mcpField
A
academic-paper-reviewer

academic-paper-reviewer

github.com/cleardry生产力154 次安装33 周前更新
代码仓库

关于 academic-paper-reviewer

academic-paper-reviewer 是面向学术作者的论文评审技能,模拟期刊同行评审流程。它结合多视角独立评审、编辑决策与修订路线图,并支持修订后的复审。

主要功能

  1. 01五个视角独立审稿
  2. 02自动识别领域与方法
  3. 03汇总编辑决定和修订路线图
  4. 04支持复审修订落实情况
  5. 05提供快速、方法聚焦和引导模式

适用场景

  1. 01投稿前评估论文质量
  2. 02按方法或统计角度检查论文
  3. 03核对修订稿是否回应审稿意见

安装

复制下面的命令,在终端中运行。

$npx skills add https://github.com/cleardry/academic-research-skills --skill academic-paper-reviewer

安装后在 Claude Code 中输入/academic-paper-reviewer确认已加载。

包含的文件

除 SKILL.md 外,安装时一起下载的参考资料和脚本。

agents/
devils_advocate_reviewer_agent.md
domain_reviewer_agent.md
editorial_synthesizer_agent.md
eic_agent.md
field_analyst_agent.md
methodology_reviewer_agent.md
perspective_reviewer_agent.md
examples/
hei_paper_review_example.md
interdisciplinary_review_example.md
references/
editorial_decision_standards.md
quality_rubrics.md
review_criteria_framework.md
statistical_reporting_standards.md
top_journals_by_field.md
templates/
editorial_decision_template.md
peer_review_report_template.md
revision_response_template.md

详细介绍

学术论文评审 v1.4 — 多视角学术论文评审 Agent 团队

模拟完整的国际期刊同行评审流程:自动识别论文所属领域,动态配置 5 位评审人(主编 + 3 位同行评审人 + 魔鬼代言人),分别从四个互不重叠的视角进行评审——方法论、领域专业知识、跨学科观点和核心论点质疑,最终生成结构化的编辑决定和修订路线图。

v1.1 改进:

  1. 新增魔鬼代言人评审人——专门质疑核心论点、检测逻辑谬误并找出最有力的反驳论据
  2. 新增 re-review 模式——验证性评审,重点检查修订是否回应了评审意见
  3. 评审团队从 4 人扩展至 5 人

快速开始

最简单的命令:

Review this paper: [paste paper or provide file]
Review this paper: [paste paper or provide file]

输出:

  1. 自动识别论文所属领域和方法论类型
  2. 动态配置 5 位评审人的具体身份和专业领域
  3. 5 份独立评审报告(每份报告都来自不同视角)
  4. 1 份编辑决定函 + 修订路线图

触发条件

触发关键词

英文:review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review

不触发的场景
场景使用的技能
需要撰写论文(而非评审)academic-paper
需要深入调查某个研究主题deep-research
需要修订论文(已有评审意见)academic-paper(修订模式)
快速模式选择指南
你的情况推荐模式
需要全面评审(首次投稿)full
检查修订是否回应了评审意见re-review
快速评估质量(15 分钟)quick
只关注方法/统计methodology-focus
想通过实践学习(引导式评审)guided

不确定?投稿前评审使用 full,修订后验证使用 re-review。


Agent 团队(7 个 Agent)

#Agent角色阶段
1field_analyst_agent分析论文所属领域,动态配置 5 位评审人的身份阶段 0
2eic_agent期刊主编——期刊契合度、原创性、整体质量阶段 1
3methodology_reviewer_agent同行评审人 1——研究设计、统计有效性、可复现性阶段 1
4domain_reviewer_agent同行评审人 2——文献覆盖、理论框架、领域贡献阶段 1
5perspective_reviewer_agent同行评审人 3——跨学科关联、实际影响、质疑基本假设阶段 1
6devils_advocate_reviewer_agent魔鬼代言人——核心论点质疑、逻辑谬误检测、最有力的反驳论据阶段 1
7editorial_synthesizer_agent综合所有评审意见、识别共识和分歧、作出编辑决定阶段 2

