AgentStack
SKILL verified MIT Self-run

Food Review

skill-pangenomeai-academic-skills-food-nutrition-food-review · by PangenomeAI

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 target journal (APA 7.0 by default, or a specific journal via journal-selector). Use for pre-submission review, reviewer r…

No reviews yet
0 installs
10 views
0.0% view→install

Install

$ agentstack add skill-pangenomeai-academic-skills-food-nutrition-food-review

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Food Review? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Food-Review — Multi-Reviewer Peer Review for Food & Nutrition Manuscripts

Give the author the review a good food-science journal would return, from a panel rather than a single voice. Original work; architecture informed by open community peer-review skills (see the repo README Acknowledgements).

Modes

  • full (default) — the whole panel: three domain reviewers + devil's advocate + format check, synthesized by the coordinator into an editorial decision.
  • quick — coordinator + one blended reviewer pass; a fast readiness verdict.
  • methodology — deep dive by reviewer_methodology only.
  • re-review — re-assess a revised manuscript against the prior reports and the author's response, verifying each point was addressed.

Panel (dispatch via the Agent tool; reviewers run in parallel)

  1. review_coordinator (editor-in-chief) — sets the target journal + scope, dispatches the reviewers, synthesizes their reports, resolves disagreement, and issues the decision.
  2. reviewer_methodology — design, statistics, reproducibility, validation.
  3. reviewer_domain — novelty, significance, scope fit, domain correctness (food/nutrition science).
  4. reviewer_integrity — data & citation integrity, food-safety/ethics, reporting completeness.
  5. devils_advocate — adversarial challenge to the paper's central claim.
  6. format_checker — formatting & reference-style compliance vs the target journal.

Workflow

flowchart TD
    A[Manuscript in] --> B[review_coordinatorresolve target journal + scope]
    B --> J{Target journal?}
    J -- named --> JS[journal-selectorload journal requirements]
    J -- none --> AP[default: APA 7.0]
    B --> R1[reviewer_methodology]
    B --> R2[reviewer_domain]
    B --> R3[reviewer_integrity]
    B --> R4[devils_advocate]
    JS --> FC[format_checker]
    AP --> FC
    R1 --> C[review_coordinatorsynthesize + decision]
    R2 --> C
    R3 --> C
    R4 --> C
    FC --> C
    C --> O[Panel report:per-reviewer reports + format check +editorial decision + revision checklist +response-letter skeleton]

Formatting / target journal

The review_coordinator first establishes the target journal. If the user names one, it calls the journal-selector skill to load that journal's structure, limits, and reference/citation style; format_checker then audits the manuscript against those requirements. If no journal is named, APA 7.0 is the default standard for the formatting check.

Output

A consolidated panel report: each reviewer's report (strengths → major → minor, each concern actionable), the devil's advocate challenge, the formatting compliance report, and the coordinator's editorial decision (Accept / Minor / Major / Reject) with a prioritized revision checklist and a response-letter skeleton the author can fill in. Critique the work, not the author.

References (load as needed)

  • references/review-criteria.md — what each reviewer checks (food-tuned).
  • references/quality-rubrics.md — 1–5 scoring per dimension + weights.
  • references/editorial-decisions.mdreview_coordinator: Accept/Minor/Major/Reject logic + overrides.
  • references/ethics-integrity-checklist.mdreviewer_integrity (canonical; shared with deep-research).
  • food-paper/references/statistics-reporting.mdreviewer_methodology: stats red flags.

Handoff

Feeds food-paper (revise mode) for the author to act on; part of the food-pipeline review→revise loop.

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Versions

  • v0.1.0 Imported from the upstream source.