food-review

Name: food-review
Author: PangenomeAI

16stars1forks

How to install food-review?

pangenomeai/academic-skills-food-nutrition/food-review

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

Installs into the current project.

Summary

Multi-reviewer peer-review system for food & nutrition manuscripts. Simulates an editorial panel — a coordinating editor, three domain reviewers (methodology/statistics, domain/novelty, integrity/ethics), and a devil's advocate — plus a formatting-compliance check against the tar

Files · 1

View on GitHub

SKILL.md

1	# Food-Review — Multi-Reviewer Peer Review for Food & Nutrition Manuscripts
2
3	Give the author the review a good food-science journal would return, from a
4	panel rather than a single voice. Original work; architecture informed by open
5	community peer-review skills (see the repo README Acknowledgements).
6
7	## Modes
8	- full (default) — the whole panel: three domain reviewers + devil's advocate + format check, synthesized by the coordinator into an editorial decision.
9	- quick — coordinator + one blended reviewer pass; a fast readiness verdict.
10	- methodology — deep dive by `reviewer_methodology` only.
11	- re-review — re-assess a revised manuscript against the prior reports and the author's response, verifying each point was addressed.
12
13	## Panel (dispatch via the Agent tool; reviewers run in parallel)
14	1. `review_coordinator` (editor-in-chief) — sets the target journal + scope, dispatches `knowledge_builder`, then the reviewers, synthesizes their reports, resolves disagreement, and issues the decision.
15	2. `knowledge_builder` — runs first: reads the manuscript's cited sources (Pathway A) and the field's key literature (Pathway B) into a shared knowledge base so the panel judges the science from knowledge, not impression.
16	3. `reviewer_methodology` — design, statistics, reproducibility, validation.
17	4. `reviewer_domain` — novelty, significance, scope fit, domain correctness (food/nutrition science).
18	5. `reviewer_integrity` — data & citation integrity, food-safety/ethics, reporting completeness.
19	6. `devils_advocate` — adversarial challenge to the paper's central claim.
20	7. `format_checker` — formatting & reference-style compliance vs the target journal.
21
22	## Ground the panel first — the knowledge base
23	Reviewers must understand the topic and its background before they critique it.
24	`knowledge_builder` runs before the reviewers and builds one knowledge base from:
25	- A — the manuscript's own citations: retrieve and **read the full cited
26	articles**, extract what each actually shows, and audit whether it supports the
27	claim it is attached to.
28	- B — the field's key literature: extract the manuscript's **keywords and
29	research disciplines**, search the literature for the field's key work
30	(may use the `food-research` `full review` branch for discovery/screening —
31	but knowledge extraction only, no literature-review article).
32
33	A + B give the panel the state of the art, standard methods and benchmark values,
34	consensus vs contested points, a novelty map, and gaps — so novelty and correctness
35	are judged, not guessed. Never summarize a source that was not retrieved; mark
36	abstract-only and unretrievable items. In quick mode, build a light version
37	(Pathway A spot-checks on the load-bearing citations).
38
39	Inside `food-pipeline` (Stage 1 already ran): don't search the field twice —
40	reuse the Stage-1 evidence base in place of the Pathway-B search, topped up with
41	`food-research` quick brief to find the field's key review publications and
42	read them in full; knowledge base = Stage-1 knowledge + key-review knowledge
43	(Pathway A still runs). Standalone `food-review` is unaffected and always builds
44	the full A + B.
45
46	## Workflow
47
48	```mermaid
49	flowchart TD
50	A[Manuscript in] --> B[review_coordinator<br/>resolve target journal + scope]
51	B --> JS[journal-selector<br/>ask once → journal or 'generic'/APA 7.0]
52	B --> KB[knowledge_builder<br/>A: read cited sources<br/>B: key field literature]
53	KB --> KBase[(Knowledge base<br/>state of the art · benchmarks ·<br/>novelty map · cited-source audit)]
54	KBase --> R1[r

People who liked this also viewed

6 picks

Type

food-review

16stars1forks

View on GitHub

How to install food-review?

pangenomeai/academic-skills-food-nutrition/food-review

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

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Food-Review — Multi-Reviewer Peer Review for Food & Nutrition Manuscripts
2
3	Give the author the review a good food-science journal would return, from a
4	panel rather than a single voice. Original work; architecture informed by open
5	community peer-review skills (see the repo README Acknowledgements).
6
7	## Modes
8	- full (default) — the whole panel: three domain reviewers + devil's advocate + format check, synthesized by the coordinator into an editorial decision.
9	- quick — coordinator + one blended reviewer pass; a fast readiness verdict.
10	- methodology — deep dive by `reviewer_methodology` only.
11	- re-review — re-assess a revised manuscript against the prior reports and the author's response, verifying each point was addressed.
12
13	## Panel (dispatch via the Agent tool; reviewers run in parallel)
14	1. `review_coordinator` (editor-in-chief) — sets the target journal + scope, dispatches `knowledge_builder`, then the reviewers, synthesizes their reports, resolves disagreement, and issues the decision.
15	2. `knowledge_builder` — runs first: reads the manuscript's cited sources (Pathway A) and the field's key literature (Pathway B) into a shared knowledge base so the panel judges the science from knowledge, not impression.
16	3. `reviewer_methodology` — design, statistics, reproducibility, validation.
17	4. `reviewer_domain` — novelty, significance, scope fit, domain correctness (food/nutrition science).
18	5. `reviewer_integrity` — data & citation integrity, food-safety/ethics, reporting completeness.
19	6. `devils_advocate` — adversarial challenge to the paper's central claim.
20	7. `format_checker` — formatting & reference-style compliance vs the target journal.
21
22	## Ground the panel first — the knowledge base
23	Reviewers must understand the topic and its background before they critique it.
24	`knowledge_builder` runs before the reviewers and builds one knowledge base from:
25	- A — the manuscript's own citations: retrieve and **read the full cited
26	articles**, extract what each actually shows, and audit whether it supports the
27	claim it is attached to.
28	- B — the field's key literature: extract the manuscript's **keywords and
29	research disciplines**, search the literature for the field's key work
30	(may use the `food-research` `full review` branch for discovery/screening —
31	but knowledge extraction only, no literature-review article).
32
33	A + B give the panel the state of the art, standard methods and benchmark values,
34	consensus vs contested points, a novelty map, and gaps — so novelty and correctness
35	are judged, not guessed. Never summarize a source that was not retrieved; mark
36	abstract-only and unretrievable items. In quick mode, build a light version
37	(Pathway A spot-checks on the load-bearing citations).
38
39	Inside `food-pipeline` (Stage 1 already ran): don't search the field twice —
40	reuse the Stage-1 evidence base in place of the Pathway-B search, topped up with
41	`food-research` quick brief to find the field's key review publications and
42	read them in full; knowledge base = Stage-1 knowledge + key-review knowledge
43	(Pathway A still runs). Standalone `food-review` is unaffected and always builds
44	the full A + B.
45
46	## Workflow
47
48	```mermaid
49	flowchart TD
50	A[Manuscript in] --> B[review_coordinator<br/>resolve target journal + scope]
51	B --> JS[journal-selector<br/>ask once → journal or 'generic'/APA 7.0]
52	B --> KB[knowledge_builder<br/>A: read cited sources<br/>B: key field literature]
53	KB --> KBase[(Knowledge base<br/>state of the art · benchmarks ·<br/>novelty map · cited-source audit)]
54	KBase --> R1[r

People who liked this also viewed

6 picks

Type