$npx -y skills add PangenomeAI/academic-skills-food-nutrition --skill food-paperMulti-subagent manuscript system for food & nutrition science covering the whole research process: understand the field, frame research questions, curate and analyze data, run statistics, build figures and tables, construct the discussion, draft, polish, and self-review — journal
| 1 | # Food-Paper — Whole-Process Manuscript System for Food & Nutrition Science |
| 2 | |
| 3 | Take a food/nutrition study from data and idea to a submission-ready, journal- |
| 4 | formatted manuscript, using a team of subagents for each stage of the research |
| 5 | and writing process. Original work; architecture informed by open community |
| 6 | paper-writing and Nature-style skills (see the repo README Acknowledgements). |
| 7 | |
| 8 | ## First move — resolve the target journal (once) |
| 9 | Before drafting, load **`journal-selector/SKILL.md`** (a shared procedure, not an |
| 10 | installed skill) and follow it — it **asks the author which journal |
| 11 | they are targeting** (they may answer 'generic' for **APA 7.0** defaults). Do this |
| 12 | **once**: record the resolved journal and its constraints and reuse them for every |
| 13 | subagent and stage — do **not** ask again. Re-run `journal-selector` only if the |
| 14 | author asks to switch journals, or reuse the choice already resolved by |
| 15 | `food-pipeline`/an earlier turn. The constraints govern structure, word/abstract |
| 16 | limits, reference style, and the figure spec passed to `food-figure`. |
| 17 | |
| 18 | ## Modes |
| 19 | - **full** (default) — the whole pipeline: field → questions → data/stats → figures → argument → draft → polish → self-review. |
| 20 | - **plan** — Socratic planning of the paper chapter by chapter (no full draft). |
| 21 | - **outline** — detailed outline + evidence map only. |
| 22 | - **section** — draft or rewrite one section (intro/methods/results/discussion/abstract). |
| 23 | - **stats** — statistical analysis plan/execution guidance only. |
| 24 | - **revise** — revise against an existing review (a `food-review` report and/or margin comments on a Word file). Edit **the original `.docx` with Tracked Changes** (do not start a fresh copy), resolving each comment. **Inside `food-pipeline`:** update the existing **Review & Response Report (`.docx`)** in place with each item's response — **no separate response letter**. **Standalone** (real journal reviewers): produce a **point-by-point response letter as a new Word document**. All deliverables are `.docx`, never Markdown. See `references/revision-response.md`. |
| 25 | - **format-convert** — convert a draft to the target journal's structure + reference style; output **Markdown, LaTeX (.tex), or DOCX**, and **build a PDF** via Pandoc or `latexmk` (see `references/latex-guide.md`). Yes — this skill can prepare and edit LaTeX drafts. When the source is a Word file, **preserve EndNote/Zotero/Mendeley citation fields** (`references/word-field-codes.md`) — don't flatten field codes into text. |
| 26 | - **polish** — language editing to publication-quality English **and removal of AI writing tells** (`polisher` runs `references/human-writing.md`): inflated significance, "-ing" tack-ons, vague attribution ("studies have shown" → a real citation), stock AI vocabulary, "serves as" → "is", filler, hedge **stacking**, generic upbeat endings — then the two-pass check *"what still reads as machine-written?"*. Keeps calibrated hedging, passive Methods, and journal-mandated form; never changes a number, claim scope, or citation. Good for non-native-English drafts and for anything AI helped write. |
| 27 | |
| 28 | ## Subagent team (dispatch via the Agent tool; independent stages run in parallel) |
| 29 | | # | Subagent | Stage of the research process | |
| 30 | |---|---|---| |
| 31 | | 1 | |