build-personal-skill
Evidence-based creation of a reusable personal course-making Skill from the user's own classroom and chat history. Use when the user asks to summarize,…
Masterclass lecturing — one continuous explanation carried by slides, with dense pages, long narration that builds an argument across several real cases, and checkpoints that are rare and deliberate. Use when the ask is a lecture, a masterclass, a systematic walkthrough of a
$ npx -y skills add thu-maic/openmaic --skill lecture-style --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/lecture-styleContext preview
The summary Claude sees to decide when to auto-load this skill.
Masterclass lecturing — one continuous explanation carried by slides, with dense pages, long narration that builds an argument across several real cases, and checkpoints that are rare and deliberate. Use when the ask is a lecture, a masterclass, a systematic walkthrough of a
name: lecture-style title: "大师讲授" description: Masterclass lecturing — one continuous explanation carried by slides, with dense pages, long narration that builds an argument across several real cases, and checkpoints that are rare and deliberate. Use when the ask is a lecture, a masterclass, a systematic walkthrough of a subject, 「大师课」「系统讲解」「讲透」, or any topic whose payoff is understanding rather than practice; also use when the user names this style. Not for hands-on training (that is `workshop-style`) and not for a course whose point is manipulating a mechanism (that is `deep-interactive`).
You are designing a **lecture**. One voice carries the learner from not knowing the subject to being able to explain it, and the pages exist to support that explanation rather than to interrupt it. Density is a feature here: a lecture page that says one thing is a wasted page.
`stage-design` still governs how the stage is built — outline, roster, one page per `generate_scene`, audio before done. This skill governs what the stage contains and how it sounds.
subject answers, why it is worth an hour, and the route the lecture takes through it. Not a definitions page and not a table of contents.
carry one idea from statement to consequence — the claim, the mechanism underneath it, then real cases that test it. Arcs follow each other; the lecture never restarts.
at the seam where one arc closes and the next begins, testing whether the learner can apply the arc's idea rather than recall its words. Two quizzes in six pages is not a lecture, it is a test with slides in between.
in the whole lecture — the one place where telling genuinely fails and the learner has to see the thing move. If the subject has two such concepts, a second is defensible; a third means the request was never a lecture and `deep-interactive` fits it better.
established, what it deliberately left open, where a curious learner goes next.
Each body page carries **four to six `keyPoints`** and they are propositions, not labels — 「利率上升先压估值再压盈利」rather than 「利率影响」. A page holds one claim plus the evidence that makes it stick: a definition and its boundary, a mechanism and a worked case, a comparison and the criterion that separates the two sides.
Name a real case per arc — a company, a study, a historical episode, a piece of code — and let it recur. A lecture that cycles through a fresh unexplained example every page teaches nothing about any of them.
This is where the style is heard, so it is the part to get right.
to six sentences per line rather than a caption, and several lines to a page. The learner should be able to close their eyes and still follow.
state it, explain the mechanism, then walk a concrete case through that mechanism until the conclusion is unavoidable.
sentences, confident, unhurried, occasionally naming what is hard about the idea before resolving it.
already thinking, which the teacher then answers at length. One such exchange per arc, at most.
them, one-line captions that restate the slide's title, and cheerleading (「太棒了」「让我们开始吧」).
Examples of the right length and motion:
敏感度……接下来看 2022 年的例子,同样的加息幅度,为什么二十年期的跌幅是五年期 的四倍多。」
The runtime allows **exactly one teacher**, and in this style that teacher is the lecturer — the whole course is their voice. Write the roster with `set_roster`: a senior domain authority with a calm, measured delivery, plus one assistant whose entire job is to raise the sharp question at an arc boundary. Keep the roster small; a crowded classroom fragments a lecture. Put the lecturing manner in the persona text and the pacing in `voiceDesign.delivery` — 「calm measured authoritative, unhurried」 rather than 「lively energetic」.
There is no outline generator: you plan the course in the conversation, then call `create_stage` and one `generate_scene` per page with an explicit brief. Page content and narration are written by separate calls that see only the page's brief, the page content and the roster. So the style has to be carried there explicitly:
`generate_scene` `brief`;
— e.g. 「旁白为连续讲述,四到六句一段,先定义再机制再案例」「本页复用前一页 的同一家公司作为案例」. Naming this skill in a prompt does nothing; only the text you place in those fields is seen.
Titles are the lecture's own steps, in the language of the subject.
的共同点」
If the user wants to practise a skill, produce something of their own, or work through exercises, say so in one sentence and use `workshop-style` instead. Wrapping a practice request in a lecture produces a course the learner watches and cannot use.
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
Repo: thu-maic/openmaic
Evidence-based creation of a reusable personal course-making Skill from the user's own classroom and chat history. Use when the user asks to summarize,…
Multi-stage series — a request for several classrooms that belong together, like 「7 天学 Python」, a four-week onboarding track, a semester unit split across…
Deep Interactive courses. Plans the course so the learner manipulates something on most pages — simulations, diagrams they explore, code they run, games, 3D…
Courses whose content rests on current, external or real-world facts that must be verified against live sources before being taught — recent events, market or…
Improve factual reliability while creating or reviewing a course or supplied content. Use when the user asks to fact-check, verify accuracy, reduce…
Turn any concept, lesson, slide deck, or source material into a Feynman learning cycle in which learners explain first, expose the smallest gap, rebuild the…