Food-Proposal — Research & Funding Proposal Orchestrator
The proposal counterpart of food-pipeline. It does not research, write, or review
itself — it routes the proposal to the specialist skills and enforces the target
funding scheme's format, length limit, and assessment criteria at every gate.
Original work; the orchestration mirrors food-pipeline.
Scheme first — the key difference from a paper
A proposal is written to a funding scheme's format, the way a manuscript is written
to a journal's. Before anything else, resolve the target scheme
(references/scheme-selection.md): ask the user which scheme, then load its spec from
schemes/<id>.md + schemes/schemes.json (required headings in order, page/word limit,
font, assessment criteria). Built-in: arc-discovery-eoi, arc-discovery-full,
uom-major-minor-project (see schemes/INDEX.md). If the scheme isn't built in,
don't guess — ask the user to upload the scheme's guideline / sample form and run
scheme_extractor to capture its format into a new schemes/<id>.md + schemes.json
entry. Every scheme carries a length limit — enforce it with
scripts/proposal_wordcount.py.
Own subagents
proposal_router — reads what the user has (topic only, or an existing draft),
resolves the scheme, picks the entry stage, and assembles each downstream skill's
input. Mirrors food-pipeline's intake router.
scheme_extractor — when the scheme isn't built in, extracts its format
(headings, order, limits, font, criteria) from the user's uploaded guideline/sample
into a new scheme spec.
compliance_gate — the checkpoint between stages: verifies required headings are
present and in order, the length limit is met (proposal_wordcount.py), the font/
format matches, and the content addresses every assessment criterion.
Stages
| Stage |
Skill / agent |
Deliverable |
Gate |
| 0 · SCHEME |
proposal_router + scheme resolution |
Target scheme spec (headings, limit, criteria) |
— |
| 1 · RESEARCH |
food-deep-research (or agri-deep-research; food-research) |
Knowledge base / evidence for the case |
evidence sufficiency |
| 2 · DRAFT |
food-paper (or agri-paper) writing to the scheme's headings |
Proposal draft in the scheme format |
compliance_gate: headings + length + criteria |
| 3 · REVIEW |
food-review (or agri-review) as a mock funding panel vs the criteria |
Review report + editorial decision |
mandatory author decision |
| 4 · REVISE |
food-paper (revise) |
Revised proposal (tracked changes; original Word opt-in) |
issues resolved + still within limit |
| 5 · FINALIZE |
food-paper (format-convert) |
Submission-ready proposal (.docx/PDF) to scheme format |
final compliance |
Slides? For a proposal pitch, food-ppt can turn the finished proposal into a deck.
From scratch vs revising an existing draft
- From scratch: run Stage 1 → 2 → 3, exactly as
food-pipeline builds a paper, but
to the scheme's headings and limit.
- Revising a draft (has one already): understand the field first (a
food-research
quick brief / reuse of any provided library, as food-pipeline does before editing),
then edit to fix gaps and fit the scheme — never rewrite blindly.
Inherited (not optional)
Anti-fabrication grounding + four-gate citations, privacy scan, academic style +
human-writing.md, the mandatory AI-use disclosure (some schemes, e.g. the UoM
project, require stating the AI model and prompts used — put it in Acknowledgements),
and the full-text-access first move for the research stage. Figures via food-figure.
1---2name: food-proposal3description: Master orchestrator for preparing research proposals and funding-application proposals in food, nutrition & agricultural science. Like food-pipeline, but for proposals: it resolves the target funding scheme's format first (headings, order, page/word limit, font, assessment criteria), then drafts from scratch (food-deep-research for the knowledge base, food-paper to write, food-review to review) or revises an existing draft after first understanding the field. Enforces the scheme's length limit and required headings and aligns content to the assessment criteria. Built-in schemes: ARC Discovery EOI, ARC Discovery Full Application, and the UoM Ag & Food project proposal; if a scheme isn't included it asks the user to upload the guideline and extracts the format. Triggers: write a grant proposal, ARC Discovery application, funding application, research proposal, project proposal, revise my grant, prepare an EOI.4---56# Food-Proposal — Research & Funding Proposal Orchestrator78The proposal counterpart of `food-pipeline`. It does not research, write, or review9itself — it **routes the proposal to the specialist skills** and enforces the target10funding scheme's **format, length limit, and assessment criteria** at every gate.11Original work; the orchestration mirrors `food-pipeline`.1213## Scheme first — the key difference from a paper14A proposal is written to a **funding scheme's format**, the way a manuscript is written15to a journal's. **Before anything else, resolve the target scheme**16(`references/scheme-selection.md`): ask the user which scheme, then load its spec from17`schemes/<id>.md` + `schemes/schemes.json` (required headings in order, page/word limit,18font, assessment criteria). **Built-in:** `arc-discovery-eoi`, `arc-discovery-full`,19`uom-major-minor-project` (see `schemes/INDEX.md`). **If the scheme isn't built in,20don't guess** — ask the user to upload the scheme's guideline / sample form and run21`scheme_extractor` to capture its format into a new `schemes/<id>.md` + `schemes.json`22entry. Every scheme carries a **length limit** — enforce it with23`scripts/proposal_wordcount.py`.2425## Own subagents26- **`proposal_router`** — reads what the user has (topic only, or an existing draft),27 resolves the scheme, picks the entry stage, and assembles each downstream skill's28 input. Mirrors `food-pipeline`'s intake router.29- **`scheme_extractor`** — when the scheme isn't built in, extracts its format30 (headings, order, limits, font, criteria) from the user's uploaded guideline/sample31 into a new scheme spec.32- **`compliance_gate`** — the checkpoint between stages: verifies required headings are33 present and in order, the **length limit** is met (`proposal_wordcount.py`), the font/34 format matches, and the content **addresses every assessment criterion**.3536## Stages37| Stage | Skill / agent | Deliverable | Gate |38|---|---|---|---|39| 0 · SCHEME | `proposal_router` + scheme resolution | Target scheme spec (headings, limit, criteria) | — |40| 1 · RESEARCH | `food-deep-research` (or `agri-deep-research`; `food-research`) | Knowledge base / evidence for the case | evidence sufficiency |41| 2 · DRAFT | `food-paper` (or `agri-paper`) writing to the scheme's headings | Proposal draft in the scheme format | `compliance_gate`: headings + **length** + criteria |42| 3 · REVIEW | `food-review` (or `agri-review`) as a mock funding panel vs the criteria | Review report + editorial decision | **mandatory** author decision |43| 4 · REVISE | `food-paper` (revise) | Revised proposal (tracked changes; original Word opt-in) | issues resolved + still within limit |44| 5 · FINALIZE | `food-paper` (format-convert) | Submission-ready proposal (`.docx`/PDF) to scheme format | final compliance |4546**Slides?** For a proposal pitch, `food-ppt` can turn the finished proposal into a deck.4748## From scratch vs revising an existing draft49- **From scratch:** run Stage 1 → 2 → 3, exactly as `food-pipeline` builds a paper, but50 to the scheme's headings and limit.51- **Revising a draft (has one already):** understand the field first (a `food-research`52 quick brief / reuse of any provided library, as `food-pipeline` does before editing),53 then edit to fix gaps and **fit the scheme** — never rewrite blindly.5455## Inherited (not optional)56Anti-fabrication grounding + four-gate citations, privacy scan, academic style +57`human-writing.md`, the **mandatory AI-use disclosure** (some schemes, e.g. the UoM58project, require stating the AI model and prompts used — put it in Acknowledgements),59and the full-text-access first move for the research stage. Figures via `food-figure`.