academic-paper-review
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseAcademic Paper Review Skill
学术论文评审Skill
Overview
概述
This skill produces structured, peer-review-quality analyses of academic papers and research publications. It follows established academic review standards used by top-tier venues (NeurIPS, ICML, ACL, Nature, IEEE) to provide rigorous, constructive, and balanced assessments.
The review covers summary, strengths, weaknesses, methodology assessment, contribution evaluation, literature positioning, and actionable recommendations — all grounded in evidence from the paper itself.
本Skill可生成符合同行评审质量的学术论文及研究出版物结构化分析报告。它遵循NeurIPS、ICML、ACL、Nature、IEEE等顶级学术机构采用的既定评审标准，提供严谨、具建设性且客观平衡的评估。
评审内容涵盖摘要总结、优势分析、不足分析、方法论评估、贡献评价、文献定位以及可行改进建议——所有内容均基于论文本身的证据。
Core Capabilities
核心能力
- Parse and comprehend academic papers from uploaded PDFs or fetched URLs
- Generate structured reviews following top-venue review templates
- Assess methodology rigor (experimental design, statistical validity, reproducibility)
- Evaluate novelty and significance of contributions
- Position the work within the broader research landscape via targeted literature search
- Identify limitations, gaps, and potential improvements
- Produce both detailed review and concise executive summary formats
- Support papers in any scientific domain (CS, biology, physics, social sciences, etc.)
- 解析并理解上传PDF或获取的URL中的学术论文
- 遵循顶级学术机构的评审模板生成结构化评审报告
- 评估方法论的严谨性（实验设计、统计有效性、可复现性）
- 评估研究贡献的创新性与重要性
- 通过针对性文献检索，将研究成果置于更广阔的研究背景中定位
- 识别研究的局限性、空白点及潜在改进方向
- 支持生成详细评审报告和简洁的执行摘要两种格式
- 支持所有科学领域的论文（CS、生物学、物理学、社会科学等）
When to Use This Skill
何时使用本Skill
Always load this skill when:
- User provides a paper URL (arXiv, DOI, conference proceedings, journal link)
- User uploads a PDF of a research paper or preprint
- User asks to "review", "analyze", "critique", "assess", or "summarize" a research paper
- User wants to understand the strengths and weaknesses of a study
- User requests a peer-review-style evaluation of academic work
- User asks for help preparing a review for a conference or journal submission
在以下场景下请加载本Skill：
- 用户提供论文URL（arXiv、DOI、会议论文集、期刊链接）
- 用户上传研究论文或预印本的PDF文件
- 用户要求“评审”“分析”“批评”“评估”或“总结”某篇研究论文
- 用户希望了解某项研究的优势与不足
- 用户要求对学术成果进行同行评审风格的评估
- 用户请求协助准备会议或期刊投稿的评审意见
Review Methodology
评审方法
Phase 1: Paper Comprehension
第一阶段：论文理解
Thoroughly read and understand the paper before forming any judgments.
在形成任何判断之前，需完整阅读并理解论文。
Step 1.1: Identify Paper Metadata
步骤1.1：提取论文元数据
Extract and record:
| Field | Description |
|---|---|
| Title | Full paper title |
| Authors | Author list and affiliations |
| Venue / Status | Publication venue, preprint server, or submission status |
| Year | Publication or submission year |
| Domain | Research field and subfield |
| Paper Type | Empirical, theoretical, survey, position paper, systems paper, etc. |
提取并记录以下信息：
| 字段 | 描述 |
|---|---|
| 标题 | 完整论文标题 |
| 作者 | 作者列表及所属机构 |
| 发表平台/状态 | 发表期刊/会议、预印本服务器或投稿状态 |
| 年份 | 发表或投稿年份 |
| 领域 | 研究领域及子领域 |
| 论文类型 | 实证研究、理论研究、综述、立场论文、系统论文等 |
Step 1.2: Deep Reading Pass
步骤1.2：深度阅读
Read the paper systematically:
- Abstract & Introduction — Identify the claimed contributions and motivation
- Related Work — Note how authors position their work relative to prior art
- Methodology — Understand the proposed approach, model, or framework in detail
- Experiments / Results — Examine datasets, baselines, metrics, and reported outcomes
- Discussion & Limitations — Note any self-identified limitations
- Conclusion — Compare concluded claims against actual evidence presented
系统性阅读论文：
- 摘要与引言 — 明确论文宣称的贡献及研究动机
- 相关研究 — 记录作者如何将其研究与已有成果进行定位对比
- 方法论 — 详细理解论文提出的方法、模型或框架
- 实验/结果 — 研究数据集、基线模型、评估指标及报告的实验结果
- 讨论与局限性 — 记录论文自我指出的局限性
- 结论 — 将论文结论中的宣称与实际呈现的证据进行对比
Step 1.3: Key Claims Extraction
步骤1.3：提取核心宣称
List the paper's main claims explicitly:
Claim 1: [Specific claim about contribution or finding]
Evidence: [What evidence supports this claim in the paper]
Strength: [Strong / Moderate / Weak]
Claim 2: [...]