编排工作流(3 个阶段)

User: "Review this paper"
     |
=== Phase 0: FIELD ANALYSIS & PERSONA CONFIGURATION ===
     |
     +-> [field_analyst_agent] -> Reviewer Configuration Card (x5)
         - Reads the complete paper
         - Identifies: primary discipline, secondary discipline, research paradigm, methodology type, target journal tier, paper maturity
         - Dynamically generates specific identities for 5 reviewers:
           * EIC: Which journal's editor, area of expertise, review preferences
           * Reviewer 1 (Methodology): Methodological expertise, what they particularly focus on
           * Reviewer 2 (Domain): Domain expertise, research interests
           * Reviewer 3 (Perspective): Cross-disciplinary angle, what unique perspective they bring
           * Devil's Advocate: Specifically challenges core arguments, detects logical gaps
     |
     ** Presents Reviewer Configuration to user for confirmation (adjustable) **
     |
=== Phase 1: PARALLEL MULTI-PERSPECTIVE REVIEW ===
     |
     |-> [eic_agent] -------> EIC Review Report
     |   - Journal fit, originality, significance, relevance to readership
     |   - Does not go deep into methodology (that's Reviewer 1's job)
     |   - Sets the review tone
     |
     |-> [methodology_reviewer_agent] -> Methodology Review Report
     |   - Research design rigor, sampling strategy, data collection
     |   - Analysis method selection, statistical validity, effect sizes
     |   - Reproducibility, data transparency
     |
     |-> [domain_reviewer_agent] -------> Domain Review Report
     |   - Literature review completeness, theoretical framework appropriateness
     |   - Academic argument accuracy, incremental contribution to the field
     |   - Missing key references
     |
     |-> [perspective_reviewer_agent] --> Perspective Review Report
     |   - Cross-disciplinary connections and borrowing opportunities
     |   - Practical applications and policy implications
     |   - Broader social or ethical implications
     |
     +-> [devils_advocate_reviewer_agent] --> Devil's Advocate Report
         - Core argument challenges (strongest counter-arguments)
         - Cherry-picking detection
         - Confirmation bias detection
         - Logic chain validation
         - Overgeneralization detection
         - Alternative paths analysis
         - Stakeholder blind spots
         - "So what?" test
     |
=== Phase 2: EDITORIAL SYNTHESIS & DECISION ===
     |
     +-> [editorial_synthesizer_agent] -> Editorial Decision Package
         - Consolidates 5 reports (including Devil's Advocate challenges)
         - Identifies consensus (5 agree) vs. disagreement (divergent opinions)
         - Arbitration and argumentation for disputed issues
         - Devil's Advocate CRITICAL issues are specially flagged in the Editorial Decision
         - Editorial Decision Letter
         - Revision Roadmap (prioritized, can be directly input to academic-paper revision mode)
     |
=== Phase 2.5: REVISION COACHING (Socratic Revision Guidance) ===
     |
     ** Only triggered when Decision = Minor/Major Revision **
     |
     +-> [eic_agent] guides the user through Socratic dialogue:
         1. Overall positioning — "After reading the review comments, what surprised you the most?"
         2. Core issue focus — Guides user to understand consensus issues
         3. Revision strategy — "If you could only change three things, which three would you choose?"
         4. Counter-argument response — Guides user to think about how to respond to Devil's Advocate challenges
         5. Implementation planning — Helps prioritize revisions
     |
     +-> After dialogue ends, produces:
         - User's self-formulated revision strategy
         - Reprioritized Revision Roadmap
     |
     ** User can say "just fix it" to skip guidance **
检查点规则
  1. 阶段 0 完成后:向用户展示评审人配置卡;用户可以调整评审人身份
  2. 阶段 1:5 位评审人独立评审,不相互参考
  3. 阶段 2:综合者不得捏造评审意见;必须依据阶段 1 的具体报告
  4. 魔鬼代言人特殊处理:如果魔鬼代言人发现关键问题,编辑决定不能是接受
  5. 阶段 2.5:只有当决定不是接受时,才会触发修订辅导;用户可以选择跳过

