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 SlideSpeak/slide-design-skill --skill academicgit clone --depth 1 https://github.com/SlideSpeak/slide-design-skillWrote 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/slidespeak/slide-design-skill/academic)<a href="https://agentmods.dev/skills/slidespeak/slide-design-skill/academic"><img src="https://agentmods.dev/badge/skills/slidespeak/slide-design-skill/academic.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00048 | $0.00971 |
| Opus 5 | $0.00024 | $0.00485 |
| Sonnet 5 | $0.00010 | $0.00194 |
| Haiku 4.5 | $0.00005 | $0.00097 |
Grade A, and why
academic 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 8d 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Academic Style — Authoring Guide
You write decks as if you are a researcher presenting to peers at a top conference. The audience is expert. They will read your figures, not your prose.
Voice
- Past tense for methods and findings ("We sampled", "Subjects reported").
- Hedge precisely ("suggests", "is consistent with", "does not support"), don't oversell.
- Every claim has an inline citation (Author, Year) or footnote number.
- Never use "obviously", "clearly", "simply" — they patronize an expert audience.
- Equations are first-class content, not decoration. Render with proper notation.
Structure (canonical academic arc)
- Title — paper title, authors, affiliation, conference/journal, date
- Motivation — the problem in 1 slide, 2-3 references max
- Research question — single line, possibly with sub-questions
- Prior work — bibliography-style list with positioning
- Method — diagram + 3-4 step list
- Data — tables, sample sizes, sources
- Results (3-6 slides) — one finding per slide, with supporting figure
- Discussion — implications, limitations, future work
- Conclusion — 3 takeaways
- References — full bibliography
- Q&A holding slide — contact, paper link, code/data link
Visual System
- Cream ground (#F5F1E8), ink (#1A1A1A).
- Accent: deep teal (#0F4C5C) — used sparingly for headlines and key data callouts.
- Figures: 2-3 tones max. Default palette: ink, teal, muted-rust (#A8554E).
- Tables: 1px hairlines, no fills, no zebra striping. Tufte minimalism.
- Equations centered with extra vertical space. Use proper math typography.
- Footnote-style citations in muted gray at the bottom margin.
Graphic system
- Signature mark: the citation bracket. The [n] apparatus that runs through the deck becomes the visual identity; the title slide sets a giant pale serif bracket, cropped by the left canvas edge, behind the paper title.
- Structural device: the double hairline (.ax-rule), two 1px ink rules set under every section headline. Tufte separator, never a thick bar.
- Evidence plate (.ax-plate): a 1px ink frame with a small teal tab on its top edge wraps anything evidentiary: result figures, result tables. The tab marks "exhibit", never status.
- Surface: title and Q&A carry a faint parchment grain. Working slides stay flat.
- The system never does: icons, color beyond the one teal, brackets as repeated decoration (the giant bracket exists once, on the title).
What ships with it
5 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.
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.
- 8d ago First seen · 72 lines · 48 tokens per session scan A 872a2fda87e3
academic is a skill published in the GitHub repository SlideSpeak/slide-design-skill (19 stars, last pushed 2mo ago), licensed MIT. It adds 48 tokens to every session and 971 once invoked, about $0.0002 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
omh-jit-learn
This is a Hermes-native jit-learn workflow skill.
omh-codebase-uml
This is a Hermes-native codebase-uml workflow skill.
omh-curriculum-design
This is a Hermes-native curriculum-design workflow skill.
omh-paper-learning
This is a Hermes-native paper-learning workflow skill.
qiuzhi2046-skill
A Chinese-language, hands-on approach to teaching and reviewing AI tools, starting with a user problem and ending with a practical solution. It combines beginner-to-advanced tutorials, tool testing, short and long content, and organized knowledge bases.
learn
Guided, hands-on course teaching architects how to use Codex or Claude Code — six short modules, each built around an exercise on a bundled sandbox project (a fictional Brooklyn art museum expansion). Resumable across sessions via PROGRESS.md. Use when the user runs $learn or /as:learn, says they're new to AI-assisted…