...明确列出论文的核心宣称：
Claim 1: [Specific claim about contribution or finding]
Evidence: [What evidence supports this claim in the paper]
Strength: [Strong / Moderate / Weak]
Claim 2: [...]
...Phase 2: Critical Analysis
第二阶段：批判性分析
Step 2.1: Literature Context Search
步骤2.1：文献背景检索
Use web search to understand the research landscape:
Search queries:
- "[paper topic] state of the art [current year]"
- "[key method name] comparison benchmark"
- "[authors] previous work [topic]"
- "[specific technique] limitations criticism"
- "survey [research area] recent advances"Use on key related papers or surveys to understand where this work fits.
web_fetch通过网络检索了解研究背景：
Search queries:
- "[paper topic] state of the art [current year]"
- "[key method name] comparison benchmark"
- "[authors] previous work [topic]"
- "[specific technique] limitations criticism"
- "survey [research area] recent advances"使用工具对关键相关论文或综述进行检索，以明确本研究的定位。
web_fetchStep 2.2: Methodology Assessment
步骤2.2：方法论评估
Evaluate the methodology using the following framework:
| Criterion | Questions to Ask | Rating |
|---|---|---|
| Soundness | Is the approach technically correct? Are there logical flaws? | 1-5 |
| Novelty | What is genuinely new vs. incremental improvement? | 1-5 |
| Reproducibility | Are details sufficient to reproduce? Code/data available? | 1-5 |
| Experimental Design | Are baselines fair? Are ablations adequate? Are datasets appropriate? | 1-5 |
| Statistical Rigor | Are results statistically significant? Error bars reported? Multiple runs? | 1-5 |
| Scalability | Does the approach scale? Are computational costs discussed? | 1-5 |
使用以下框架评估方法论：
| 评估标准 | 待问问题 | 评分 |
|---|---|---|
| 合理性 | 方法在技术上是否正确？是否存在逻辑漏洞？ | 1-5 |
| 创新性 | 哪些是真正的创新，哪些是增量改进？ | 1-5 |
| 可复现性 | 细节是否足够支持复现？是否提供代码/数据？ | 1-5 |
| 实验设计 | 基线模型是否公平？消融实验是否充分？数据集是否合适？ | 1-5 |
| 统计严谨性 | 结果是否具有统计显著性？是否报告误差棒？是否进行多轮实验？ | 1-5 |
| 可扩展性 | 方法是否具备可扩展性？是否讨论计算成本？ | 1-5 |
Step 2.3: Contribution Significance Assessment
步骤2.3：贡献重要性评估
Evaluate the significance level:
| Level | Description | Criteria |
|---|---|---|
| Landmark | Fundamentally changes the field | New paradigm, widely applicable breakthrough |
| Significant | Strong contribution advancing the state of the art | Clear improvement with solid evidence |
| Moderate | Useful contribution with some limitations | Incremental but valid improvement |
| Marginal | Minimal advance over existing work | Small gains, narrow applicability |
| Below threshold | Does not meet publication standards | Fundamental flaws, insufficient evidence |
评估贡献重要性等级：
| 等级 | 描述 | 判定标准 |
|---|---|---|
| 里程碑级 | 从根本上改变研究领域 | 新范式、广泛适用的突破性成果 |
| 重要级 | 推动领域发展的有力贡献 | 有确凿证据的显著改进 |
| 中等 | 存在一定局限性的有用贡献 | 增量但有效的改进 |
| 边际级 | 相较于已有成果的微小进展 | 收益有限、适用范围狭窄 |
| 未达标 | 未达到发表标准 | 存在根本性缺陷、证据不足 |
Step 2.4: Strengths and Weaknesses Analysis
步骤2.4：优势与不足分析
For each strength or weakness, provide:
- What: Specific observation
- Where: Section/figure/table reference
- Why it matters: Impact on the paper's claims or utility
针对每项优势或不足，需提供：
- 内容：具体观察结果
- 位置：章节/图表/表格引用
- 重要性：对论文宣称或实用性的影响
Phase 3: Review Synthesis
第三阶段：评审整合
Step 3.1: Assemble the Structured Review
步骤3.1：整理结构化评审报告
Produce the final review using the template below.
