agri-deep-research

Name: agri-deep-research
Author: PangenomeAI

16stars1forks

How to install agri-deep-research?

pangenomeai/academic-skills-food-nutrition/agri-deep-research

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

Installs into the current project.

Summary

Deep research producing a fully written, source-validated literature review on an agricultural question, as a senior agricultural scientist of the relevant discipline: scope, design the method, discover and screen by journal ranking, validate every source, extract and verify evid

Files · 1

View on GitHub

SKILL.md

1	# Agri-Deep-Research — Source-Validated Reviews for Agricultural Science
2
3	Run the `food-deep-research` skill exactly — its 12-subagent team
4	(`research_scope`, `research_architect`, `investigator`, `source_screener`,
5	`source_verifier`, `bibliography`, `claim_verifier`, `synthesizer`, `critic`,
6	`compiler`, `editor`, `ethics_reviewer`), both loops (evidence loop and
7	compile↔review loop), and its source discipline — with the agriculture
8	substitutions in
9	[`agri-research/references/agriculture-domain.md`](../agri-research/references/agriculture-domain.md).
10	Read that file first. No new machinery here.
11
12	## The substitutions
13	1. Persona — a senior agricultural scientist of the specific discipline;
14	name it and apply its standards (domain §2). `research_architect` designs the
15	method to that discipline's conventions.
16	2. Evidence base — `source_screener` ranks agriculture + multidisciplinary
17	literature: Tier 1 = Q1/Q2 of the seven agriculture categories
18	([`journals/_coverage_agriculture.md`](../journals/_coverage_agriculture.md)) +
19	Nature/Science/Cell/PNAS + Q1/Q2 adjacent disciplines; Tier 2 = Q3 for gaps;
20	Q4 avoided. FAO/USDA/CGIAR/EFSA and extension sources are evidence with a
21	source and date (domain §3).
22	3. Journal routing — `bibliography` and `compiler` format via `journal-selector`
23	using the agriculture coverage map (domain §4); APA 7.0 by default.
24
25	## Source discipline (inherited, non-negotiable)
26	Investigation and claim-checking operate only on validated sources — those that
27	passed `source_screener` (ranking) and `source_verifier` (existence, venue
28	legitimacy, retraction, predatory check). Every claim carries a source and locator;
29	inference is labelled as inference; `[EVIDENCE GAP]` rather than filling from memory.
30
31	## Agricultural rigour
32	Apply domain §5 — the `critic` should attack the usual agricultural weak points:
33	single site-year generalised to a recommendation, pseudoreplication (subsamples
34	treated as replicates), pot-to-field extrapolation, missing G×E, and causal language
35	unearned by the design.
36
37	## Inherited unchanged (not optional)
38	Four-gate citation verification (`scripts/verify_citations.py`), privacy scan,
39	`food-paper/references/human-writing.md`, and the mandatory AI-use disclosure.
40	Also the full-text-access first move — `food-deep-research`'s highlighted, one-time
41	request for the user's EndNote `.Data` folder / reference PDFs, and full-text
42	extraction via the ladder before the evidence loop
43	(`food-research/references/full-text-access.md`).

People who liked this also viewed

6 picks

Type

agri-deep-research

16stars1forks

View on GitHub

How to install agri-deep-research?

pangenomeai/academic-skills-food-nutrition/agri-deep-research

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Agri-Deep-Research — Source-Validated Reviews for Agricultural Science
2
3	Run the `food-deep-research` skill exactly — its 12-subagent team
4	(`research_scope`, `research_architect`, `investigator`, `source_screener`,
5	`source_verifier`, `bibliography`, `claim_verifier`, `synthesizer`, `critic`,
6	`compiler`, `editor`, `ethics_reviewer`), both loops (evidence loop and
7	compile↔review loop), and its source discipline — with the agriculture
8	substitutions in
9	[`agri-research/references/agriculture-domain.md`](../agri-research/references/agriculture-domain.md).
10	Read that file first. No new machinery here.
11
12	## The substitutions
13	1. Persona — a senior agricultural scientist of the specific discipline;
14	name it and apply its standards (domain §2). `research_architect` designs the
15	method to that discipline's conventions.
16	2. Evidence base — `source_screener` ranks agriculture + multidisciplinary
17	literature: Tier 1 = Q1/Q2 of the seven agriculture categories
18	([`journals/_coverage_agriculture.md`](../journals/_coverage_agriculture.md)) +
19	Nature/Science/Cell/PNAS + Q1/Q2 adjacent disciplines; Tier 2 = Q3 for gaps;
20	Q4 avoided. FAO/USDA/CGIAR/EFSA and extension sources are evidence with a
21	source and date (domain §3).
22	3. Journal routing — `bibliography` and `compiler` format via `journal-selector`
23	using the agriculture coverage map (domain §4); APA 7.0 by default.
24
25	## Source discipline (inherited, non-negotiable)
26	Investigation and claim-checking operate only on validated sources — those that
27	passed `source_screener` (ranking) and `source_verifier` (existence, venue
28	legitimacy, retraction, predatory check). Every claim carries a source and locator;
29	inference is labelled as inference; `[EVIDENCE GAP]` rather than filling from memory.
30
31	## Agricultural rigour
32	Apply domain §5 — the `critic` should attack the usual agricultural weak points:
33	single site-year generalised to a recommendation, pseudoreplication (subsamples
34	treated as replicates), pot-to-field extrapolation, missing G×E, and causal language
35	unearned by the design.
36
37	## Inherited unchanged (not optional)
38	Four-gate citation verification (`scripts/verify_citations.py`), privacy scan,
39	`food-paper/references/human-writing.md`, and the mandatory AI-use disclosure.
40	Also the full-text-access first move — `food-deep-research`'s highlighted, one-time
41	request for the user's EndNote `.Data` folder / reference PDFs, and full-text
42	extraction via the ladder before the evidence loop
43	(`food-research/references/full-text-access.md`).

People who liked this also viewed

6 picks

Type