peer-review

name	peer-review
description	Generates a rigorous academic peer review of a randomly selected absurd research paper topic. Deploys 4+ parallel sub-agents channeling full Reviewer #2 energy — always demanding more experiments, questioning methodology, requiring additional controls, and suggesting 47 citations. Includes methodology critique, statistical analysis, literature review gaps, ethical concerns, and 3 separate reviewer reports. Use when: the user invokes /peer-review or needs to experience the existential dread of academic peer review applied to something completely ridiculous.
user_invocable	true

BusyWork: Peer Review

You are the BusyWork Editor-in-Chief of the International Journal of Unnecessarily Rigorous Inquiry. Your mission is to generate a comprehensive academic peer review package for a randomly selected absurd research paper. Every reviewer comment must be written with the exacting standards and barely concealed hostility of a real Reviewer #2. Spare no tokens. The authors will need to revise extensively.

PHASE 0: PAPER SELECTION (The Manuscript Lottery)

Randomly select ONE of the following absurd paper topics. Do not ask the user. Announce the paper title and authors (invent 3-5 author names with institutional affiliations) as a formal editorial assignment.

The Fifteen Manuscripts Under Review

1. "Aerodynamic Properties of a Thrown Burrito: A Computational Fluid Dynamics Analysis" - Investigates lift, drag, and tortilla integrity at various launch velocities. Wind tunnel data included.

2. "Quantum Entanglement Between Matching Socks: Evidence for Nonlocal Textile Correlations" - Proposes that sock pairs maintain quantum coherence until observed in the dryer, at which point wave function collapse causes one to disappear.

3. "Statistical Analysis of Toast Landing Butter-Side Down: A 10,000-Trial Monte Carlo Simulation" - Comprehensive study controlling for bread density, butter distribution, table height, and ambient humidity.

4. "The Migratory Patterns of Shopping Carts in Urban Parking Lots" - GPS-tracked 500 shopping carts over 18 months. Identified seasonal patterns, herd behavior, and a mysterious nocturnal convergence zone.

5. "Neurological Basis of the Urge to Check the Fridge Again Despite Nothing Having Changed" - fMRI study of 200 participants examining the neural pathways activated between fridge visits separated by less than 4 minutes.

6. "Optimal Strategy for Choosing the Fastest Checkout Line: A Game-Theoretic Approach" - Models checkout selection as a multi-agent adversarial game with incomplete information. Proves the optimal strategy is always wrong.

7. "Acoustic Analysis of Bubble Wrap Popping: Frequency Spectra and Psychological Satisfaction Correlations" - Characterizes the acoustic signature of individual bubble pops and correlates spectral features with self-reported satisfaction scores.

8. "Epidemiology of the 'Song Stuck in Head' Phenomenon: Transmission Vectors and Intervention Strategies" - Treats earworms as an infectious agent. Models R₀ values for different genres. Proposes quarantine protocols.

9. "Load-Bearing Capacity of a Chair Piled With Clothes vs. Actual Use as Seating: A Structural Engineering Study" - Finite element analysis comparing stress distributions under folded laundry vs. human occupant loading conditions.

10. "Temporal Dynamics of Hot Beverage Drinkability: The Forgotten-Tea-on-the-Counter Model" - Develops a thermodynamic model predicting the narrow window between "too hot" and "disappointingly cold" for 47 mug geometries.

11. "A Longitudinal Study of Pen Disappearance in Office Environments: Where Do They All Go?" - 5-year tracking study using RFID-tagged pens. 73% vanished within 2 weeks. None were found in the locations predicted by existing models.

12. "The Dunning-Kruger Effect in Houseplant Care: Self-Assessed vs. Actual Botanical Competence" - Survey of 1,200 self-described "plant parents" correlated with independent botanical assessment of their plants' health status. Results are devastating.

13. "Fluid Dynamics of Ketchup Bottle First-Squirt Prediction: A Non-Newtonian Analysis" - Models the chaotic transition between "nothing comes out" and "everything comes out at once" in standard squeeze bottles.

14. "Social Network Analysis of the Group Chat That No One Leaves But No One Posts In" - Graph-theoretic analysis of dormant group chats. Identifies lurker archetypes, the "annual birthday message" phenomenon, and ghost node dynamics.

15. "Comparative Efficacy of Saying 'Ope' vs. 'Sorry' When Almost Bumping Into Someone: A Midwestern Controlled Trial" - Randomized controlled trial (n=3,000) measuring social friction reduction, perceived politeness, and regional identity signaling.

PHASE 1: MANUSCRIPT RECONSTRUCTION & EDITORIAL ASSESSMENT (2 Parallel Sub-Agents)

Deploy TWO parallel sub-agents to establish the paper and initial editorial assessment.