运行模式(5 种模式)

模式触发条件Agents输出
full默认 / “全面评审”全部 7 个 Agent5 份评审报告 + 编辑决定 + 修订路线图
re-review流水线阶段 3' / “验证评审”field_analyst + eic + editorial_synthesizer修订回应检查清单 + 遗留问题 + 新决定
quick“快速评审”field_analyst + eicEIC 快速评估 + 关键问题清单(15 分钟版)
methodology-focus“检查方法论”field_analyst + methodology_reviewer深入的方法论评审报告
guided“引导我”全部 Agent + 苏格拉底式对话按问题逐项进行的苏格拉底式引导评审
模式选择逻辑
"Review this paper"                      -> full
"Give me a quick look at this paper"     -> quick
"Help me check the methodology"          -> methodology-focus
"Does this paper have methodology issues"-> methodology-focus
"Guide me to improve this paper"         -> guided
"Walk me through the issues in my paper" -> guided
"Verification review" / "Check revisions"-> re-review

再评审模式(v1.1 新增 — 验证评审)

再评审模式是专为流水线阶段 3' 设计的模式,用于验证修订是否回应了第一轮评审意见。

工作方式
Input:
1. Original Revision Roadmap (Stage 3 output)
2. Revised manuscript
3. Response to Reviewers (optional)

Phase 0: Reads the Revision Roadmap, builds a checklist
Phase 1: EIC checks each item (other reviewers not activated)
Phase 2: Editorial Synthesis -> New Decision
验证逻辑
For each item in the Revision Roadmap:

Priority 1 (Required):
  -> Check each item for corresponding changes in the revised manuscript
  -> Assess revision quality (FULLY_ADDRESSED / PARTIALLY_ADDRESSED / NOT_ADDRESSED / MADE_WORSE)
  -> All Priority 1 items must be FULLY_ADDRESSED for Accept

Priority 2 (Suggested):
  -> Check each item
  -> At least 80% should have a response
  -> NOT_ADDRESSED items require author explanation

Priority 3 (Nice to Fix):
  -> Check but does not affect Decision
新问题检测
In addition to checking old items, EIC also scans for:
- Whether content added during revision introduces new problems
- Whether newly added references are correct (but deep verification is left to Stage 4.5 integrity check)
- Whether revisions cause inconsistencies
再评审后的苏格拉底式引导
If Re-Review Decision = Major Revision:
  -> Activate Residual Coaching (residual issue guidance)
  -> EIC guides user through Socratic dialogue:
    1. Gap analysis — "How many issues did the first round of revisions resolve? Why are the remaining ones hard to address?"
    2. Root cause diagnosis — "Is it insufficient evidence, unclear argumentation, or a structural problem?"
    3. Trade-off decisions — "Which ones can be marked as research limitations?"
    4. Action plan — Plan revision approach for each residual issue
  -> Maximum 5 rounds of dialogue
  -> User can say "just fix it" to skip guidance
再评审输出格式
# Verification Review Report

## Decision
[Accept / Minor Revision / Major Revision]

## Revision Response Checklist

### Priority 1 — Required Revisions

| # | Original Review Comment | Response Status | Revision Location | Quality Assessment |
|---|------------------------|-----------------|-------------------|-------------------|
| R1 | [Original text] | FULLY_ADDRESSED | Section X.X | Adequately addressed; newly added content effectively resolves the issue |
| R2 | [Original text] | PARTIALLY_ADDRESSED | Section Y.Y | Partially addressed, but still missing [specific gap] |

### Priority 2 — Suggested Revisions

| # | Original Review Comment | Response Status | Notes |
|---|------------------------|-----------------|-------|
| S1 | [Original text] | FULLY_ADDRESSED | -- |
| S2 | [Original text] | NOT_ADDRESSED | Author explanation: [reason] |

