agri-review

Name: agri-review
Author: PangenomeAI

16stars1forks

How to install agri-review?

pangenomeai/academic-skills-food-nutrition/agri-review

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

Installs into the current project.

Summary

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

Files · 1

View on GitHub

SKILL.md

1	# Agri-Review — Peer-Review Panel for Agricultural Science
2
3	Run the `food-review` skill exactly — its panel (`review_coordinator`,
4	`knowledge_builder`, `reviewer_methodology`, `reviewer_domain`,
5	`reviewer_integrity`, `devils_advocate`, `format_checker`), its modes (**full ·
6	quick · methodology · re-review**), and its report format — with the agriculture
7	substitutions in
8	[`agri-research/references/agriculture-domain.md`](../agri-research/references/agriculture-domain.md).
9	Read that file first. No new machinery here.
10
11	## The substitutions
12	1. Persona — every reviewer is a **senior agricultural scientist of the specific
13	discipline** (agronomy · soil science · horticulture · dairy & animal science ·
14	agricultural engineering · agricultural economics & policy). Name the discipline;
15	a soil-carbon paper gets a soil scientist's standards (domain §2).
16	2. Knowledge base — `knowledge_builder` runs first, unchanged in method:
17	Pathway A reads the manuscript's cited sources in full and audits whether each
18	supports its claim; Pathway B reads the field's key literature, ranked as
19	Tier 1 Q1/Q2 agriculture ([`journals/_coverage_agriculture.md`](../journals/_coverage_agriculture.md))
20	+ Nature/Science/Cell/PNAS + Q1/Q2 adjacent disciplines, Q4 avoided. Pathway B
21	may use `agri-research`'s `full review` branch for discovery/screening —
22	knowledge extraction only, no literature-review article (domain §3).
23	Inside `agri-pipeline` with a Stage-1 evidence base: reuse it and top up with
24	`agri-research` quick brief key reviews, exactly as `food-review` does.
25	3. Journal routing — `format_checker` audits against the journal resolved once by
26	`journal-selector` from the agriculture coverage map (domain §4); APA 7.0 default.
27
28	## What an agricultural reviewer checks first (domain §5)
29	- The experimental unit / pseudoreplication — subsamples counted as replicates,
30	plants scored as units within one plot, animals within one pen. The single most
31	common fatal flaw; raise it as Critical when present.
32	- Field-trial reporting — site, season(s)/years, soil classification,
33	cultivar, plot size, design, replication, management, statistical model.
34	- Generalisation — one site-year, one region, or a pot/glasshouse study presented
35	as a general agronomic recommendation; missing G×E.
36	- Animal work — ethics approval and ARRIVE; diet composition; unit (pen vs
37	animal).
38	- Soil work — sampling depth, bulk density, equivalent-soil-mass basis for stock
39	claims.
40	- Economics/policy — identification strategy; causal language unearned by design.
41
42	## Inherited unchanged (not optional)
43	The report format (`food-review/references/report-format.md`: Parts A/B/C, stable
44	issue IDs, `Response (type)` taxonomy, **editorial decision — Accept · Minor
45	Revision · Major Revision · Reject with the decisive reasons**) and its
46	Word (`.docx`) deliverable rule — never Markdown; inside `agri-pipeline` this is
47	the single Review & Response Report that `agri-paper` later fills responses into,
48	so no separate reviewer report or response letter is created. Also inherited:
49	editor-query comments placed in the manuscript for fixes needing the author's
50	data (`word-review-comments.md`), the AI-writing-tell check (`human-writing.md`), the
51	privacy scan, and the rule that a source never retrieved is **marked, not
52	summarized**.

People who liked this also viewed

6 picks

Type

agri-review

16stars1forks

View on GitHub

How to install agri-review?

pangenomeai/academic-skills-food-nutrition/agri-review

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Agri-Review — Peer-Review Panel for Agricultural Science
2
3	Run the `food-review` skill exactly — its panel (`review_coordinator`,
4	`knowledge_builder`, `reviewer_methodology`, `reviewer_domain`,
5	`reviewer_integrity`, `devils_advocate`, `format_checker`), its modes (**full ·
6	quick · methodology · re-review**), and its report format — with the agriculture
7	substitutions in
8	[`agri-research/references/agriculture-domain.md`](../agri-research/references/agriculture-domain.md).
9	Read that file first. No new machinery here.
10
11	## The substitutions
12	1. Persona — every reviewer is a **senior agricultural scientist of the specific
13	discipline** (agronomy · soil science · horticulture · dairy & animal science ·
14	agricultural engineering · agricultural economics & policy). Name the discipline;
15	a soil-carbon paper gets a soil scientist's standards (domain §2).
16	2. Knowledge base — `knowledge_builder` runs first, unchanged in method:
17	Pathway A reads the manuscript's cited sources in full and audits whether each
18	supports its claim; Pathway B reads the field's key literature, ranked as
19	Tier 1 Q1/Q2 agriculture ([`journals/_coverage_agriculture.md`](../journals/_coverage_agriculture.md))
20	+ Nature/Science/Cell/PNAS + Q1/Q2 adjacent disciplines, Q4 avoided. Pathway B
21	may use `agri-research`'s `full review` branch for discovery/screening —
22	knowledge extraction only, no literature-review article (domain §3).
23	Inside `agri-pipeline` with a Stage-1 evidence base: reuse it and top up with
24	`agri-research` quick brief key reviews, exactly as `food-review` does.
25	3. Journal routing — `format_checker` audits against the journal resolved once by
26	`journal-selector` from the agriculture coverage map (domain §4); APA 7.0 default.
27
28	## What an agricultural reviewer checks first (domain §5)
29	- The experimental unit / pseudoreplication — subsamples counted as replicates,
30	plants scored as units within one plot, animals within one pen. The single most
31	common fatal flaw; raise it as Critical when present.
32	- Field-trial reporting — site, season(s)/years, soil classification,
33	cultivar, plot size, design, replication, management, statistical model.
34	- Generalisation — one site-year, one region, or a pot/glasshouse study presented
35	as a general agronomic recommendation; missing G×E.
36	- Animal work — ethics approval and ARRIVE; diet composition; unit (pen vs
37	animal).
38	- Soil work — sampling depth, bulk density, equivalent-soil-mass basis for stock
39	claims.
40	- Economics/policy — identification strategy; causal language unearned by design.
41
42	## Inherited unchanged (not optional)
43	The report format (`food-review/references/report-format.md`: Parts A/B/C, stable
44	issue IDs, `Response (type)` taxonomy, **editorial decision — Accept · Minor
45	Revision · Major Revision · Reject with the decisive reasons**) and its
46	Word (`.docx`) deliverable rule — never Markdown; inside `agri-pipeline` this is
47	the single Review & Response Report that `agri-paper` later fills responses into,
48	so no separate reviewer report or response letter is created. Also inherited:
49	editor-query comments placed in the manuscript for fixes needing the author's
50	data (`word-review-comments.md`), the AI-writing-tell check (`human-writing.md`), the
51	privacy scan, and the rule that a source never retrieved is **marked, not
52	summarized**.

People who liked this also viewed

6 picks

Type