Back to Details

scientific-thinking-literature-review

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Literature Review

文献综述

Use this skill when the task is to find, screen, synthesize, and cite a body of academic or technical literature.
当任务需要查找、筛选、综合并引用一批学术或技术文献时，使用此 skill。

When to Use

使用场景

  • Building a systematic, scoping, or narrative literature review.
  • Synthesizing the state of the art for a research question.
  • Finding gaps, contradictions, or future-work directions.
  • Preparing citation-backed background sections for papers or reports.
  • Comparing evidence across peer-reviewed papers, preprints, patents, and technical reports.
  • 构建系统性、范围性或叙述性文献综述。
  • 综合回答某个研究问题的最新研究进展。
  • 找出研究空白、矛盾或未来工作方向。
  • 为论文或报告准备有引文支持的背景章节。
  • 对比同行评审论文、预印本、专利和技术报告中的证据。

Review Types

综述类型

  • Narrative review: broad synthesis; useful for orientation.
  • Scoping review: maps concepts, methods, and evidence gaps.
  • Systematic review: predefined protocol, reproducible search, explicit screening and exclusion.
  • Meta-analysis: systematic review plus quantitative effect aggregation.
Ask the user which level of rigor is needed. If unspecified, default to a scoping review for exploratory work and a systematic review for publication or clinical claims.
  • Narrative review（叙述性综述）：广泛综合；适合用于了解整体情况。
  • Scoping review（范围综述）：梳理概念、方法和证据空白。
  • Systematic review（系统综述）：预先定义方案、执行可复现检索，并明确筛选和排除标准。
  • Meta-analysis（Meta 分析）：在系统综述的基础上进行定量效应汇总。
询问用户需要何种严谨程度。如果未指定，探索性工作默认采用 scoping review，涉及发表或临床主张时默认采用 systematic review。

Workflow

工作流

1. Define the Question

1. 定义问题

Convert the prompt into a searchable research question.
For clinical or biomedical work, use PICO:
  • Population
  • Intervention or exposure
  • Comparator
  • Outcome
For technical work, use:
  • system or domain
  • method or intervention
  • comparison baseline
  • evaluation metric
将提示词转换为可检索的研究问题。
对于临床或生物医学工作，使用 PICO：
  • Population（研究人群）
  • Intervention or exposure（干预或暴露）
  • Comparator（对照）
  • Outcome（结局）
对于技术类工作，使用：
  • system or domain（系统或领域）
  • method or intervention（方法或干预）
  • comparison baseline（比较基线）
  • evaluation metric（评估指标）

2. Plan the Search

2. 规划检索

Create a search protocol before collecting sources:
  • databases to search
  • date range
  • languages
  • publication types
  • inclusion criteria
  • exclusion criteria
  • exact search strings
Minimum useful database set:
  • PubMed for biomedical and life-sciences literature.
  • arXiv for CS, math, physics, quantitative biology, and preprints.
  • Semantic Scholar or Crossref for broad academic discovery.
  • Domain-specific sources when relevant, such as clinical-trial registries, patent databases, standards bodies, or official technical docs.
收集来源之前，先制定检索方案：
  • 要检索的数据库
  • 日期范围
  • 语言
  • 出版类型
  • 纳入标准
  • 排除标准
  • 精确检索字符串
最低限度实用的数据库集合：
  • PubMed：用于生物医学和生命科学文献。
  • arXiv：用于计算机科学、数学、物理学、定量生物学及预印本。
  • Semantic Scholar 或 Crossref：用于广泛发现学术文献。
  • 相关领域来源，例如临床试验注册库、专利数据库、标准机构或官方技术文档。

3. Search and Log Evidence

3. 检索并记录证据

Keep a search log that makes the review reproducible:
markdown
| Database | Date searched | Query | Filters | Results | Export |
| --- | --- | --- | --- | ---: | --- |
| PubMed | 2026-05-11 | `("CRISPR"[tiab] OR "Cas9"[tiab]) AND "sickle cell"[tiab]` | 2020:2026, English | 86 | PMID list |
| arXiv | 2026-05-11 | `CRISPR sickle cell gene editing` | q-bio, 2020:2026 | 9 | BibTeX |
Save raw IDs, URLs, DOIs, abstracts, and notes separately from the final prose.
维护检索日志，以确保综述的可复现性：
markdown
| Database | Date searched | Query | Filters | Results | Export |
| --- | --- | --- | --- | ---: | --- |
| PubMed | 2026-05-11 | `("CRISPR"[tiab] OR "Cas9"[tiab]) AND "sickle cell"[tiab]` | 2020:2026, English | 86 | PMID list |
| arXiv | 2026-05-11 | `CRISPR sickle cell gene editing` | q-bio, 2020:2026 | 9 | BibTeX |
将原始 ID、URL、DOI、摘要和备注与最终正文分开保存。

