Lecture Style logo

Lecture Style

OrganizationPopular
THU-MAIC
lecture-style

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`).

Overview

PublisherTHU-MAIC
RepositoryOpenMAIC
Skill namelecture-style
Stars
37.6K
Forks
5.9K
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by THU-MAIC on GitHub. Read the source before you install it.

Installation

Install the Lecture Style AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/THU-MAIC/OpenMAIC.git /tmp/OpenMAIC
mkdir -p .claude/skills
cp -r /tmp/OpenMAIC/skills/agent-runtime/lecture-style .claude/skills/lecture-style
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Lecture Style in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Lecture Style on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Lecture Style is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Masterclass lecture design

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.

The shape

  • Scene 1 is a slide that opens the lecture properly — the question the 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.
  • The body is slide pages, in arcs. An arc is three to five pages that 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.
  • Checkpoints are rare. One quiz roughly every four to five pages, placed 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.
  • At most one interactive page, at the single most mechanism-heavy concept 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.
  • Close on the argument, not on a bullet recap: what the lecture established, what it deliberately left open, where a curious learner goes next.

Page density

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.

Narration is the lecture

This is where the style is heard, so it is the part to get right.

  • Every body page gets a long, continuous stretch of teacher speech — four 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.
  • Narration moves forward. Each line picks up the last one's final idea: state it, explain the mechanism, then walk a concrete case through that mechanism until the conclusion is unavoidable.
  • The register is an authority thinking aloud in front of a room — full sentences, confident, unhurried, occasionally naming what is hard about the idea before resolving it.
  • The assistant speaks rarely, and only to ask the question the room is already thinking, which the teacher then answers at length. One such exchange per arc, at most.
  • Forbidden in this style: 「大家想一想」-style prompts with nothing behind 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:

  • Good: 「我们先把定义钉住——所谓久期,不是债券还剩多少年,而是价格对利率的 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。」
  • Bad: 「这一页讲久期。久期很重要。下面我们来看例子。」

The roster

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」.

Carrying the style into the generators

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:

  • put the arc structure and the density expectation into each page's generate_scene brief;
  • put the lecturing manner into each persona of set_roster;
  • pass the narration directive for each page in generate_scene.materialFacts — 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.

Scene naming

Titles are the lecture's own steps, in the language of the subject.

  • Good: 「久期到底在度量什么」「同样加息,为什么长债跌得更狠」「三个反例,和它们 的共同点」
  • Bad: 「概念介绍」「案例分析」「本课总结」

If the request is not a lecture

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.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Lecture Style AI skill do?

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`).

Why use Lecture Style on TypingMind?

Because you install it once and use it with any model. Lecture Style is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Lecture Style in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/THU-MAIC/OpenMAIC/tree/main/skills/agent-runtime/lecture-style. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Lecture Style?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Lecture Style?

As many as you like. As long as a model supports skills, you can use Lecture Style with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Lecture Style AI skill free?

Yes. It is published on GitHub by THU-MAIC under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