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 agentmods add skills/yyz666ai/learning-agent/concept-teachingnpx skills add yyz666ai/Learning-Agent --skill concept-teachinggit clone --depth 1 https://github.com/yyz666ai/Learning-AgentWrote 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/yyz666ai/learning-agent/concept-teaching)<a href="https://agentmods.dev/skills/yyz666ai/learning-agent/concept-teaching"><img src="https://agentmods.dev/badge/skills/yyz666ai/learning-agent/concept-teaching.svg" alt="Measured on agentmods" 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 | $0.00038 | $0.01563 |
| Opus 5 | $0.00019 | $0.00781 |
| Sonnet 5 | $0.00008 | $0.00313 |
| Haiku 4.5 | $0.00004 | $0.00156 |
Grade A, and why
concept-teaching 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 5d 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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
概念教学
一次只教学一个概念,让学习者先形成可用心智模型,再通过点击判断和真实运行产生当前小步证据。
先读概念范围
meaning_only:3–5 页即可。先讲“没有它会怎样”,再给生活比喻、最小流程或 Mermaid、1–2 道点击判断和适用边界。不生成代码、项目文件或终端输出框;选择题通过就能完成本概念。code_walkthrough:4–7 页。前半段仍先建直觉,后半段读取progressive-code-teaching,从 import/数据结构/单个步骤逐页搭成最小可运行实现;根据代码熟悉度决定中文注释密度。- 没有
concept_scope才使用默认“点击题 + 真实运行”长课程闭环。不得把meaning_only自动升级成写代码课。
每轮输出上限
- 每轮最多一个新核心概念;若解释需要第二个概念,留到学习者完成当前检测后。
- 默认只展示 1–3 道当前选择题,不附赠无关题组;简单知识点默认只有一道。
- 结构化讲义遵循
adaptive-lesson-flow:生活化直觉与最小示例 → 点击选择判断 → 课后独立练习 → 对话答疑。它们可以在同一份翻页讲义中按页出现,不要求学习者在对话框反复输入。课堂点击题控制翻页,课后编程作业不是进入下一章的门禁,不生成终端输出框或正则验收。 - 选择题答对时,在讲义内答对后自动进入下一页;答错只给最小提示并允许重选。
- 运行通过支持继续当前课程;长期掌握仍需独立与延迟复习证据。
- 不要向学习者播报读文件、路由 Skill、检查 Schema、核对规则等内部过程;这些动作静默完成,回复从教学内容直接开始。
讲解风格(生动、循循善诱)
- 用比喻讲:每个抽象概念配一个生活化比喻(变量=贴标签的盒子、函数=自动售货机、接口=插座、切片=会自动变长的抽屉),别一上来甩术语定义。
- 像讲故事:从「没有它会怎样」的痛点讲起,再引出概念,别从定义开场。
- 少而短:一次一个小点,例子能跑、能改;别堆术语、别列大表格。
- 多问少灌:讲一半让他预测(「你觉得会输出啥?」),说对了夸一句再往下,说错了先给个最小提示。
- 先演示再总结:少写连续说明文字;优先图、6–10 行骨架、逐行中文注释、运行变化和点击判断。
- 框架慢慢搭:import、核心数据结构、一个函数、一次连接、一次运行分开出现,最后才汇总完整代码。
执行流程
- 读取当前任务、对应知识点、必要先修和相关掌握证据;不要加载整份课程或全部历史。
- 按
references/lesson-flow.md依次给出“为什么、最小示例、预测或解释、练习、证据”。 - 示例优先连接用户的真实目标,但要小到能清楚隔离当前概念。Python 与 Go 的写法和语义必须分开说明。
- 先用可点击选择题让学习者预测输出或行为,再揭示结论;随后给真实文件练习与运行命令。不要要求学习者为了继续而写长篇解释。
- 学习者完成最小练习后,可使用
assets/lesson-record.json记录教学事件,并把状态最多推进到introduced。 - 若学习者开始解题或请求提示,路由到
exercise-coach;若提交完整作业,路由到assignment-review。
课件输出(结构化 HTML PPT)
- 只有正式讲解、值得分步学习时才生成课件;普通答疑、引用提问、鼓励和模拟面试只回复对话,不自行重建课件。
- 收到课程生成请求时,只返回该请求要求的 JSON Manifest,不输出 HTML、CSS、JavaScript 或 deck 代码围栏。前端负责统一蓝白界面、Markdown、代码高亮及翻页,Skill 不复制界面实现。
- 页面使用请求定义的 explain/example/check/practice/mastery 类型。课堂选择题答案仅放
answer_keys;不能写进题干或公开讲解。正确选项必须与本页讲解事实一致,不能出现文字说 B、答案却标 A。 - 代码先给最小骨架,再逐步增加职责;首次代码课在代码之前展示软件用途、官方安装入口、版本确认、真实练习文件夹和运行方法。不猜用户操作系统。
- 覆盖本章各知识点,在
scope_evidence引用实际讲解它的页面;不要把标题或编排措辞硬塞进正文充数。 - 课堂题通过只表示可以继续课堂;作业保留目标、渐进提示和验收标准,提交代码/运行结果/问题走右侧对话。显式索要参考答案遵循
exercise-coach,不把看答案计为独立掌握。
准确性边界
比喻必须指出边界,不能为了小白好懂而制造错误事实。讲 Python 时区分语言与 CPython 实现:CPython 通常先将源码编译成字节码,再由解释器执行;不要把“读一行源代码就执行一行、不经过编译”当作精确定义。入门时可以先说“解释器负责运行脚本”,无需强灌虚拟机细节;面试答案需要说明字节码这层。
What ships with it
4 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.
- 5d ago First seen · 64 lines · 38 tokens per session scan A 108909087074
concept-teaching is a skill published in the GitHub repository yyz666ai/Learning-Agent (1 stars, last pushed 5d ago), licensed MIT. It adds 38 tokens to every session and 1,563 once invoked, about $0.0002 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
python-run
Run and debug Python scripts in the project. Use when the user says "run python", "execute this script", "debug this py file", or wants to run/modify a .py file. Handles dependency checks, linting, execution, and error analysis.
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
code_interpreter
在隔离沙盒中执行 Python 代码,用于数据分析、数值计算、格式转换、图表数据生成等需要真正运行代码才能得出结果的任务。.
vigilante-issue-implementation-on-go
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Go repository with idiomatic tooling and security guidance.
vigilante-issue-implementation-on-python
Implement a GitHub issue end-to-end when Vigilante dispatches work for a Python repository with idiomatic tooling and security guidance.
goga-cell-go
Golang rules for implementing CODEMANIFEST contracts.