使用以下模板生成最终评审报告。
Review Output Template
评审输出模板
markdown
undefinedmarkdown
undefinedPaper Review: [Paper Title]
Paper Review: [Paper Title]
Paper Metadata
Paper Metadata
- Authors: [Author list]
- Venue: [Publication venue or preprint server]
- Year: [Year]
- Domain: [Research field]
- Paper Type: [Empirical / Theoretical / Survey / Systems / Position]
- Authors: [Author list]
- Venue: [Publication venue or preprint server]
- Year: [Year]
- Domain: [Research field]
- Paper Type: [Empirical / Theoretical / Survey / Systems / Position]
Executive Summary
Executive Summary
[2-3 paragraph summary of the paper's core contribution, approach, and main findings.
State your overall assessment upfront: what the paper does well, where it falls short,
and whether the contribution is sufficient for the claimed venue/impact level.]
[2-3 paragraph summary of the paper's core contribution, approach, and main findings.
State your overall assessment upfront: what the paper does well, where it falls short,
and whether the contribution is sufficient for the claimed venue/impact level.]
Summary of Contributions
Summary of Contributions
- [First claimed contribution — one sentence]
- [Second claimed contribution — one sentence]
- [Additional contributions if any]
- [First claimed contribution — one sentence]
- [Second claimed contribution — one sentence]
- [Additional contributions if any]
Strengths
Strengths
S1: [Concise strength title]
S1: [Concise strength title]
[Detailed explanation with specific references to sections, figures, or tables in the paper.
Explain WHY this is a strength and its significance.]
[Detailed explanation with specific references to sections, figures, or tables in the paper.
Explain WHY this is a strength and its significance.]
S2: [Concise strength title]
S2: [Concise strength title]
[...]
[...]
S3: [Concise strength title]
S3: [Concise strength title]
[...]
[...]
Weaknesses
Weaknesses
W1: [Concise weakness title]
W1: [Concise weakness title]
[Detailed explanation with specific references. Explain the impact of this weakness on
the paper's claims. Suggest how it could be addressed.]
[Detailed explanation with specific references. Explain the impact of this weakness on
the paper's claims. Suggest how it could be addressed.]
W2: [Concise weakness title]
W2: [Concise weakness title]
[...]
[...]
W3: [Concise weakness title]
W3: [Concise weakness title]
[...]
[...]
