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 page-clonegit 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/page-clone)<a href="https://agentmods.dev/skills/thu-maic/openmaic/page-clone"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/page-clone/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/page-clone"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/page-clone.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Prompt Injection · line 65 Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.Fix: Remove the large whitespace padding (blank-line blocks or long space runs) and review any content hidden below or to the right of it. Keep skill files compact and reviewable so no instructions can be
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 | $0.00120 | $0.03121 |
| Opus 5.5 | $0.00048 | $0.01248 |
| Sonnet 5.5 | $0.00024 | $0.00624 |
| Haiku 4.5 | $0.00012 | $0.00312 |
Grade A, and why
page-clone 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 — 189 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cloning one page's design
The design already exists on another page. Your job is to put new content into that design without redrawing it: copy the page, then swap what it says.
Copy-then-edit is the only clone path in this runtime. generate_scene always
re-rolls a page from its outline entry — the model invents a fresh element tree
every time — so calling it on a copied page destroys exactly the design you came
for. Nothing here validates the shape of your result either: the design is
preserved because you copied it, and the judgement about which elements are
content and which are the skeleton is yours.
The sequence
duplicate_scene({ templateSceneId, targetOrder, title })— an exact copy of the model page at the position you want (templateOrderworks too, but an id is safer). The copy carries the full content, no narration actions, and a new outline entry. Pass atitlethat names the NEW page; the entry inherits the model page's brief, and a copy still called 「第 3 章回顾」 misleads both the learner and the narration step.- Read the copy with
read_stage,path:/scenes/<order|id>,detail:"source"— this is your address space and your fidelity source. It returns the whole page's persisted JSON, including raw content HTML, inline spans, fonts, colours, fills, shadows, geometry and z-order, and it is the root your patch paths are written against: a field you read at/content/canvas/elements/2/contentis written back through that same path. Copy unchanged markup and style fields from this result; do not reconstruct them from stripped text. - Decide, element by element, what each one is. Content slots are the ones whose words belong to the old subject. Skeleton is everything else — rules, bands, page numbers, logos, decorative shapes, background art — and it stays untouched even when it holds text.
- Call
patch_stageonce per content slot, withop:"set"on the exact path that holds that slot's words —/content/canvas/elements/3/contentfor a paragraph,/content/canvas/elements/5/data/0/0/textfor a table cell. One leaf per call: everything you do not name keeps the value you copied.slide-dslis the manual for which field holds the words in each element type. Do not patch geometry or style paths while cloning — they ARE the design you copied. - Read the copy with
read_stage detail:"text"after the edits. It returns every text-bearing element as{ path, id, type, text }plus a page-widecombinedText, so you read the whole page's words in one call and get the pointer to fix with them. Search it for source-topic residue; the read reports, and you decide what is stale, thenset,remove, ordelete_elementit. generate_actionson the copy to give it narration (audio is on by default). A duplicated page arrives silent.
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 · 189 lines · 120 tokens per session scan A eeb220cf64b6
page-clone is a skill published in the GitHub repository THU-MAIC/OpenMAIC (41,328 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 3,121 once invoked, about $0.0005 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
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
visual-ralph
Visual Ralph orchestration for frontend UI from generated references, static references, or live URL targets, using $ultragoal with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
glance-canonical-layouts
Use this skill to create home screen widgets using Jetpack Glance Canonical Layouts from the Android Platform Samples project, or when asked to implement standard widget layout patterns (including Check List, Image Grid, Snap Scrolling, and Standard Toolbar).
accessibility
Consolidated accessibility skill entrypoint for WCAG 2.2, ARIA Authoring Practices, cognitive accessibility, Section 508, EN 301 549, design intent verification, and the Accessibility Planner workflow.