agri-paper

Name: agri-paper
Author: PangenomeAI

16stars1forks

How to install agri-paper?

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

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

Installs into the current project.

Summary

Multi-subagent manuscript system for agricultural science, written as a senior agricultural scientist of the relevant discipline: understand the field, frame questions, curate data, run statistics, build figures and tables, construct the discussion, draft, polish, and self-review

Files · 1

View on GitHub

SKILL.md

1	# Agri-Paper — Manuscript System for Agricultural Science
2
3	Run the `food-paper` skill exactly — its 12 subagents (`intake`,
4	`literature_lead`, `question_framer`, `data_curator`, `statistician`,
5	`viz_designer`, `structure_architect`, `argument_builder`, `draft_writer`,
6	`polisher`, `citation_manager`, `internal_reviewer`), all modes (**full · plan ·
7	outline · section · stats · revise · format-convert · polish**), and its output
8	contracts — with the agriculture 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 write to its standards (domain §2).
15	2. Evidence base — `literature_lead` calls `agri-research` (not
16	`food-research`); `citation_manager` prefers Tier 1 agriculture +
17	multidisciplinary sources, Q4 avoided (domain §3).
18	3. Journal routing — resolve the target journal once via `journal-selector`
19	using the agriculture coverage map (domain §4); APA 7.0 if 'generic'.
20
21	Figures still route through `food-figure` at the journal spec — it is
22	domain-neutral (bar/box, dose–response, kinetics, PCA, heatmaps, forest plots all
23	apply to agricultural data). Revision still follows
24	`food-paper/references/revision-response.md`; peer review calls `agri-review`.
25
26	## Agricultural reporting (domain §5) — enforce in Methods and Results
27	- Field trials: site (coordinates), season(s)/years, soil type and
28	classification, cultivar/genotype, plot size, design (RCBD/split-plot/Latin
29	square) and replication, agronomic management, and the statistical model.
30	- The experimental unit stated explicitly — plot/pen, not plant/animal;
31	subsamples are not replicates (pseudoreplication is the classic reviewer kill).
32	- G×E and season-to-season variation addressed, or the limitation stated; a
33	single site-year does not support a general recommendation.
34	- Animal work: ethics approval + ARRIVE; housing, diet composition, unit.
35	- Soil work: sampling depth/strategy, bulk density, method, equivalent-soil-mass
36	basis where stocks are claimed.
37	- Units: SI; yield t/ha with moisture basis; nutrient rates kg/ha; mean ± SD/SEM
38	with n and the test.
39
40	## Inherited unchanged (not optional)
41	Anti-fabrication grounding + four-gate citations (`scripts/verify_citations.py`),
42	`word-field-codes.md` (never flatten EndNote/Zotero fields), privacy scan,
43	`human-writing.md` (write like a scientist, not a chatbot), and the **mandatory
44	AI-use disclosure** in Acknowledgements.

People who liked this also viewed

6 picks

Type

agri-paper

16stars1forks

View on GitHub

How to install agri-paper?

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

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Agri-Paper — Manuscript System for Agricultural Science
2
3	Run the `food-paper` skill exactly — its 12 subagents (`intake`,
4	`literature_lead`, `question_framer`, `data_curator`, `statistician`,
5	`viz_designer`, `structure_architect`, `argument_builder`, `draft_writer`,
6	`polisher`, `citation_manager`, `internal_reviewer`), all modes (**full · plan ·
7	outline · section · stats · revise · format-convert · polish**), and its output
8	contracts — with the agriculture 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 write to its standards (domain §2).
15	2. Evidence base — `literature_lead` calls `agri-research` (not
16	`food-research`); `citation_manager` prefers Tier 1 agriculture +
17	multidisciplinary sources, Q4 avoided (domain §3).
18	3. Journal routing — resolve the target journal once via `journal-selector`
19	using the agriculture coverage map (domain §4); APA 7.0 if 'generic'.
20
21	Figures still route through `food-figure` at the journal spec — it is
22	domain-neutral (bar/box, dose–response, kinetics, PCA, heatmaps, forest plots all
23	apply to agricultural data). Revision still follows
24	`food-paper/references/revision-response.md`; peer review calls `agri-review`.
25
26	## Agricultural reporting (domain §5) — enforce in Methods and Results
27	- Field trials: site (coordinates), season(s)/years, soil type and
28	classification, cultivar/genotype, plot size, design (RCBD/split-plot/Latin
29	square) and replication, agronomic management, and the statistical model.
30	- The experimental unit stated explicitly — plot/pen, not plant/animal;
31	subsamples are not replicates (pseudoreplication is the classic reviewer kill).
32	- G×E and season-to-season variation addressed, or the limitation stated; a
33	single site-year does not support a general recommendation.
34	- Animal work: ethics approval + ARRIVE; housing, diet composition, unit.
35	- Soil work: sampling depth/strategy, bulk density, method, equivalent-soil-mass
36	basis where stocks are claimed.
37	- Units: SI; yield t/ha with moisture basis; nutrient rates kg/ha; mean ± SD/SEM
38	with n and the test.
39
40	## Inherited unchanged (not optional)
41	Anti-fabrication grounding + four-gate citations (`scripts/verify_citations.py`),
42	`word-field-codes.md` (never flatten EndNote/Zotero fields), privacy scan,
43	`human-writing.md` (write like a scientist, not a chatbot), and the **mandatory
44	AI-use disclosure** in Acknowledgements.

People who liked this also viewed

6 picks

Type