Peer Review

Phase 2: Manuscript Analysis

1. Read the manuscript PDF thoroughly — Abstract, Methods, Results, Discussion, Tables, Figures.
2. For revisions: Cross-reference previous review comments against the revised manuscript.
3. Identify key issues using this systematic checklist:
   • Data splitting / leakage (patient-level vs image-level)
   • Reference standard validity
   • Validation strategy / confidence intervals / calibration
   • Clinical comparator / incremental value
   • Reproducibility (preprocessing, hyperparameters, segmentation)
   • Protocol heterogeneity
   • Intended use clarity
   • Overclaiming relative to evidence level
   • Sample size adequacy
   • Statistical methodology appropriateness
4. Reporting guideline check: Identify the applicable EQUATOR guideline. Flag MISSING items as candidate comments. If /check-reporting is available, delegate.
5. Prioritize: Rank issues by impact on validity. Select top 3-5 for Major, 3-4 for Minor.
6. Gate: Present findings to user — "Here are the key issues I found — do you agree with this prioritization?"

Phase 3: Draft Review

Generate {manuscript_id}_review_draft.md:

# {manuscript_id} — Review Draft

**Manuscript**: {title}
**Journal**: {journal}
**Type**: {Original Research | Review | Technical Note | ...}
**Recommendation**: {Major Revision | Minor Revision}

---

## {Journal-specific scores section, if applicable}

---

## CONFIDENTIAL COMMENTS TO THE EDITOR

{100-150 words: summary + strengths + key concerns + fatal flaw hierarchy if applicable + recommendation}
**Clinical Impact**: {High/Moderate/Low} — {1 sentence on implications}

---

## COMMENTS TO THE AUTHORS

**Research Summary & General Comments**

{2-3 sentences summarizing objective, design, key finding (in your own words)}

Major strengths:
1. {Specific strength}
2. {Specific strength}
3. {Specific strength (optional)}

{Scope + feasibility: 1-2 sentences — "I have suggestions focused on [areas]. Achievable within existing data."}

(80-150 words total)

**Major Comments**

1) **{Issue title}**

{Problem 1-2 sentences. Location cited.}

Suggested revisions:
- {Fix 1}
- {Fix 2}

2) **{Issue title}**
...

**Minor Comments**

1) {One sentence, location cited.}
2) ...

**Closing Remark**

{2-3 sentences, constructive.}

Conciseness targets:

• Author section: 500-800 words (max 1000)
• Major: 3-5 items, each 5-8 lines
• Minor: 3-4 items, each 1 sentence

Phase 4: Self-QC

After drafting, verify mechanically:

1. Numerical accuracy: All cited numbers (sample size, p-value, AUC) match the manuscript.
2. Citation accuracy: Section/Table/Figure references match manuscript.
3. Feasibility: All suggested revisions achievable with existing data.
4. Word count: Author section within 500-1000 words.
5. Forbidden words: No recommendation words (accept/reject/minor/major revision) in Comments to Authors.

Fix all issues found, then present to user.

Phase 5: Refinement

1. Present the draft to the user for review.
2. Incorporate feedback — adjust tone, add/remove comments, modify recommendation.
3. Generate {manuscript_id}_review_final.md — the polished version.
4. Generate {manuscript_id}_submission.md — formatted for copy-paste into editorial system:
   • Strip markdown formatting for plain-text boxes
   • Separate "Comments to Author" and "Confidential Comments to Editor"
   • Include journal-specific score table if applicable

Phase 6: Pre-Submission QC

• No recommendation words in Comments to Authors
• All cited numbers match the manuscript
• Major comments ranked by impact
• All suggestions feasible with existing data
• Author section within 500-1000 word range
• Fatal flaw hierarchy stated in Confidential Comments (if applicable)

Tone and Calibration

• Default: Developmental, constructive tone
• Escalate tone only when: clinical validity threatened, patient safety concern, severe data leakage, or reference standard fundamentally flawed
• Default recommendation: Major Revision (unless issues are purely reporting/clarity → Minor Revision)
• Fatal flaw signal: State in Confidential Comments which issue(s) represent fundamental design limitations, rather than recommending Reject directly

Signature Review Patterns

Recurring high-yield checks — apply to every manuscript:

1. Patient-level data splitting: Splitting at patient level, not image/exam level
2. Confidence intervals: All primary metrics should have 95% CIs
3. Intended use statement: Clinical workflow position and decision influenced should be clear
4. Calibration: AUC alone insufficient for prediction models — calibration metrics needed
5. Overclaiming: Language should match evidence level (CI overlap, small test sets, single-center)
6. Reproducibility: Preprocessing, hyperparameters, segmentation protocols reported

Journal-Specific Formatting

Radiology: AI (ScholarOne)

• Scores: Scientific Merit, Originality/Importance, Practical Value, Reader Interest, Overall (1-9)
• "Reject: Encourage major revision and resubmission" = Major Revision

Investigative Radiology (Editorial Manager)

• Scores: Interest (H/M/L), Innovation (H/M/L), Importance (H/M/L), Language editing (No minor/Yes major)

AJR (Editorial Manager)

• Section-by-section structure (Title → Abstract → Introduction → Methods → Results → Discussion → References → Tables → Figures)
• Continuous numbering across sections

Custom Journal

• If the journal is not listed above, use the generic format from Phase 3
• Ask the user if the journal has specific score requirements or formatting

Output Contract

Skill Interactions

What This Skill Does NOT Do

• Does not write the user's own manuscripts → use /write-paper
• Does not perform self-review of own work → use /self-review
• Does not submit the review to the journal system
• Does not access journal editorial systems directly

Anti-Hallucination

• Never fabricate manuscript content. All cited numbers, methods, and findings must come from the actual manuscript.
• Never invent journal scoring criteria. If uncertain about a journal's format, ask the user or use the generic format.
• Never generate references from memory. Use /search-lit if citations are needed for reviewer comments.
• If a reporting guideline item is uncertain, flag it as [CHECK] rather than asserting compliance.