agentsclimarketplace

Agri review

Skill PangenomeAI/academic-skills-food-nutrition/agri-review

Open, MIT-licensed food & nutrition science research skills for Claude Code, Codex, and MiniMax Agent — multi-agent literature/systematic review, journal-aware writing, peer review, and figures, plus author-guideline skills for 150+ journals. Initiated by the Food Science Group, University of Melbourne.

Install
npx -y skills add PangenomeAI/academic-skills-food-nutrition --skill agri-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 25 days oldThe repository was created 25 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 17 stars17 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Multi-reviewer peer-review system for agricultural manuscripts. Simulates an editorial panel — a coordinating editor, three domain reviewers (methodology, domain/novelty, integrity/ethics) and a devil's advocate — plus a formatting check against the target journal, all acting as senior agricultural scientists. Same machinery as food-review, including the knowledge_builder that reads the cited sources and key field literature first, grounded in agriculture literature (Q1/Q2 preferred, Q4 avoided) and agricultural standards for field trials, experimental unit and pseudoreplication, animal ethics and soils. Triggers: review my agronomy paper, peer review agricultural manuscript, referee report soil science, critique my crop paper, pre-submission review agriculture, mock review animal science.

SKILL.md

4.5 KB, as published. Nobody here has run it

Agri-Review — Peer-Review Panel for Agricultural Science

Run the food-review skill exactly — its panel (review_coordinator, knowledge_builder, reviewer_methodology, reviewer_domain, reviewer_integrity, devils_advocate, format_checker), its modes (full · quick · methodology · re-review), and its report format — with the agriculture substitutions in agri-research/references/agriculture-domain.md. Read that file first. No new machinery here.

The substitutions

  1. Persona — every reviewer is a senior agricultural scientist of the specific discipline (agronomy · soil science · horticulture · dairy & animal science · agricultural engineering · agricultural economics & policy). Name the discipline; a soil-carbon paper gets a soil scientist's standards (domain §2).
  2. Knowledge base — knowledge_builder runs first, unchanged in method: Pathway A reads the manuscript's cited sources in full and audits whether each supports its claim; Pathway B reads the field's key literature, ranked as Tier 1 Q1/Q2 agriculture (journals/_coverage_agriculture.md)
    • Nature/Science/Cell/PNAS + Q1/Q2 adjacent disciplines, Q4 avoided. Pathway B may use agri-research's full review branch for discovery/screening — knowledge extraction only, no literature-review article (domain §3). Inside agri-pipeline with a Stage-1 evidence base: reuse it and top up with agri-research quick brief key reviews, exactly as food-review does.
  3. Journal routing — format_checker audits against the journal resolved once by journal-selector from the agriculture coverage map (domain §4); APA 7.0 default.

What an agricultural reviewer checks first (domain §5)

  • The experimental unit / pseudoreplication — subsamples counted as replicates, plants scored as units within one plot, animals within one pen. The single most common fatal flaw; raise it as Critical when present.
  • Field-trial reporting — site, season(s)/years, soil classification, cultivar, plot size, design, replication, management, statistical model.
  • Generalisation — one site-year, one region, or a pot/glasshouse study presented as a general agronomic recommendation; missing G×E.
  • Animal work — ethics approval and ARRIVE; diet composition; unit (pen vs animal).
  • Soil work — sampling depth, bulk density, equivalent-soil-mass basis for stock claims.
  • Economics/policy — identification strategy; causal language unearned by design.

Inherited unchanged (not optional)

The report format (food-review/references/report-format.md: Parts A/B/C, stable issue IDs, Response (type) taxonomy, editorial decision — Accept · Minor Revision · Major Revision · Reject with the decisive reasons) and its Word (.docx) deliverable rule — never Markdown; inside agri-pipeline this is the single Review & Response Report that agri-paper later fills responses into, so no separate reviewer report or response letter is created. Also inherited: editor-query comments placed in the manuscript for fixes needing the author's data (word-review-comments.md), the AI-writing-tell check (human-writing.md), the privacy scan, and the rule that a source never retrieved is marked, not summarized.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.