4. Deduplicate

4. 去重

Deduplicate in this order:
  1. DOI
  2. PMID or arXiv ID
  3. exact title
  4. normalized title plus first author and year
Record how many duplicates were removed.
按以下顺序去重：
  1. DOI
  2. PMID 或 arXiv ID
  3. 完全一致的标题
  4. 标准化标题、第一作者和年份的组合
记录去除了多少重复项。

5. Screen Sources

5. 筛选来源

Screen in stages:
  1. title
  2. abstract
  3. full text
For systematic work, record exclusion reasons:
  • wrong population
  • wrong intervention
  • wrong outcome
  • not primary research
  • duplicate
  • unavailable full text
  • outside date range
分阶段筛选：
  1. 标题
  2. 摘要
  3. 全文
对于系统性工作，记录排除原因：
  • 研究对象不符
  • 干预措施不符
  • 结局指标不符
  • 非原始研究
  • 重复文献
  • 无法获取全文
  • 不在日期范围内

6. Extract Data

6. 提取数据

Use a structured extraction table:
markdown
| Study | Design | Population/Data | Method | Comparator | Outcome | Key finding | Limitations |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Author Year | RCT/cohort/review/etc. | sample or corpus | method | baseline | measured outcome | result | caveat |
For technical papers, include dataset, benchmark, metric, baseline, and reproducibility notes.
使用结构化提取表：
markdown
| Study | Design | Population/Data | Method | Comparator | Outcome | Key finding | Limitations |
| --- | --- | --- | --- | --- | --- | --- | --- |
| Author Year | RCT/cohort/review/etc. | sample or corpus | method | baseline | measured outcome | result | caveat |
对于技术类论文，还应包含数据集、benchmark、metric、baseline 和可复现性说明。

7. Synthesize

7. 综合分析

Group evidence by theme rather than summarizing papers one by one.
Useful synthesis lenses:
  • strongest evidence
  • conflicting evidence
  • methodological weaknesses
  • population or dataset limits
  • recency and replication
  • practical implications
  • unanswered questions
Separate claims by confidence:
  • High confidence: replicated, high-quality evidence across sources.
  • Medium confidence: plausible but limited by sample, method, or recency.
  • Low confidence: early, speculative, single-source, or weakly measured.
按主题对证据进行分组，而不是逐篇总结论文。
常用的综合分析视角：
  • 最有力的证据
  • 相互冲突的证据
  • 方法学缺陷
  • 样本人群或数据集局限
  • 时效性和重复验证情况
  • 实际应用
  • 未解决的问题
按置信度区分主张：
  • 高置信度：不同来源中经过重复验证的高质量证据。
  • 中置信度：具有合理性，但受样本、方法或时效性限制。
  • 低置信度：属于早期、推测性、单一来源或测量不充分的证据。

8. Verify Citations

8. 核验引文

Before finalizing:
  • verify DOI, PMID, arXiv ID, or official URL
  • check author names and publication year
  • do not cite a paper for a claim it does not make
  • mark preprints as preprints
  • distinguish reviews from primary evidence
最终定稿前：
  • 核验 DOI、PMID、arXiv ID 或官方 URL
  • 检查作者姓名和出版年份
  • 不得用论文支持其并未提出的主张
  • 将预印本明确标记为预印本
  • 区分综述与原始证据

Output Template

输出模板

markdown
undefined
markdown
undefined

Literature Review: <Topic>

Literature Review: <Topic>

Generated: <date> Review type: <narrative | scoping | systematic | meta-analysis> Search window: <dates> Databases: <list>
Generated: <date> Review type: <narrative | scoping | systematic | meta-analysis> Search window: <dates> Databases: <list>

Research Question

Research Question

Search Strategy

Search Strategy

Inclusion and Exclusion Criteria

Inclusion and Exclusion Criteria

Evidence Summary

Evidence Summary

Thematic Synthesis

Thematic Synthesis

Gaps and Limitations

Gaps and Limitations

References

References

Search Log

Search Log

undefined
undefined

Pitfalls

常见陷阱

  • Do not treat search snippets as evidence.
  • Do not mix preprints, reviews, and primary studies without labeling them.
  • Do not omit negative or conflicting findings.
  • Do not claim systematic-review rigor without a reproducible protocol.
  • Do not use a single database for a broad claim unless the scope is explicitly limited to that database.
  • 不要将检索摘要片段当作证据。
  • 不要在未加标识的情况下混用预印本、综述和原始研究。
  • 不要遗漏负面或相互冲突的研究结果。
  • 没有可复现的方案时，不要声称采用了 systematic review 的严谨程度。
  • 除非明确将范围限定在该数据库内，否则不要仅使用单一数据库支撑广泛主张。