用法：assets/template.html 是完整成功案例（《君子動口不動手・排座位篇》）。
內容收集完、開始產出時，先把它整份複製到 scratchpad，再逐區塊替換內容（標題、單元、
提示詞、驗收、證書詞庫、MD_TEXT），機制程式碼原樣保留。不要憑記憶重寫整頁——重寫
容易遺漏備援與修過的 bug；也不用為了了解機制先通讀整份範本，下方規格表就是機制摘要。
起點：三種情境都能做
- 已有完成的專案＋提示詞（最佳）：直接進入內容收集，講義忠實還原實際建構過程。
- 只有課程主題或構想：先陪使用者把成品做出來（在對話中實際建構一次），過程中自然產生提示詞、預期錯誤、踩坑點——這些是驗收清單的素材；成品做完再產講義，並產出可分享的成果參考連結。不要憑空杜撰提示詞和驗收項：沒實測過的驗收清單會在課堂上翻車。
- 只有專案程式碼、沒有提示詞（逆向還原）：讀懂程式 → 列出功能清單 → 按教學節奏分部（骨架 → 資料 → 參數化 → 輸出 → 保存 → 交付）→ 每部反推一句提示詞。反推時用學員的「需求語言」寫（畫面上看得到的行為、使用情境），不要寫成從程式碼翻譯出來的技術規格。反推的提示詞務必試跑驗證：開新對話實測一輪，確認能長出功能相近的成品、記下實際跳出的錯誤訊息當驗收素材；跳過驗證就交付，講義會在課堂上翻車。
- 非 AI 實作課（Excel、Canva、任何分部驟教學）：泡泡裡放的不一定是提示詞，可以是指令、操作步驟或設定值；「複製按鈕＋驗收清單＋證書」的機制完全通用。
第一步：向使用者收集內容
缺什麼問什麼，能推斷就不要問：
- 課名（短、有記憶點）＋副標／篇名（如「排座位篇」）＋ 20 字內課程介紹（可幫忙擬幾個讓使用者挑）
- 成果參考連結（可選）：完成品的體驗連結（如 Google 試算表 /copy 連結）
- 單元拆解：課程分幾部（建議 4–8 部），每部包含——
- 目標（一句話）
- 給 AI／給工具的操作內容（提示詞、指令或步驟）
- 操作步驟（學員實際要做的事）
- 驗收清單（2–5 項可打勾、可實測的項目）
- 技巧點評（一句話，該部的方法論）
- 開始之前：準備清單＋工作區介紹＋反覆出現的循環動作（做成術語浮動說明）
- 結尾：帶走的原則（3 條左右）＋回家挑戰題
固定機制（template.html 已全部實作，直接沿用）
| 機制 | 規格要點 |
|---|---|
| 單元收合 | .unit.closed 預設全收起；點 h2 展開（▸/▾）；單元底部「▲ 收起本單元」按鈕，收起後 scrollIntoView 回標題；h2 有 tabindex=0 支援鍵盤 |
| 提示詞複製 | 泡泡右上角「複製」鈕；三層備援：navigator.clipboard → execCommand('copy') → 自動選取文字提示按 Ctrl+C（Artifact 沙箱常擋新 API，此備援必要） |
| 驗收清單 | 真核取方塊，勾選後文字轉灰；驗收項必須「可實測」，含刻意設計的預期錯誤（「跳出 Error 是正常的！」）與暖身幽默項（「會呼吸、會眨眨眼」） |
| 術語浮動說明 | 反覆出現的循環動作包 .cyc span，hover/focus 浮出深色步驟框；只包 HTML 內文，不要動到 MD_TEXT 字串（批次取代時特別小心） |
| 畫筆標註 | 全頁 canvas，文件座標（筆跡跟內容捲動）；五色（紅橘藍綠黑）＋橡皮擦（destination-out）＋全部清除；筆跡存 strokes 陣列，ResizeObserver 監聽頁高變化重繪；收起畫筆後筆跡保留、頁面恢復互動；ESC 清空並離開 |
| 結業證書 | 姓名必填（空白擋下、紅框提示）→ 檢查所有 .check 勾選狀態 → 未完成列「哪部差幾項」；全過跳金雙邊框證書：隨機頭銜（形容詞 25 × 稱號 25，依課程主題重寫兩個詞庫）、可重抽、民國紀年落款。文案順序：茲證明→姓名→已完成→獲頒榮譽頭銜→特頒此狀 |
| Markdown 下載 | 全文打包成 MD_TEXT 字串（驗收用 - [ ]），彈窗＋複製全文；不宣告 downloads capability（與公開分享互斥），但保留 claude.use('downloads') 偵測 |
| ESC 優先序 | 有彈窗開著先關彈窗，其次才清畫筆筆跡 |
| 成果搶先看 | 頁首橫幅＋按鈕連到成品連結（target=_blank），文案定位為「體驗成品」不是「比對程式」 |
What ships with it
2 files 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 · 71 lines · 217 tokens per session scan A bd6c0b310ee5
course-handout is a skill published in the GitHub repository unbias38/my-claude-skills (2 stars, last pushed 17d ago), licensed MIT. It adds 217 tokens to every session and 2,390 once invoked, about $0.0011 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
stuck
Diagnoses a broken course setup by reading the folder, so the student never has to describe the problem in English. Takes no argument. Reports which class they are on and which files are filled, then names one blocker and one fix: Claude Code opened at the wrong level, .claude/skills/ missing, skills not loading…
shipkit-communications
Use when user wants to visualize or present shipkit content as HTML. Triggers: 'create presentation', 'visualize this', 'HTML report'.
claude-students
Transforma una carpeta cruda de material de un parcial universitario (PDFs, DOC/DOCX, PPT, audios .ogg de WhatsApp, capturas) en un material de estudio polished y completo — HTML SOTA autocontenido + paquete de artefactos de NotebookLM (podcast en español, infografía, guía de estudio, briefing doc, mind map, quiz…
interview-kit-builder
Build a complete, structured interview kit for a role — competency-based questions, what good/weak answers look like, a scoring rubric, and a stage plan. Use when the user is preparing to interview candidates, asks for interview questions, needs an interview scorecard, or wants to set up a hiring process for a role.
skill-creation-walkthrough
Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not…
read-book
When you want to read and extract structured notes from a book — PDF, EPUB, MOBI, markdown, .txt, pasted text, or URL to a public-domain work. Reads in chunks (by chapter when a TOC exists, by 50-page blocks otherwise), extracts per-chapter TL;DR + key concepts + quotes + action items + frameworks, and offers to…