OpenMAIC is a multi-agent classroom platform that uses agents to plan, build, and revise interactive courses from prompts and uploaded materials. It is designed for immersive learning experiences and supports course components such as slides, quizzes, interactives, projects, images, video, voices, and PowerPoint imports, with catalogue skills covering its workflows.
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 skills add THU-MAIC/OpenMAIC --skill lecture-stylegit clone --depth 1 https://github.com/THU-MAIC/OpenMAICWrote 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/thu-maic/openmaic/lecture-style)<a href="https://agentmods.dev/skills/thu-maic/openmaic/lecture-style"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/lecture-style/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/thu-maic/openmaic/lecture-style"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/lecture-style.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00121 | $0.01491 |
| Opus 5 | $0.00060 | $0.00745 |
| Sonnet 5 | $0.00024 | $0.00298 |
| Haiku 4.5 | $0.00012 | $0.00149 |
Grade A, and why
lecture-style 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 9d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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
slidethat 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
slidepages, 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
quizroughly 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
interactivepage, 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 anddeep-interactivefits 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.
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.
- 9d ago First seen · 120 lines · 121 tokens per session scan A 540e7a4b34cd
lecture-style is a skill published in the GitHub repository THU-MAIC/OpenMAIC (33,238 stars, last pushed 2d ago), licensed MIT. It adds 121 tokens to every session and 1,491 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 2026-08-30.
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.