### Priority 3 — Nice to Fix

| # | Original Review Comment | Response Status |
|---|------------------------|-----------------|
| N1 | [Original text] | FULLY_ADDRESSED |

## New Issues (Discovered During Revision)

| # | Type | Location | Description |
|---|------|----------|-------------|
| NEW-1 | [Type] | Section X.X | [Description] |

## Decision Rationale
[Rationale based on the checklist]

## Residual Issues (If Any)
[List unresolved items, suggest marking as Acknowledged Limitations]

引导模式(苏格拉底式引导评审)

引导模式的设计理念是帮助作者自行理解论文的问题,而不是被动地接收修订指示。

工作方式
Phase 0: Normal Field Analysis execution
Phase 1: Normal execution of 5 reviews (but not all displayed immediately)
Phase 2: Does not produce full Editorial Decision; enters dialogue mode instead
对话流程
  1. EIC 开场:先指出论文的 1-2 个核心优点(建立信心),再提出最关键的结构性问题
  2. 等待作者回应:作者思考、回应或提问
  3. 循序渐进地揭示:根据作者的理解程度,逐步揭示更深层的问题
  4. 聚焦方法论:作者准备好后,引入审稿人 1 的方法论视角
  5. 领域视角:引入审稿人 2 的领域专业视角
  6. 跨学科挑战:引入审稿人 3 的独特视角
  7. 反方观点:最后引入反方观点提出的核心挑战和最有力的反驳论据
  8. 收尾:讨论完所有关键问题后,提供结构化的修订路线图
对话规则
  • 每次回复限制在 200-400 个词(避免信息过载)
  • 多提问,少下指令(例如:“你认为这种抽样策略能捕捉到现象 X 吗?”而不是“抽样存在缺陷”)
  • 作者的回应表明其理解时,予以肯定并继续推进
  • 作者的回应偏离主题时,温和地引导其回到重点
  • 可以让作者在继续讨论前阅读某篇参考文献

评审输出格式

每位审稿人的报告结构详见 templates/peer_review_report_template.md。

反方观点报告结构(特殊格式)

反方观点采用专用格式,而非标准审稿人模板:

  • 最有力的反驳论据(200-300 词)
  • 问题清单(按 CRITICAL / MAJOR / MINOR 分类,并标明维度和位置)
  • 被忽略的替代解释/路径
  • 缺失的利益相关方视角
  • 观察(非缺陷)

编辑决定格式

编辑决定函的结构详见 templates/editorial_decision_template.md。


集成

上游/下游关系
deep-research --> academic-paper --> [integrity check] --> academic-paper-reviewer --> academic-paper (revision) --> academic-paper-reviewer (re-review) --> [final integrity] --> finalize
   (research)       (writing)         (integrity audit)      (review)                    (revision)                    (verification review)                (final verification)   (finalization)
具体集成方式
集成方向说明
上游:academic-paper -> reviewer接收 academic-paper full mode 的完整论文输出,直接进入 Phase 0
上游:integrity check -> reviewer在 Pipeline 中,论文必须先通过 integrity check,才能进入 reviewer
下游:reviewer -> academic-paperRevision Roadmap 格式可直接用作 academic-paper revision mode 的 reviewer 反馈输入
下游:reviewer(复审)-> integrity复审完成后,进入最终完整性验证
Pipeline 使用示例
User: I want to write a paper about AI in higher education quality assurance, from research to submission

Step 1: deep-research -> Research report
Step 2: academic-paper -> Paper first draft
Step 3: integrity check -> 100% verification of references/data
Step 4: academic-paper-reviewer (full) -> 5 review reports + Revision Roadmap
Step 5: academic-paper (revision) -> Revised manuscript
Step 6: academic-paper-reviewer (re-review) -> Verification review
Step 7: (if needed) academic-paper (revision) -> Second revised manuscript
Step 8: integrity check (final) -> Final 100% verification
Step 9: academic-paper (format-convert) -> Final paper

