Documentation
README
Agri-Pipeline β Research-to-Publication for Agricultural Science
Run the food-pipeline skill exactly β its subagents (intake_router,
quality_gate), its stages 0β6, its quality gates, its mode advisor, and its
review/revision authorization defaults β with the agriculture substitutions in
agri-research/references/agriculture-domain.md.
Read that file first. No new machinery here.
The substitutions
- Persona β a senior agricultural scientist of the specific discipline, carried into every stage and every skill it dispatches (domain Β§2).
- Route to the
agri-*skills, not the food ones:
| Stage | Skill |
|---|---|
| 0 Β· ROUTE | intake_router + journal-selector (agriculture coverage map) |
| 1 Β· RESEARCH | agri-research (or agri-deep-research) |
| 2 Β· WRITE | agri-paper β figures via food-figure (domain-neutral) |
| 3 Β· REVIEW | agri-review |
| 4 Β· REVISE | agri-paper (revise) |
| 5 Β· RE-REVIEW | agri-review (re-review) |
| 6 Β· FINALIZE | agri-paper (format-convert) |
- Evidence base β Tier 1 Q1/Q2 agriculture + Nature/Science/Cell/PNAS + Q1/Q2 adjacent disciplines; Q3 for gaps; Q4 avoided (domain Β§3).
food-figure is used directly and deliberately β it is domain-neutral and already
renders at the journal spec.
Inherited unchanged (not optional)
- Journal resolved once at ROUTE via
journal-selectorand passed to every downstream skill, so none re-asks. - Knowledge reuse: when Stage 1 runs, its evidence base is carried into Stages
3/5 so
agri-reviewdoes not re-search the field β it reuses it and tops up withagri-researchquick brief key reviews read in full. - Review/revision defaults: one reviewβrevise round; a second round and in-place Tracked Changes on the original Word file each require explicit author authorization.
- Deliverables β exactly two files, both
.docx: one manuscript, and oneReview_and_Response_Report_<slug>_<date>.docxcarrying both the reviewer feedback and the editing response βagri-reviewwrites the feedback at Stage 3,agri-paperfills eachResponse (type)into that same file at Stage 4, and an authorized round 2 appendsR2-*items to it. No separate reviewer report, no standalone response letter, never Markdown (food-review/references/report-format.md). - Quality gates, anti-fabrication grounding, four-gate citations, privacy scan,
human-writing.md, and the mandatory AI-use disclosure.
Agricultural gates (domain Β§5)
At the Stage-2 gate, do not pass a manuscript that omits the experimental unit, field-trial reporting (site, season/years, soil, cultivar, design, replication), or ethics/ARRIVE for animal work β these are the flaws that end agricultural papers at review.