Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add chengkj99/kj-skills/plugin install kj-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/chengkj99/kj-skills/course-generator)<a href="https://agentmods.dev/skills/chengkj99/kj-skills/course-generator"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/course-generator/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/chengkj99/kj-skills/course-generator"><img src="https://agentmods.dev/badge/skills/chengkj99/kj-skills/course-generator.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 | $0.00176 | $0.02965 |
| Opus 5 | $0.00088 | $0.01483 |
| Sonnet 5 | $0.00035 | $0.00593 |
| Haiku 4.5 | $0.00018 | $0.00297 |
Grade A, and why
course-generator 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 7d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
course-generator:单章节课程正文生成
把一份章节大纲和一堆参考材料,写成一篇学员读完就能上手、读起来像康健本人在讲的课程正文。一次只写一章,写深写透,不批量铺框架。
适用边界(先确认是不是该用我)
- ✅ 用我:已有章节标题 + 小节大纲 + 参考材料,要写这一章的完整正文。
- ❌ 不用我:还没想好写什么章节 →
ai-programming-topic-planner;手上是一段实战操作记录要整理成案例 →coding-session-to-tutorial;想一次生成整门课所有章节 → 拆成多次调用我,一章一章来。
输入(缺什么就先问,别瞎补)
按这四项收集,前两项必需,后两项强烈建议:
- 课程名称(必需)— 如「Claude Code 从入门到精通」。决定输出目录。
- 章节编号 + 标题(必需)— 如「第08讲:Claude Code 的 Agent 模式详解」。
- 小节大纲(建议)— 列表形式。没有就根据参考材料和章节标题,先产出一版小节结构给用户确认,再动笔。
- 参考材料(可选)— 用户主动提供的材料优先使用,两种形态:
- 本地文件:直接 Read 读取(
.md/.txt/ 代码文件等)。 - 网页链接:用 WebFetch 抓取正文。抓不到就告诉用户,不要编造内容。
- 本地文件:直接 Read 读取(
输入不全时的动作:只缺大纲 → 先生成小节结构请用户确认;缺参考材料 → 不要直接开写,先执行「第 0 步:主动搜料」,用搜到的材料支撑内容质量。
工作流程
第 0 步:主动搜料(必须执行,不能跳)
无论用户是否提供了参考材料,都要执行此步——用户给的材料是起点,不是终点。搜料的目标:让这章的内容有充分的事实依据、可复现的示例、准确的技术细节。
详细搜索策略见 references/material-hunt.md,执行摘要如下:
1. 搜本地仓库(优先,速度快)
从章节标题提取 2–4 个核心关键词(英文 + 中文),在以下路径搜索:
# 在当前课程仓库搜
grep -r "<关键词>" . --include="*.md" -l
# 在 kj-skills 仓库搜(技能文档、已有教程)
grep -r "<关键词>" /Users/chengkangjian/work/kj-skills --include="*.md" -l
# 在 kj-llm-wiki 搜(知识沉淀)
grep -r "<关键词>" "/Users/chengkangjian/Library/Mobile Documents/iCloud~md~obsidian/Documents/kj-llm-wiki" --include="*.md" -l 2>/dev/null
命中的文件用 Read 读取相关段落,提取可用知识点。
2. 搜网络(补充官方一手资料和最新内容)
用 WebSearch 执行 2–4 轮搜索,查询策略见 material-hunt.md。搜到高质量 URL 后用 WebFetch 抓取正文。
3. 汇总材料清单
搜完后,在脑中(或草稿)列出:
- 已读材料 N 篇、覆盖哪些知识点
- 哪些知识点仍然空白(技术细节不足 / 无可复现示例)
如果空白太多(超过章节主干的 30%),告知用户并请求补充,而不是硬写靠猜。
第 1 步:吃透材料,定结构
- 读全部参考材料(本地 Read + 网页 WebFetch),提取这一章真正要讲清楚的知识点清单。
- 判断章节类型(决定用哪套结构骨架,详见 references/chapter-blueprint.md):
- 概念讲解型(讲清一个原理 / 模式,如「Agent 模式详解」)
- 工具操作型(教会一个配置 / 功能,如「MCP 配置」)
- 实战项目型(带做一个完整产物,如「实战一:核心功能实现」)
- 方法论型(讲思维 / 工作流,如「写出高质量 Prompt」)
- 把知识点对应到小节大纲。大纲缺失或不合理时,按 blueprint 的最佳实践重排,改动要告诉用户原因。
第 2 步:写正文
打开 references/chapter-blueprint.md 对应章节类型的骨架,逐节落笔。同时严格遵守 references/style-and-gate.md 的写作风格。
What ships with it
5 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.
- 7d ago Changed · +1 lines 99be07d1acf7
- 11d ago First seen · 140 lines · 176 tokens per session scan A f586efeb8cf4
course-generator is a skill published in the GitHub repository chengkj99/kj-skills (14 stars, last pushed 10d ago), licensed MIT. It adds 176 tokens to every session and 2,965 once invoked, about $0.0009 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 2026-08-30.
Other skills, from other repositories
hr-onboarding
A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".
book-mirror
Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…
miniapp
Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.
eli5
Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.
deck-course-module
A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.
master-yinguang
A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.