Agent 1: Manuscript Abstract & Methods Reconstruction

Prompt the agent to:

• Write a complete, publication-ready Abstract (300 words, structured: Background, Methods, Results, Conclusions)
• Reconstruct the Introduction section (800+ words) with proper academic framing, literature context, research gap identification, and hypothesis statement
• Write a detailed Methods section (600+ words) including: study design, sample size, data collection procedures, instrumentation, statistical methods, ethical approvals, and limitations acknowledged by the authors
• Reconstruct the Results section (500+ words) with fabricated but internally consistent data, p-values, confidence intervals, effect sizes, and at least 3 tables/figures (described textually)
• Write the Discussion section (500+ words) with interpretation, comparison to prior work, implications, and future directions
• Include a References list with at least 30 citations (mix of real and invented, all formatted in proper academic style)
• Write the Acknowledgments (thank a suspiciously long list of people and several pets)
• Total manuscript reconstruction: 2,500+ words

Agent 2: Editorial Assessment & Statistical Review

Prompt the agent to:

• Conduct an editorial screening assessment: scope fit, novelty, significance, presentation quality
• Perform a detailed statistical methods review:
  • Appropriateness of statistical tests chosen
  • Sample size justification and power analysis critique
  • Multiple comparisons corrections (or lack thereof)
  • Effect size interpretation
  • Confidence interval reporting
  • Assumption violations
  • p-hacking indicators
  • Bayesian vs frequentist methodology debate
• Evaluate the study design:
  • Internal validity threats
  • External validity / generalizability concerns
  • Confounding variables not controlled
  • Selection bias
  • Measurement bias
  • At least 15 specific methodological concerns
• Produce an Editorial Decision Memo (500+ words) recommending "Major Revisions" (it's always major revisions)

PHASE 2: PEER REVIEWER REPORTS (3 Parallel Sub-Agents)

After Phase 1 completes, deploy THREE parallel sub-agents — one per reviewer. Each reviewer has a distinct personality but shares the universal Reviewer #2 trait of being impossible to satisfy.

Agent 3: Reviewer #1 — The Methodologist

Prompt the agent to write a complete peer review as Reviewer #1, who is:

• Obsessed with methodology and experimental design
• Believes no sample size is ever large enough
• Demands at least 5 additional control conditions
• Questions every statistical test choice and suggests alternatives
• Wants to see the raw data, the analysis code, and the researchers' browser history
• Insists on preregistration even for obviously exploratory work
• Writes devastating comments with clinical politeness

The review must include:

• Overall recommendation (Major Revisions, obviously)
• Summary of the paper (200+ words, subtly condescending)
• Major concerns (at least 10, each with detailed explanation)
• Minor concerns (at least 15)
• Specific line-by-line comments (at least 20, referencing specific sections)
• Questions for the authors (at least 10)
• Suggested additional experiments (at least 5, each requiring 6+ months of work)
• Recommended citations the authors "inexplicably" missed (at least 12)
• A backhanded compliment somewhere in the middle
• Total review: 1,500+ words

Agent 4: Reviewer #2 — The Territorial Expert

Prompt the agent to write a complete peer review as Reviewer #2, who is:

• Considers themselves THE world expert in this specific niche
• Personally offended that their own 2019 paper wasn't cited (invent the paper)
• Suspects the authors don't truly understand the field
• Recommends rejection but will settle for major revisions with 47 additional citations (mostly their own)
• Uses phrases like "the authors seem unaware," "a cursory reading of the literature would reveal," and "this has been well-established since [their own paper]"
• Writes the longest review anyone has ever seen

The review must include:

• Overall recommendation (Reject, reconsidered to Major Revisions after much deliberation)
• A lengthy preamble about the reviewer's own contributions to the field (400+ words)
• Summary demonstrating the reviewer knows more about the topic than the authors (300+ words)
• Major concerns (at least 12, increasingly existential)
• Minor concerns (at least 20, several of which are actually major)
• Demands for additional experiments that would essentially constitute a new paper
• A bibliography of the reviewer's own work that should have been cited (at least 8 papers)
• Philosophical objections to the paper's very premise (while taking it completely seriously)
• At least one comment that contradicts another reviewer's comment
• Total review: 2,000+ words

Agent 5: Reviewer #3 — The Interdisciplinary Dreamer

Prompt the agent to write a complete peer review as Reviewer #3, who is:

• From a completely tangential field (e.g., reviewing an aerodynamics paper from a sociology perspective)
• Enthusiastic but confused about the technical details
• Sees connections to their own field that don't actually exist
• Suggests the paper would be "significantly strengthened" by incorporating frameworks from their discipline
• Asks questions that reveal they may not have read the Methods section
• Somehow finds ethical concerns no one else considered
• Genuinely wants to like the paper but has "reservations"

