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 workshop-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/workshop-style)<a href="https://agentmods.dev/skills/thu-maic/openmaic/workshop-style"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/workshop-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/workshop-style"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/workshop-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 | $0.00144 | $0.01546 |
| Opus 5.5 | $0.00058 | $0.00618 |
| Sonnet 5.5 | $0.00029 | $0.00309 |
| Haiku 4.5 | $0.00014 | $0.00155 |
Grade A, and why
workshop-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 1mo 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workshop design
You are designing a workshop. Nothing is explained for longer than it takes to set up the next thing the learner does, and every idea is followed immediately by a page where they try it. The learner leaves having built something, not having been told about it.
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, and it is short: what the learner will have made by the end, and the first thing they are about to try. No agenda, no history of the field. - Every concept is followed at once by a hands-on page. The rhythm is
concept → do it, concept → do it: roughly one
interactiveorquizpage for every two pages in the course. If two explanatory pages ever sit next to each other, one of them is unnecessary. interactivepages are the exercises. Each isolates one thing to build, vary or trace. Consecutive interactive pages must not reuse the samewidgetType— as the learner moves from trying to predicting to applying, the modality moves with them.quizpages are quick self-checks, not exams — placed right after a hands-on page to make the learner state what they just observed. Short, two or three questions.- The last page is a small integrating project: one
interactivepage whose task needs several of the workshop's pieces at once, with the earlier exercises as its parts. Not a summary slide. This is the page the learner screenshots afterwards.
Slides are task briefs
A slide in a workshop exists to make the next exercise possible. Keep it to
two or three keyPoints — the rule, the shape, the one gotcha — and put
everything else in the exercise. A workshop slide that could be read on its own
as a lesson is too long: cut it and let the interactive page teach.
widgetOutline
Every interactive page must carry a populated widgetOutline, always
including concept — the one thing this exercise is about. An interactive page
with an empty widget outline degrades into a generic page, which in this style
takes the course's whole point with it.
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.
- 1mo ago First seen · 121 lines · 144 tokens per session scan A 002a4c984206
workshop-style is a skill published in the GitHub repository THU-MAIC/OpenMAIC (41,328 stars, last pushed yesterday), licensed MIT. It adds 144 tokens to every session and 1,546 once invoked, about $0.0006 per session on Opus 5.5. 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…
exam-forecast
Analyze past exams from the same professor to surface patterns — subject weighting, recurring issue-spot traps, favored hypo types, policy-vs-doctrine mix — and forecast likely emphases for the upcoming exam. Use when the user says "what's on the exam", "analyze past exams", "predict the exam", or shares past exams.
lean-formalize
Develop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific…
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.