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 deep-interactivegit 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/deep-interactive)<a href="https://agentmods.dev/skills/thu-maic/openmaic/deep-interactive"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/deep-interactive/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/deep-interactive"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/deep-interactive.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 | $0.00074 | $0.00643 |
| Opus 5.5 | $0.00030 | $0.00257 |
| Sonnet 5.5 | $0.00015 | $0.00129 |
| Haiku 4.5 | $0.00007 | $0.00064 |
Grade A, and why
deep-interactive 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 — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Deep Interactive course design
Default to doing, not reading. A page earns the slide type only when the
learner has nothing to manipulate on it.
Structure
- Scene 1 is a
slide: it frames the question the course answers and tells the learner what they are about to play with. One page, no more. - The body is
interactive. Each body scene isolates one mechanism, one variable, one structure — so the learner can change it and watch the result. - The last scene is a
slideor aquizthat consolidates what the manipulation showed. - Consecutive interactive scenes must not use the same
widgetType. Two simulations in a row is a design failure; vary the modality as the concept moves from "watch it" to "trace it" to "predict it".
Choosing a widget type
| widgetType | Use when the learner should… |
|---|---|
simulation |
vary parameters and watch a system respond in real time |
diagram |
explore structure, flow or hierarchy by expanding and following |
code |
read, modify and run a short program that embodies the idea |
game |
make repeated decisions under a rule set and see the score move |
visualization3d |
inspect a spatial object or scene from angles a slide cannot show |
widgetOutline
Every interactive scene must carry a widgetOutline populated for its type —
an interactive scene with an empty widget outline degrades to a generic page and
defeats the whole point.
simulation:concept,keyVariables(the actual sliders/inputs)diagram:diagramType,nodes(withlabel, andparentIdfor hierarchy)code:language,conceptgame:gameType,challenge,playerControlsvisualization3d:visualizationType,objects,interactions
Scene naming
Titles name what the learner does or discovers, not the topic heading.
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 · 58 lines · 74 tokens per session scan A bb26d6b34f34
deep-interactive is a skill published in the GitHub repository THU-MAIC/OpenMAIC (41,328 stars, last pushed yesterday), licensed MIT. It adds 74 tokens to every session and 643 once invoked, about $0.0003 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.