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 QuantumBFS/sci-brain --skill write-slidesgit clone --depth 1 https://github.com/QuantumBFS/sci-brainWrote 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/quantumbfs/sci-brain/write-slides)<a href="https://agentmods.dev/skills/quantumbfs/sci-brain/write-slides"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/write-slides/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/quantumbfs/sci-brain/write-slides"><img src="https://agentmods.dev/badge/skills/quantumbfs/sci-brain/write-slides.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 | $0.00028 | $0.01472 |
| Opus 5.5 | $0.00011 | $0.00589 |
| Sonnet 5.5 | $0.00006 | $0.00294 |
| Haiku 4.5 | $0.00003 | $0.00147 |
Grade A, and why
write-slides 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 29d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Installed resources
Keep the working directory at the user's project. Resolve this loaded SKILL.md
with Path(path).resolve() before locating resources; follow symlinks. A path
written as skills/<name>/... means the installed <name> skill's directory from
the agent's skill catalog. Locate dependencies by public skill name.
The slide template, gallery, layouts, and style documentation come from
GiggleLiu/sci-brain-slides.
Use release v0.1.0, package @preview/sci-brain-slides:0.1.0, with Typst
0.14.0 or newer. Check typst --version and typst fonts; the upstream
starter uses DejaVu Sans, with math and monospace fonts bundled with Typst.
Write scientific slides
Build a PDF talk from an agreed outline, using the upstream template's setup()
API. The upstream repository owns the slide components and their tests. This
skill owns the research context, presentation workflow, and final deck review.
For an actual manuscript, use write-paper; for an in-paper figure, use
how-to-review-figure with the figure's authoring tools.
1. Load context and agree the outline
Read the relevant manuscript or docs/discussion/*-brainstorm-ideas-log.md.
Resolve the project KB using how-to-download-ref when needed. Reuse figures
from $KB/.figures/, the manuscript, or earlier talks, and verify that claims
and citations match the source.
Capture the topic, audience, talk duration, and main claim. Propose sections with one claim and a figure idea for each. Get outline approval before composing the deck; an already approved outline can be reused.
2. Initialize the upstream template
Initialize from the published Typst package. Typst downloads v0.1.0 and its pinned dependencies automatically:
mkdir -p slides
typst init @preview/sci-brain-slides:0.1.0 slides/my-talk
Use a new deck directory rather than overwriting an existing talk. Record the package version and compile command alongside the deck so collaborators can repeat the setup. The first build needs network access; later builds can reuse Typst's package cache.
What ships with it
20 files 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.
- gallery.typ 9.9 KB
- references/layout-patterns.md 8.2 KB
- references/style-tokens.md 7.4 KB
- scripts/scaffold.py 4.4 KB runs code
- zoo/gadgets_cetz.typ 2.4 KB
- zoo/gadgets_pin.typ 1.3 KB
- zoo/gadgets.typ 12 KB
- zoo/layouts.typ 2.9 KB
- zoo/lib.typ 3.9 KB
- zoo/palettes/academic.typ 1.0 KB
- zoo/palettes/brand.typ 2.2 KB
- zoo/palettes/dark.typ 1.0 KB
- zoo/palettes/minimal.typ 1.1 KB
- zoo/palettes/vibrant.typ 1.0 KB
- zoo/scale.typ 688 B
- zoo/themes/academic.typ 739 B
- zoo/themes/brand.typ 983 B
- zoo/themes/dark.typ 771 B
- zoo/themes/minimal.typ 817 B
- zoo/themes/vibrant.typ 745 B
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.
- 29d ago Changed · -9 lines 3891ecf1c394
- 1mo ago Changed · -110 lines d5d3f5b55372
- 1mo ago First seen · 255 lines · 28 tokens per session scan A a44f3ed1d9a7
write-slides is a skill published in the GitHub repository QuantumBFS/sci-brain (101 stars, last pushed 23d ago), licensed MIT. It adds 28 tokens to every session and 1,472 once invoked, about $0.0001 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 2026-09-03.
Other skills, from other repositories
pydicom
Reads, inspects, writes, transforms, and preflights local DICOM datasets and pixel data. Applies to DICOM metadata, transfer syntaxes, compression plugins, frames, private elements, JSON, and bounded de-identification review.
pptx-posters
Creates and audits editable scientific posters in macro-free PowerPoint (.pptx) from author-approved local content and assets. Used when the requested deliverable is a PowerPoint research/conference poster and exact physical, printer, accessibility, provenance, and package-security checks are required.
nature-paper-trans
A workflow for translating selected pages or a complete English research-paper PDF into a simplified-Chinese, image-based PDF. bioRxiv is not mentioned in the provided details; the workflow applies to research-paper PDFs generally.
extracting-lab-tables
Detects and extracts tabular laboratory panels from PDFs, scans, and images into structured rows ready for OpenMed and FHIR. Use when the user has a CBC, CMP, lipid panel, or other lab report as a scanned image / PDF / spreadsheet and needs the test name, value, unit, reference range, and abnormal flag as clean rows.…
paper-compile
A build workflow that turns LaTeX source files into a PDF and checks whether the paper compiles correctly. LaTeX is a text-based system commonly used for academic papers.
figures
Makes publication-quality plots from data with matplotlib, learning curves, scaling laws, benchmark and ablation comparisons, Pareto trade-offs, heatmaps and confusion matrices, sized for the page, vector, with uncertainty shown. Use whenever results are plotted, charted or visualized for a paper, report or answer, or…