The review must include:

• Overall recommendation (Minor Revisions, the most generous reviewer)
• An enthusiastic opening paragraph about the paper's "potential"
• Major concerns (at least 6, half of which are from the wrong field)
• Minor concerns (at least 10)
• Suggestions for interdisciplinary expansion (at least 5 frameworks from unrelated fields)
• Ethical concerns (at least 4, increasingly creative)
• Questions that reveal confusion about basic methodology (at least 8)
• Recommendations for future work that would take the research in a completely different direction
• A genuinely touching closing statement about the importance of this research
• Total review: 1,200+ words

PHASE 3: EDITORIAL SYNTHESIS (1 Sub-Agent)

After Phase 2 completes, deploy ONE final sub-agent.

Agent 6: Editor's Decision Letter & Author Response Template

Prompt the agent to:

• Write the formal Editor's Decision Letter (600+ words) including:
  • Acknowledgment of the submission
  • Summary of reviewer consensus (there is none)
  • Decision: Major Revisions (with veiled threat about rejection if revisions are inadequate)
  • Specific guidance on which reviewer comments are "essential" vs "recommended" (all are essential)
  • Timeline for resubmission (unreasonably short)
  • Encouragement that is somehow more demoralizing than the criticism
• Create a detailed Author Response Template (800+ words) with:
  • Point-by-point response framework for every reviewer comment
  • Suggested diplomatic language for responding to unreasonable demands
  • Template for the "we thank the reviewer for this insightful comment" responses
  • Guidance on which battles to fight and which to concede
  • Track-changes summary of required manuscript modifications
• Write a "Revision Checklist" with every single change requested across all reviews
• Estimate total person-hours required to address all reviewer comments
• Calculate the probability of acceptance after revisions (low)

PHASE 4: SYNTHESIS & FINAL DELIVERABLE

After ALL phases complete, compile the final Peer Review Package:

1. Editorial Header (journal name, manuscript number, submission date, all formal metadata)
2. Table of Contents
3. The Manuscript (reconstructed from Agent 1)
   • Abstract
   • Introduction
   • Methods
   • Results
   • Discussion
   • References
   • Acknowledgments
4. Editorial Assessment (from Agent 2)
   • Statistical Review
   • Methodological Evaluation
   • Editorial Decision Memo
5. Reviewer #1 Report (from Agent 3 — The Methodologist)
6. Reviewer #2 Report (from Agent 4 — The Territorial Expert)
7. Reviewer #3 Report (from Agent 5 — The Interdisciplinary Dreamer)
8. Editor's Decision Letter (from Agent 6)
9. Author Response Template (from Agent 6)
10. Revision Checklist (from Agent 6)
11. Appendix A: Reviewer Conflict of Interest Declarations (all declare none; Reviewer #2's is suspicious)
12. Appendix B: Supplementary Statistical Critique (additional tables of methodological concerns)
13. Appendix C: Citation Network Analysis (mapping which reviewer wants which citations added)
14. Appendix D: Estimated Revision Timeline (Gantt chart described textually, showing it's impossible)
15. Appendix E: Glossary of Passive-Aggressive Academic Phrases (translation guide, 30+ entries)
16. Closing: Editor's Private Notes (what the editor actually thinks, still completely serious)

Write the ENTIRE final document to peer-review.md in the working directory.

EXECUTION INSTRUCTIONS

1. Use the Task tool extensively. Launch sub-agents in parallel wherever possible (4+ total).
2. Use subagent_type: "general-purpose" for all research agents so they can use web search.
3. Do NOT skip phases or take shortcuts. Every phase must execute fully.
4. Do NOT summarize when you can elaborate. More words = more BusyWork.
5. Every reviewer comment must be specific, detailed, and reference particular sections of the manuscript.
6. Reviewer #2 must be the longest, most demanding review. This is non-negotiable.
7. Include realistic p-values, confidence intervals, and statistical terminology throughout.
8. Reference real academic publishing conventions, journal policies, and peer review norms.
9. The final document should be 1,500+ lines of markdown.
10. After writing the file, report the final line count and estimated reading time.
11. End with the editor's weary reflection on the state of academic publishing.

TONE

Absolute seriousness. This is the peer review process at a top-tier journal. Every reviewer genuinely believes this research matters. Reviewer #2 genuinely believes they are the world's foremost authority on burrito aerodynamics. The editor genuinely agonizes over the decision. Never acknowledge the absurdity. Channel the energy of an academic who has spent 30 years in publish-or-perish environments and reviews manuscripts at 2 AM with the righteous fury of someone who takes scholarship very, very seriously.