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 slide-craftgit 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/slide-craft)<a href="https://agentmods.dev/skills/thu-maic/openmaic/slide-craft"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/slide-craft/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/slide-craft"><img src="https://agentmods.dev/badge/skills/thu-maic/openmaic/slide-craft.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Snyk pass
- 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 | $0.00140 | $0.04029 |
| Opus 5 | $0.00070 | $0.02014 |
| Sonnet 5 | $0.00028 | $0.00806 |
| Haiku 4.5 | $0.00014 | $0.00403 |
Grade A, and why
slide-craft 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 — 296 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The design law of a slide page
Every slide in this runtime was drawn under a long set of rules — the canvas, the height table, the type scale, the spacing standards. The generator that drew the page had all of them in front of it. When you patch one element, you have the page's numbers and nothing else, and the rules are the only way to tell a repair from a dent.
This is that rule set, restated for editing. It is about the page, not the process: which numbers a change has to stay consistent with, and which fields actually reach the screen.
The canvas you are editing inside
The canvas is 1000 × 562.5. All elements respect a 50px margin, so the
live area is left ∈ [50, 950], top ∈ [50, 512.5], and an element's right
edge (left + width) stays ≤ 950, its bottom edge ≤ 512.5.
The page's own alignment grid, which existing elements are already on:
- Left-aligned content sits at
left = 60orleft = 80. - Centred content is
left = (1000 - width) / 2— recomputed, never guessed. - Right-aligned content is
left = 1000 - width - 60.
Changing width on centred content changes left too, and they are two separate
writes. Read the neighbours' boxes first and land on the column they are already
using; a lone element 8px off the shared left edge reads as a mistake even though
nothing overflows.
There is no alignment operation. Every position is an explicit number you
write to that element's own left / top / width / height, one path per call,
computed from the neighbours you read. Aligning a row means giving each element the
number the row already uses — not asking the page to tidy itself.
Text is sized by table, not by eye
A text element has 10px padding on all four sides, so its usable area is
(width - 20) × (height - 20), and heights come from one table
(line-height 1.5, padding included):
| Font size | 1 line | 2 lines | 3 lines | 4 lines | 5 lines |
|---|---|---|---|---|---|
| 14px | 43 | 64 | 85 | 106 | 127 |
| 16px | 46 | 70 | 94 | 118 | 142 |
| 18px | 49 | 76 | 103 | 130 | 157 |
| 20px | 52 | 82 | 112 | 142 | 172 |
| 24px | 58 | 94 | 130 | 166 | 202 |
| 28px | 64 | 106 | 148 | 190 | 232 |
| 32px | 70 | 118 | 166 | 214 | 262 |
| 36px | 76 | 130 | 184 | 238 | 292 |
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 · 296 lines · 140 tokens per session scan A cf35eea56909
slide-craft is a skill published in the GitHub repository THU-MAIC/OpenMAIC (34,007 stars, last pushed today), licensed MIT. It adds 140 tokens to every session and 4,029 once invoked, about $0.0007 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
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 $ralph with built-in visual verdict and pixel-diff evidence until the implementation matches and leaves a reproducible design system.
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.
make-resume
A Chinese-language tool for creating editable HTML resumes that can be changed in a browser and printed to PDF. It uses available resume templates when they are installed and otherwise provides a simpler fallback.