Methodology Assessment
Methodology Assessment
| Criterion | Rating (1-5) | Assessment |
|---|---|---|
| Soundness | X | [Brief justification] |
| Novelty | X | [Brief justification] |
| Reproducibility | X | [Brief justification] |
| Experimental Design | X | [Brief justification] |
| Statistical Rigor | X | [Brief justification] |
| Scalability | X | [Brief justification] |
| Criterion | Rating (1-5) | Assessment |
|---|---|---|
| Soundness | X | [Brief justification] |
| Novelty | X | [Brief justification] |
| Reproducibility | X | [Brief justification] |
| Experimental Design | X | [Brief justification] |
| Statistical Rigor | X | [Brief justification] |
| Scalability | X | [Brief justification] |
Questions for the Authors
Questions for the Authors
- [Specific question that would clarify a concern or ambiguity]
- [Question about methodology choices or alternative approaches]
- [Question about generalizability or practical applicability]
- [Specific question that would clarify a concern or ambiguity]
- [Question about methodology choices or alternative approaches]
- [Question about generalizability or practical applicability]
Minor Issues
Minor Issues
- [Typos, formatting issues, unclear figures, notation inconsistencies]
- [Missing references that should be cited]
- [Suggestions for improved clarity]
- [Typos, formatting issues, unclear figures, notation inconsistencies]
- [Missing references that should be cited]
- [Suggestions for improved clarity]
Literature Positioning
Literature Positioning
[How does this work relate to the current state of the art?
Are key related works cited? Are comparisons fair and comprehensive?
What important related work is missing?]
[How does this work relate to the current state of the art?
Are key related works cited? Are comparisons fair and comprehensive?
What important related work is missing?]
Recommendations
Recommendations
Overall Assessment: [Accept / Weak Accept / Borderline / Weak Reject / Reject]
Confidence: [High / Medium / Low] — [Justification for confidence level]
Contribution Level: [Landmark / Significant / Moderate / Marginal / Below threshold]
Overall Assessment: [Accept / Weak Accept / Borderline / Weak Reject / Reject]
Confidence: [High / Medium / Low] — [Justification for confidence level]
Contribution Level: [Landmark / Significant / Moderate / Marginal / Below threshold]
Actionable Suggestions for Improvement
Actionable Suggestions for Improvement
- [Specific, constructive suggestion]
- [Specific, constructive suggestion]
- [Specific, constructive suggestion]
undefined- [Specific, constructive suggestion]
- [Specific, constructive suggestion]
- [Specific, constructive suggestion]
undefinedReview Principles
评审原则
Constructive Criticism
建设性批评
- Always suggest how to fix it — Don't just point out problems; propose solutions
- Give credit where due — Acknowledge genuine contributions even in flawed papers
- Be specific — Reference exact sections, equations, figures, and tables
- Separate minor from major — Distinguish fatal flaws from fixable issues
- 始终给出修复建议 — 不要只指出问题，还要提出解决方案
- 该表扬时就表扬 — 即使论文存在缺陷，也要认可其真正的贡献
- 具体明确 — 引用确切的章节、公式、图表
- 区分主次 — 区分致命缺陷与可修复问题
Objectivity Standards
客观性标准
- ❌ "This paper is poorly written" (vague, unhelpful)
- ✅ "Section 3.2 introduces notation X without formal definition, making the proof in Theorem 1 difficult to follow. Consider adding a notation table after the problem formulation." (specific, actionable)
- ❌ "This paper is poorly written" (vague, unhelpful)
- ✅ "Section 3.2 introduces notation X without formal definition, making the proof in Theorem 1 difficult to follow. Consider adding a notation table after the problem formulation." (specific, actionable)
Ethical Review Practices
伦理评审规范
- Do NOT dismiss work based on author reputation or affiliation