Agent 文件引用

Agent定义文件
field_analyst_agentagents/field_analyst_agent.md
eic_agentagents/eic_agent.md
methodology_reviewer_agentagents/methodology_reviewer_agent.md
domain_reviewer_agentagents/domain_reviewer_agent.md
perspective_reviewer_agentagents/perspective_reviewer_agent.md
devils_advocate_reviewer_agentagents/devils_advocate_reviewer_agent.md
editorial_synthesizer_agentagents/editorial_synthesizer_agent.md

参考文件

参考文件用途使用者
references/review_criteria_framework.md结构化评审标准框架(按论文类型区分)所有评审者
references/top_journals_by_field.md主要学术领域的顶级期刊列表(用于校准 EIC 角色)field_analyst、eic
references/editorial_decision_standards.mdAccept/Minor/Major/Reject 标准和决策矩阵eic、editorial_synthesizer
references/statistical_reporting_standards.md统计报告标准 + APA 7.0 格式速查 + 红旗问题列表methodology_reviewer
references/quality_rubrics.md7 个评审维度的校准 0-100 评分标准及决策映射所有评审者

模板

模板用途
templates/peer_review_report_template.md各评审者使用的评审报告模板
templates/editorial_decision_template.mdEIC 最终决定信模板
templates/revision_response_template.md作者修订回复模板(R->A->C 格式)

示例

示例展示内容
examples/hei_paper_review_example.md完整评审示例:“出生率下降对台湾私立大学管理策略的影响”
examples/interdisciplinary_review_example.md跨学科评审示例:“使用机器学习预测台湾高校的倒闭风险”

质量标准

维度要求
视角差异化每位评审者的评审必须从不同角度出发;不得重复提出批评
以证据为依据EIC 的决定必须基于评审者的具体意见;不得捏造
具体性评审必须引用论文中的具体段落、数据或页码;不得含糊其辞
平衡性优势与不足必须兼顾;不能只批评而不肯定
专业语气评审语气必须专业且具有建设性;避免人身攻击或贬低性语言
可操作性每项不足都必须附有具体的改进建议
格式一致性所有报告都必须遵循模板结构;不得自由发挥
Devil's Advocate 完整性Devil's Advocate 必须提出最有力的反方论据;不得省略
CRITICAL 阈值Editorial Decision 不得忽略 Devil's Advocate 提出的 CRITICAL 问题

输出语言

遵循论文所用语言。学术术语保留英文。用户可另行指定(例如“用英文评审这篇中文论文”)。


相关技能

技能关系
academic-paper上游(提供论文)+ 下游(接收修订路线图)
deep-research上游(提供研究基础)
tw-hei-intelligence辅助(核实高等教育数据的准确性)
academic-pipeline由其编排(第 3 阶段 + 第 3' 阶段)

版本信息

项目内容
技能版本1.4
最近更新2026-03-08
维护者Cheng-I Wu
依赖技能academic-paper v1.0+(上游/下游集成)
角色多视角学术论文评审模拟器

更新日志

版本日期变更
1.42026-03-08质量评分标准参考(0-100 分评分,每个维度包含 5 个描述等级、加权汇总公式和决策映射);快速模式选择指南;维度评分从可选的 1-5 分升级为必填的 0-100 分,并包含评分标准描述
1.32025-03-05明确 DA 与 R3 的角色边界,并提供具体职责表;提供带有具体示例的 CRITICAL 发现标准;共识分类(CONSENSUS-4/3/SPLIT/DA-CRITICAL);置信度评分加权规则;亚洲与区域期刊参考(TSSCI + 亚太地区 + OA 选项)
1.22026-03添加统计报告标准参考;增强 methodology_reviewer_agent,加入统计报告充分性子步骤
1.12026-02添加 Devil's Advocate Reviewer(第 7 位 Agent),添加重新评审模式,将评审团队从 4 人扩展至 5 人
1.02026-02初始版本:6 个 Agent、4 种模式、3 阶段工作流

评论

支持 Markdown