| name | paper-review |
| description | Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: 5-aspect checklist (contribution sufficiency, writing clarity, results quality, testing completeness, method design), counterintuitive protocol (reject-first simulation, delete unsupported claims, score trust, promote limitations, attack novelty), reverse-outlining, and figure/table quality checks. Use when: user wants to self-review or self-check their own paper draft before submission, stress-test their claims, prepare for reviewer criticism, or mentions 'self-review', 'check my draft', 'is my paper ready'. Do NOT use for writing a peer review of someone else's paper, and do NOT use after receiving actual reviews (use paper-rebuttal instead). Also runs as a background expert: dispatch it async with a draft path and it reviews end-to-end while you keep working. |
| allowed-tools | read_file edit_file write_file think_tool |
| metadata | {"author":"EvoScientist","version":"1.2.0","type":["skill","expert"],"tags":["core","writing","academic-writing","peer-review"]} |
Paper Review
A systematic approach to self-reviewing academic papers before submission. Covers a 5-aspect review checklist, reverse-outlining for structural clarity, figure/table quality checks, and rebuttal preparation.
When to Use This Skill
- User wants to review or check a paper draft before submission
- User asks for feedback on paper quality or completeness
- User wants to prepare for potential reviewer criticism
- User mentions "review paper", "check my draft", "self-review"
If the user has already received reviewer comments and needs to write a rebuttal, use the paper-rebuttal skill instead.
Prerequisites
Before starting review, confirm the paper-writing handoff checklist is satisfied: all sections drafted, claims anchored to evidence, limitation section present, figures finalized, and no unresolved \todo{} markers. If any item is incomplete, finish writing before reviewing.
The Perfectionist Approach
Strive for perfection: review your own paper, consider every question a reviewer might ask, and address them one by one.
The best defense against negative reviews is a thorough self-review:
- Adversarial review: Read your own paper as a critical reviewer would
- Seek advisor feedback: Ask your advisor to review — the more feedback, the better
- Address everything: For every potential weakness you find, either fix it or prepare a defense
Counterintuitive Review Protocol
Run this protocol before final polishing:
- Reject-first simulation: Force yourself to write a one-paragraph reject summary before writing any positive comments.
- Delete one unsupported strong claim: If a strong claim lacks direct evidence, remove it instead of defending it.
- Score trust, not only score gains: Papers with slightly lower gains but higher fairness and reproducibility often receive better review outcomes.
- Promote one explicit limitation: Move one meaningful limitation from hidden notes into the paper; transparency can increase confidence.
- Attack your novelty claim: Ask "Could a strong PhD derive this in one afternoon?" If yes, narrow and sharpen the novelty statement.
See references/counterintuitive-review.md
5-Aspect Self-Review Checklist
Aspect 1: Contribution Sufficiency
The paper does not provide readers with new knowledge.
Ask these questions to evaluate whether the contribution is sufficient:
Red flag: If "yes" to any of these, strengthen the contribution narrative or add more technical depth.
Aspect 2: Writing Clarity
Missing technical details, not reproducible; a method module lacks motivation.
Red flag: If reproducibility is in doubt, add implementation details or supplementary material.
Aspect 3: Experimental Results Quality
Only slightly better than previous methods; or better than previous methods but still not good enough.
Red flag: If improvements are marginal, emphasize other advantages (speed, generalizability, simplicity) or add more challenging test cases.
Aspect 4: Experimental Testing Completeness
Missing ablation studies; missing important baselines; missing important evaluation metrics; data too simple.
Red flag: Missing ablations or baselines is one of the most common reasons for rejection.
Aspect 5: Method Design Issues
Experimental setting is impractical; method has technical flaws; method is not robust; new method's costs outweigh its benefits.
Red flag: If the method requires significant tuning per scenario, add robustness experiments or acknowledge and address the limitation.
Critical Reminder: Claims Must Have Support
Every claim in the paper (especially in the Abstract and Introduction) must be correct and supported by experiments. Some reviewers will reject a paper directly for unsupported claims.
Go through every claim in the Abstract and Introduction. For each claim:
An unsupported claim — especially in the Abstract or Introduction — can be grounds for rejection.
Reverse-Outlining Technique
Extract the writing plan from finished paragraphs and check whether the flow is smooth.
After writing a section (or the entire paper):
- Read each paragraph one at a time
- Write down the main message of each paragraph in one sentence
- Read the sequence of messages — does it flow logically?
- Identify breaks: Where does the flow feel abrupt or illogical?
- Fix: Reorganize paragraphs, add transitions, or split/merge paragraphs
Apply this to:
- Introduction (check narrative flow)
- Method (check if modules are presented in logical order)
- Experiments (check if results are presented in a meaningful sequence)
Figure and Table Quality Checklist
Figures
Tables
Conclusion and Limitation Check
Pre-Submission Final Checks
Handoff to Rebuttal
When reviews come back, use the paper-rebuttal skill for:
- Score diagnosis and review color-coding
- Champion strategy (arming your positive reviewer for discussion)
- 18 tactical rules for structure, content, and tone
- Counterintuitive rebuttal principles
Your self-review artifacts (reject-first simulation, claim-evidence audit, prebuttal drafts from the counterintuitive protocol) feed directly into the rebuttal process.
See references/review-checklist.md for an expanded version of the 5-aspect checklist with more detailed sub-questions.
For adversarial stress testing and reject-risk thresholds, see references/counterintuitive-review.md.
The 5-aspect pass is also available as an executed workflow:
scripts/five_aspect_review.js — load it into
the code interpreter and call await fiveAspectReview(draftText) to run the
five aspects as parallel sub-reviews with typed results (score, findings,
blocking issues per aspect) and a synthesized verdict. Prefer it over
re-deriving the fan-out in prose; fall back to the sequential checklist above
only if the interpreter is unavailable.