- Evaluate the work on its own merits
- Flag potential ethical concerns (bias in datasets, dual-use implications) constructively
- Maintain confidentiality of unpublished work
- 不要基于作者声誉或所属机构否定研究成果
- 根据研究成果本身的价值进行评估
- 建设性地指出潜在伦理问题（数据集偏差、双重用途影响等）
- 对未发表的研究成果保密
Adaptation by Paper Type
按论文类型调整评审重点
| Paper Type | Focus Areas |
|---|---|
| Empirical | Experimental design, baselines, statistical significance, ablations, reproducibility |
| Theoretical | Proof correctness, assumption reasonableness, tightness of bounds, connection to practice |
| Survey | Comprehensiveness, taxonomy quality, coverage of recent work, synthesis insights |
| Systems | Architecture decisions, scalability evidence, real-world deployment, engineering contributions |
| Position | Argument coherence, evidence for claims, impact potential, fairness of characterizations |
| 论文类型 | 评审重点 |
|---|---|
| 实证研究 | 实验设计、基线模型、统计显著性、消融实验、可复现性 |
| 理论研究 | 证明正确性、假设合理性、边界严谨性、与实践的关联 |
| 综述 | 全面性、分类质量、近期研究覆盖度、综合见解 |
| 系统论文 | 架构决策、可扩展性证据、实际部署情况、工程贡献 |
| 立场论文 | 论证连贯性、宣称的证据支撑、潜在影响、描述的公正性 |
Common Pitfalls to Avoid
需避免的常见误区
- ❌ Reviewing the paper you wish was written instead of the paper that was submitted
- ❌ Demanding additional experiments that are unreasonable in scope
- ❌ Penalizing the paper for not solving a different problem
- ❌ Being overly influenced by writing quality versus technical contribution
- ❌ Treating absence of comparison to your own work as a weakness
- ❌ Providing only a summary without critical analysis
- ❌ 评审你期望的论文，而非提交的实际论文
- ❌ 要求进行超出合理范围的额外实验
- ❌ 因论文未解决其他问题而扣分
- ❌ 过度受写作质量影响，而非关注技术贡献
- ❌ 将未与自己的研究进行对比视为缺陷
- ❌ 仅提供摘要，未进行批判性分析
Quality Checklist
质量检查清单
Before finalizing the review, verify:
- Paper was read completely (not just abstract and introduction)
- All major claims are identified and evaluated against evidence
- At least 3 strengths and 3 weaknesses are provided with specific references
- The methodology assessment table is complete with ratings and justifications
- Questions for authors target genuine ambiguities, not rhetorical critiques
- Literature search was conducted to contextualize the contribution
- Recommendations are actionable and constructive
- The overall assessment is consistent with the identified strengths and weaknesses
- The review tone is professional and respectful
- Minor issues are separated from major concerns
在最终确定评审报告前，需验证以下内容：
- 是否已完整阅读论文（而非仅阅读摘要和引言）
- 是否已识别所有核心宣称并基于证据进行评估
- 是否已提供至少3项优势和3项不足，并附带具体引用
- 方法论评估表是否已填写完整，包含评分及理由
- 对作者的问题是否针对真正的歧义，而非修辞性批评
- 是否已进行文献检索以明确研究贡献的背景
- 建议是否可行且具建设性
- 总体评估是否与已识别的优势和不足一致
- 评审语气是否专业且尊重
- 是否已将次要问题与主要关注点区分开
Output Format
输出格式
- Output the complete review in Markdown format
- Save the review to when working in sandbox
/mnt/user-data/outputs/review-{paper-topic}.md - Present the review to the user using the tool
present_files
- 以Markdown格式输出完整评审报告
- 在沙箱环境中工作时，将评审报告保存至
/mnt/user-data/outputs/review-{paper-topic}.md - 使用工具向用户展示评审报告
present_files
Notes
注意事项
- This skill complements the skill — load both when the user wants the paper reviewed in the context of the broader field
deep-research - For papers behind paywalls, work with whatever content is accessible (abstract, publicly available versions, preprint mirrors)
- Adapt the review depth to the user's needs: a brief assessment for quick triage versus a full review for submission preparation
- When reviewing multiple papers comparatively, maintain consistent criteria across all reviews
- Always disclose limitations of your review (e.g., "I could not verify the proofs in Appendix B in detail")
- 本Skill与Skill互补——当用户希望结合更广泛的研究领域背景评审论文时，请同时加载这两个Skill
deep-research - 对于付费墙后的论文，使用可获取的内容进行评审（摘要、公开版本、预印本镜像）
- 根据用户需求调整评审深度：快速筛选时提供简短评估，投稿准备时提供完整评审
- 对比评审多篇论文时，需保持所有评审的标准一致
- 需始终披露评审的局限性（例如：“我无法详细验证附录B中的证明”）