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-researchgit 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-research)<a href="https://agentmods.dev/skills/pangenomeai/academic-skills-food-nutrition/food-research"><img src="https://agentmods.dev/badge/skills/pangenomeai/academic-skills-food-nutrition/food-research/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-research"><img src="https://agentmods.dev/badge/skills/pangenomeai/academic-skills-food-nutrition/food-research.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 | $0.00154 | $0.04703 |
| Opus 5 | $0.00077 | $0.02351 |
| Sonnet 5 | $0.00031 | $0.00941 |
| Haiku 4.5 | $0.00015 | $0.00470 |
Grade A, and why
food-research 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 — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Food-Research — Comprehensive Evidence Synthesis for Food & Nutrition Science
Build a broad, defensible understanding of a topic by searching many sources, screening them consistently, and synthesizing across them. Original work; no third-party research text is reused. Architecture informed by open community literature-search skills (see Acknowledgements in the repo README).
Streams — pick one and when to use it
Four streams share the same search/screening machinery but differ in depth. Three
of them (quick brief, full review, deep research) prioritize sources by
journal ranking via journal_ranker; the systematic stream does not
(inclusion is by pre-specified eligibility, not prestige).
| Stream | Use it when… | Depth | Journal-ranking filter |
|---|---|---|---|
| quick brief | You need fast orientation on a topic — "what's known about X", a starting point, a scoping glance. | One search pass; top sources; key open questions. May run inline without subagents. | Yes — Tier 1 only, usually |
| full review | You want a thorough narrative review manuscript (the default). | Four-layer search + two-phase screening + synthesis → write manuscript (writer) → review loop (reviewer) → Word (.docx). |
Yes — Tier 1 preferred, Tier 2 to fill gaps |
| deep research | The question extends beyond the literature — regulatory landscape, market/technology state, an open-ended "investigate this" — or you want an iterative, verified deep dive on a subtopic. | Calls the food-deep-research skill (scope → plan → investigate → verify → synthesize → critique loop); its literature portion still passes through journal ranking. |
Yes — for the literature portion |
| systematic | You need a reproducible, auditable PRISMA review / meta-analysis with a protocol, ≥3 databases, dual independent screening, and risk-of-bias (OHAT) — i.e. a defensible, publishable systematic review. | Full systematic_reviewer pipeline (protocol → sr_search → dual 3-step sr_screener + sr_moderator → PRISMA → data_extractor results table → risk_of_bias OHAT → sr_synthesis → reviewer loop → writer Word .docx). |
No — eligibility-based inclusion |
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.
- agents/data_extractor.md 2.8 KB
- agents/journal_ranker.md 3.9 KB
- agents/reviewer.md 2.9 KB
- agents/risk_of_bias.md 4.7 KB
- agents/screener_appraiser.md 2.3 KB
- agents/search_strategist.md 1.7 KB
- agents/source_scout.md 1.7 KB
- agents/sr_moderator.md 1.8 KB
- agents/sr_screener.md 1.8 KB
- agents/sr_search.md 1.7 KB
- agents/sr_synthesis.md 3.1 KB
- agents/synthesis.md 1.8 KB
- agents/systematic_reviewer.md 4.6 KB
- agents/writer.md 4.0 KB
- references/full-text-access.md 13 KB
- references/journal-priority.csv 16 KB
- references/literature-sources.md 2.2 KB
- references/ohat-risk-of-bias.md 4.3 KB
- references/reporting-guidelines.md 1.5 KB
- references/source-quality-hierarchy.md 1.6 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 · 210 lines · 154 tokens per session scan A e47b95973b28
food-research is a skill published in the GitHub repository PangenomeAI/academic-skills-food-nutrition (31 stars, last pushed 12d ago), licensed MIT. It adds 154 tokens to every session and 4,703 once invoked, about $0.0008 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
paper-framework-figure-studio-pro
Human-in-the-loop research-paper framework figure workflow from S0-PAPER-FOUNDATION through terminal S5-CANDIDATE-IMAGE. Use for paper-grounded architecture, pipeline, method overview, agent workflow, system/data-flow, and mechanism figures with generated raster first-round/formal candidates, reviewer-first-glance…
autofigure
Generate clean, EDITABLE vector figures (SVG + exact-size PDF) for research papers — method / architecture / pipeline / system-overview diagrams — with AutoFigure-Edit. Use whenever the user wants to create or vectorize a paper figure from a text description OR from a draft/screenshot/draw.io image: it generates a…
paper-polish-pipeline
Staged, diagnosis-driven academic paper polishing pipeline (bilingual 中文/English). Use to revise a paper from rough draft to final submission across ordered stages: diagnose first, then optimize section by section, derive abstract/contributions from the revised body, polish the language to reduce AI-sounding phrasing…
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…
nature-reviewer
A peer-review checklist that assesses a research paper from a referee’s point of view, including its novelty, importance, and technical soundness.
nature-academic-search
Multi-source literature search, citation verification, MeSH search strategy, citation file management (.nbib/.ris/.bib conversion), and reference management (BibTeX, related articles, ID conversion) via MCP tools (PubMed, CrossRef, arXiv, Scopus, ScienceDirect). Use when the user needs coordinated multi-step…