$npx -y skills add PangenomeAI/academic-skills-food-nutrition --skill agri-researchRun a comprehensive, multi-source literature and evidence-synthesis workflow for agricultural science, as a senior agricultural scientist of the relevant discipline (agronomy, soil science, horticulture, dairy and animal science, agricultural engineering, or agricultural economic
| 1 | # Agri-Research — Evidence Synthesis for Agricultural Science |
| 2 | |
| 3 | **Run the `food-research` skill exactly** — its streams, subagents |
| 4 | (`search_strategist`, `source_scout`, `screener_appraiser`, `journal_ranker`, |
| 5 | `synthesis`, `writer`, `reviewer`, and the full `systematic_reviewer` PRISMA/OHAT |
| 6 | pipeline), gates, and output contracts — with the agriculture substitutions in |
| 7 | [`references/agriculture-domain.md`](references/agriculture-domain.md). Read that |
| 8 | file first. This skill adds no new machinery; it changes **who is working, on what |
| 9 | evidence, for which journal**. |
| 10 | |
| 11 | ## The substitutions |
| 12 | 1. **Persona** — a **senior agricultural scientist of the specific discipline** |
| 13 | (agronomy · soil science · horticulture · dairy & animal science · agricultural |
| 14 | engineering · agricultural economics & policy · agriculture multidisciplinary). |
| 15 | Name the discipline and apply its standards (domain §2). |
| 16 | 2. **Evidence base** — agriculture + multidisciplinary literature, ranked by |
| 17 | `journal_ranker`: **Tier 1** = Q1/Q2 of the seven agriculture categories |
| 18 | ([`journals/_coverage_agriculture.md`](../journals/_coverage_agriculture.md), 230 |
| 19 | journals) + Nature/Science/Cell/PNAS + Q1/Q2 of adjacent disciplines; **Tier 2** = |
| 20 | Q3 for gaps only; **Q4 avoided**. Authoritative non-journal sources (FAO, USDA, |
| 21 | CGIAR, EFSA, extension services) count as evidence with a source and date |
| 22 | (domain §3). |
| 23 | 3. **Journal routing** — via `journal-selector`, using the agriculture coverage map |
| 24 | (domain §4). |
| 25 | |
| 26 | ## Streams (as `food-research`) |
| 27 | - **quick brief** — fast orientation; Tier 1 only. |
| 28 | - **full review** — the default: four-layer search → two-phase screening → synthesis |
| 29 | → manuscript → `reviewer` loop → Word `.docx`. |
| 30 | - **deep research** — calls **`agri-deep-research`** (not `food-deep-research`). |
| 31 | - **systematic** — full PRISMA + OHAT pipeline; **inclusion by pre-specified |
| 32 | eligibility, never journal ranking**. |
| 33 | |
| 34 | ## Agricultural rigour |
| 35 | Apply domain §5 throughout — field-trial reporting (site, season/years, soil, |
| 36 | cultivar, design, replication), **the experimental unit** (plot/pen, not plant/animal |
| 37 | — pseudoreplication is the classic error), G×E and season-to-season variation, ARRIVE |
| 38 | for animal work, and no extrapolation from pot to field or region to region. |
| 39 | |
| 40 | ## Inherited unchanged (not optional) |
| 41 | Anti-fabrication grounding and the four-gate citation check |
| 42 | (`scripts/verify_citations.py`), the privacy scan, `journal-selector`'s ask-once |
| 43 | contract, `food-paper/references/human-writing.md`, and the **mandatory AI-use |
| 44 | disclosure** in every written output. Also the **full-text-access first move** — |
| 45 | `food-research`'s highlighted, one-time request for the user's EndNote `.Data` folder |
| 46 | / reference PDFs, and full-text extraction via the ladder before synthesis |
| 47 | (`food-research/references/full-text-access.md`). |