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 PangenomeAI/academic-skills-food-nutrition --skill food-pptgit clone --depth 1 https://github.com/PangenomeAI/academic-skills-food-nutritionWrote 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/pangenomeai/academic-skills-food-nutrition/food-ppt)<a href="https://agentmods.dev/skills/pangenomeai/academic-skills-food-nutrition/food-ppt"><img src="https://agentmods.dev/badge/skills/pangenomeai/academic-skills-food-nutrition/food-ppt/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/pangenomeai/academic-skills-food-nutrition/food-ppt"><img src="https://agentmods.dev/badge/skills/pangenomeai/academic-skills-food-nutrition/food-ppt.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 | $0.00208 | $0.01758 |
| Opus 5 | $0.00104 | $0.00879 |
| Sonnet 5 | $0.00042 | $0.00352 |
| Haiku 4.5 | $0.00021 | $0.00176 |
Grade A, and why
food-ppt 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 12d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Food-Ppt — Editable Presentations from Food & Nutrition Reports
Turn a review report, evidence brief, or manuscript into a fully editable
.pptx — every title, bullet, table, and figure is a native PowerPoint object the
author can edit, never a flattened image. Original work; the schema→builder→QA
architecture and design sensibility are informed by the open-source (MIT) ppt-master,
GordenPPTSkill, and codex-ppt-skill skills and the taste-skill and
ui-ux-pro-max-skill design guides (see the repo README Acknowledgements). No
third-party templates are bundled.
What it converts
The outputs of the suite's other skills, or any report/paper the user supplies:
food-reviewpanel report / Review & Response Report → a review-findings deck.food-research/food-deep-researchevidence brief or literature review → a synthesis deck.food-papermanuscript (or sections) → a paper-presentation / journal-club deck.food-pipeline— offered at FINALIZE to package the finished work as slides.
Required content for a proposal / paper deck
- Experimental-design flow diagram — a
flowslide near the front, built fromfood-figure's blueprint (experimental-flow.md) and rendered as native, movable PowerPoint shapes (one box per step, one arrow per transition — never a flattened image), so the audience grasps the design at a glance. Mandatory for any deck from a research proposal or research paper. - Results slides illustrate the result — each is a
resultslide: a figure (fromfood-figure, theme-matched) where feasible, or a scientific table when the numbers are the point, plus a Key findings panel of takeaways. - Big numbers and parallel facts get their own design — a single striking figure
goes on a
metricbig-number hero; a set of parallel facts (objectives, contributions, study parameters, KPIs) goes on acardsaccent-bar grid, not a bullet list (references/slide-design.md). - Executive summary — a closing summary slide is required in every deck.
- Theme-matched figures — figures use the deck theme's palette so they match the slides.
What ships with it
21 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.
- agents/deck_builder.md 1.1 KB
- agents/deck_qa.md 1.5 KB
- agents/figure_placer.md 1.8 KB
- agents/outline_planner.md 1.6 KB
- agents/ppt_coordinator.md 2.1 KB
- agents/slide_writer.md 1.7 KB
- examples/ai-news-brief-demo.deck.json 7.1 KB
- examples/ai-news-brief-demo.pptx 57 KB
- examples/experimental-design-demo.deck.json 4.0 KB
- examples/experimental-design-demo.pptx 54 KB
- examples/polyphenols-antimicrobial-review.deck.json 5.3 KB
- examples/polyphenols-antimicrobial-review.pptx 56 KB
- examples/README.md 3.8 KB
- references/deck-spec.md 5.6 KB
- references/editability-and-qa.md 2.4 KB
- references/slide-design.md 3.5 KB
- references/source-to-slides.md 3.1 KB
- references/templates.md 2.8 KB
- templates/INDEX.md 5.1 KB
- templates/theme-previews.svg 127 KB
- templates/themes.json 8.4 KB
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.
- 12d ago First seen · 94 lines · 208 tokens per session scan A ef476597c95a
food-ppt is a skill published in the GitHub repository PangenomeAI/academic-skills-food-nutrition (31 stars, last pushed 12d ago), licensed MIT. It adds 208 tokens to every session and 1,758 once invoked, about $0.0010 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
nature-paper2ppt
Build a complete but efficient Nature-style Chinese PPTX presentation from a scientific paper, preprint, PDF, article text, abstract, figure legends, or reading notes. Use this skill whenever the user asks to make slides/PPT/PPTX for journal club, group meeting, paper sharing, thesis seminar, lab meeting, department…
aaai-artifact-evaluation
Use when packaging AAAI code, data, multimedia appendices, technical appendices, reproducibility evidence, and post-acceptance artifact releases without violating double-blind or immutable-supplement rules.
acl-artifact-evaluation
Use when packaging code, datasets, prompts, model outputs, or annotation materials for an ACL submission under ACL Rolling Review, covering anonymized supplement archives, scientific-artifact items of the Responsible NLP checklist, licensing and intended-use documentation, data statements, and post-acceptance public…
aer-consistency
Use when auditing a finished or near-finished AER, AER:Insights, or AEJ manuscript for internal consistency: headline numbers across abstract, introduction, results, and tables; sample sizes; log-point and percentage-point conversions; cross-references; and in-text-citation/bibliography matching. Apply after the body…
thesis-consistency-audit
A consistency audit for quantitative master’s and doctoral theses in management, finance, or strategy. It checks whether numbers, tables, analyses, and claims agree, and can inspect hidden author information in office documents.
tikz-figure-review
Review and fix alignment, label collision, clipping, legend-over-data, overlap, and layout issues in TikZ and pgfplots figures inside LaTeX documents. Use when the user wants to review figures in a paper, tutorial, lecture notes, or thesis before submission; when a reviewer flags figure problems; when a rendered…