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/magic3007/dotfiles/interactive-concept-tutornpx skills add magic3007/dotfiles --skill interactive-concept-tutorgit clone --depth 1 https://github.com/magic3007/dotfilesWhat 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 | $0.00110 | $0.01065 |
| Opus 5 | $0.00055 | $0.00532 |
| Sonnet 5 | $0.00022 | $0.00213 |
| Haiku 4.5 | $0.00011 | $0.00106 |
Grade A, and why
interactive-concept-tutor 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 3d 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.
What it actually says
Interactive Concept Tutor
教学不是把答案倒给用户,而是先摸清对方站在哪里,再用可运行、可改的 notebook 带对方一步步推导。两条经验驱动这个 skill:
- 先提问探测水平 —— 有奇效。同一个概念对新手和专家要讲得完全不同,不探测就大概率讲错深度。
- Jupyter Notebook 交互 —— LaTeX 讲清"为什么",可运行代码让用户"亲眼看到"机制,而不是被动读文字。
When to use
- 用户说"讲讲 / 教我 / 帮我理解 X"
- 用户想吃透某个算法、数学推导、模型架构、系统原理
- 用户在读论文或代码,卡在某个概念上
不适用:用户只要一个事实性答案、只要修 bug、只要写代码完成任务 —— 那就直接做,别启动教学流程。
Workflow
Phase 0 — 探测水平(必做,不可跳过)
在写任何内容之前,先问 2–4 个问题。这是整个 skill 效果的关键。目标是定位用户的"最近发展区":他已经会什么,下一步能接住什么。
问题应覆盖:
- 背景锚点:相关前置概念熟不熟?(例:教线性 attention 前,先探 softmax attention / RNN 的掌握度)
- 目标深度:要到什么程度?(建立直觉?能自己推导?能动手实现?)
- 触发点:为什么现在学?(在读某篇论文?看某段代码?)
模板见 references/check-questions.md。等用户回答后再进入 Phase 1,不要自问自答。
Phase 1 — 规划教学路径
根据回答列出章节大纲,采用演进式结构:从用户已知的起点出发,一步步推到目标。每一节回答一个"为什么"—— 为什么需要它、上一步的缺陷是什么。跟用户快速确认大纲后再动手。
Phase 2 — 生成 notebook
用 jupyter-notebook skill 来生成 .ipynb —— 它有模板和 new_notebook.py 脚本,避免手写 notebook JSON 出错。本 skill 只负责教学内容的组织,不重复造生成机制。
内容组织原则:
- markdown cell 讲原理:用 LaTeX 写数学。注意在 Python 生成脚本里用 raw string(
r"""...""")避免反斜杠被转义吃掉。 - code cell 让用户亲眼看到:每引入一个关键公式或算法,配一段小 numpy/torch 实验。
- 用
assert/np.allclose验证"两种写法等价"(例:递推形式 ≡ 直接求和)。 - 打印中间变量(遗忘因子、状态范数、误差项)让抽象的机制变具体。
- cell 要小、聚焦、可独立运行,输出简短。
- 用
- 收尾节:画出演进链(A 的缺陷 → B 如何补 → C 再补),并指明下一步能学什么。
生成后,若环境允许就跑一遍 top-to-bottom 验证无误;跑不了就明确告知用户如何在本地验证。
Phase 3 — 交互跟进
交付 notebook 不是终点。主动邀请用户改参数、跑 cell、提问。用检验性提问确认对方是否真懂,而不是假装懂 —— 维度和题库见 references/check-questions.md。根据反馈补充 cell 或调整深度。
Reference map
references/check-questions.md—— Phase 0 的水平探测模板 + Phase 3 的检验性提问(直觉/推导/边界/代码对应四个维度),含线性 attention / KDA 的具体范例题库。
相关 skill
jupyter-notebook—— 生成和编辑.ipynb的机制层。本 skill 依赖它产出 notebook。
What ships with it
1 file 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.
- 3d ago First seen · 65 lines · 110 tokens per session scan A 0d00b25e0bb0
interactive-concept-tutor is a skill published in the GitHub repository magic3007/dotfiles (10 stars, last pushed 7d ago), licensed MIT. It adds 110 tokens to every session and 1,065 once invoked, about $0.0006 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
assess-quality
Foundational quality framework: the five questions (readable, easy to start, expands without bloat, consistent, intentional) every other dev skill is judged against, plus the dual-audience and workshop principles. Use when onboarding to a project, defining a quality bar, setting an assessment checklist, or arbitrating…
create-oss-skill
Create well-formed Agent Skills following the agentskills.io specification. Scaffold directories, write SKILL.md files, bundle scripts, and structure instructions for progressive disclosure. Use when creating a new skill, reviewing skill structure, optimizing a skill description, or setting up evals for skill quality.
extend-oss-skills-to-claude
Extend standard agentskills.io skills with Claude Code-specific features. Invocation control, subagent execution, dynamic context injection, string substitutions, model/effort overrides, and deployment scoping. Use when adapting a portable skill for Claude Code, adding Claude-specific frontmatter, setting up subagent…
orchestrate-agents
Orchestrate multiple agent CLIs (Claude, Codex, Antigravity) via tmux with a shared fleet store, dispatching one guardian subagent per pane. Survey-first: inspects and adopts existing tmux sessions, windows, and agent panes before creating anything new. Use when running a multi-agent session, dispatching parallel…
scaffold-project
Generates cross-language standard files (README, AGENTS.md, LICENSE, CONTRIBUTING.md, SECURITY.md, sr.yaml, .envrc, llms.txt), documentation conventions, and project structure, then dispatches to language-specific scaffolds. Use first for cross-language standard files and structure, THEN load the matching scaffold…
test-code
Testing philosophy, test types (unit, integration, golden, fuzz, property, benchmark, smoke, E2E), per-language conventions (Rust, Go, Python, TypeScript), file organization, fixtures/mocks, CI strategy, and what NOT to test. Use when writing tests, reviewing test coverage, setting up test infrastructure, or deciding…