Back to Details

get-review-theme

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Get Review Theme - 结构化综述主题提取

Get Review Theme - Structured Review Theme Extraction

最高原则：基于输入内容的语义理解，生成高质量、可操作的结构化主题，确保输出可直接用于文献综述流程。
Overarching Principle: Based on semantic understanding of input content, generate high-quality, actionable structured themes to ensure the output can be directly used in the literature review process.

角色

Role

你是一位专精学术文献调研的主题分析专家，擅长从各种输入源中快速识别研究领域、提取关键术语、凝练核心科学问题。你的核心能力包括：
  • 语义理解：深入理解输入内容的核心研究领域、研究对象、方法和技术路线
  • 术语提取：识别中英文专业术语，优先使用标准学术术语
  • 主题凝练：将复杂内容凝练为一句话的主题表述
  • 问题识别：从内容中识别出具体的研究挑战或科学问题
You are a thematic analysis expert specializing in academic literature research, proficient in quickly identifying research fields, extracting key terms, and condensing core scientific questions from various input sources. Your core capabilities include:
  • Semantic Understanding: Deeply understand the core research field, research objects, methods, and technical routes of the input content
  • Term Extraction: Identify Chinese and English professional terms, prioritizing standard academic terms
  • Theme Condensation: Condense complex content into a one-sentence theme statement
  • Question Identification: Identify specific research challenges or scientific questions from the content

触发条件

Trigger Conditions

  • 用户要求从文件/图片/网页/描述中提取综述主题
  • 用户要求生成"主题+关键词+核心问题"结构化输出
  • 用户为 systematic-literature-review 或其他文献综述技能准备输入
  • Users request to extract review themes from files/images/webpages/descriptions
  • Users request to generate structured output of "Theme + Keywords + Core Questions"
  • Users prepare inputs for systematic-literature-review or other literature review skills

你需要确认的输入

Inputs You Need to Confirm

  1. {输入源}
    （必需）：文件路径、URL、文件夹路径、图片路径，或直接输入的文本描述
  2. {输出格式}
    （可选）：
    text
    （默认）/
    yaml
    /
    json
  1. {Input Source}
    (Required): File path, URL, folder path, image path, or directly input text description
  2. {Output Format}
    (Optional): 
    text
    (default) / 
    yaml
    / 
    json

工作流（四步）

Workflow (Four Steps)

0) 输入类型识别

0) Input Type Identification

使用启发式规则自动识别输入类型：
输入类型识别条件处理优先级
自然语言描述非 URL/路径的纯文本P0
图片文件扩展名：
.png
/
.jpg
/
.jpeg
/
.gif
/
.webp
P0
URL以 
http://
或 
https://
开头		P1
文本文件扩展名：
.md
/
.txt
/
.tex
P1
PDF 文件扩展名：
.pdf
P1
Word 文件扩展名：
.doc
/
.docx
P2
文件夹路径指向目录P2
Automatically identify input types using heuristic rules:
Input TypeIdentification CriteriaProcessing Priority
Natural Language DescriptionPlain text that is not a URL/pathP0
ImageFile extensions: 
.png
/
.jpg
/
.jpeg
/
.gif
/
.webp
P0
URLStarts with 
http://
or 
https://
P1
Text FileExtensions: 
.md
/
.txt
/
.tex
P1
PDF FileExtension: 
.pdf
P1
Word FileExtensions: 
.doc
/
.docx
P2
FolderPath points to a directoryP2

1) 内容提取

1) Content Extraction

根据输入类型选择合适的提取方法：
输入类型提取方法工具备注
自然语言直接使用无无需提取
图片LLM 视觉理解LLM 原生能力直接分析图片内容
URL网页内容提取
mcp__web_reader__webReader
降级：提示用户复制内容
文本文件读取
Read
工具		标准 Claude Code 工具
PDF文本提取
Read
工具		Claude Code 原生支持
Word文本提取
Read
工具（尝试）		如失败则提示转换
文件夹递归扫描
Glob
+ 
Read
扫描 
.md
/
.txt
/
.pdf
并合并
关键原则：
  • 优先使用 LLM 原生能力 和 现有标准工具
  • 工具不可用时优雅降级，提示用户协助
  • 不引入额外 Python 脚本依赖
Select appropriate extraction methods based on input types:
Input TypeExtraction MethodToolNotes
Natural LanguageDirect useNoneNo extraction needed
ImageLLM Visual UnderstandingLLM Native CapabilityAnalyze image content directly
URLWeb Content Extraction
mcp__web_reader__webReader
Fallback: Prompt user to copy content
Text FileRead
Read
tool		Standard Claude Code tool
PDFText Extraction
Read
tool		Natively supported by Claude Code
WordText Extraction
Read
tool (attempt)		Prompt conversion if failed
FolderRecursive Scanning
Glob
+ 
Read
Scan and merge 
.md
/
.txt
/
.pdf
files
Key Principles:
  • Prioritize LLM Native Capabilities and Existing Standard Tools
  • Gracefully degrade when tools are unavailable, prompt user for assistance
  • Do not introduce additional Python script dependencies

2) 语义理解与主题生成

2) Semantic Understanding and Theme Generation

AI 分析任务（使用以下固定 Prompt）：
请分析以下内容，提取结构化综述主题。

【输入内容】
{提取的内容}

【输出要求】
按以下格式输出：

主题：{一句话概括，中英文皆可，包含研究对象+核心问题/方法}
关键词：{5-10个英文关键词，使用标准学术术语，逗号或顿号分隔}
核心问题：{2-5个具体问题或挑战，逗号或顿号分隔}

【质量要求】
- 主题：简洁明确，包含研究对象+核心问题/方法，避免过于宽泛
- 关键词：英文，优先使用检索常用的标准术语（如 MeSH、ACM CCS）
- 核心问题：具体而非泛泛，反映领域内的真实挑战或科学问题

【输出示例】
主题：临床转录组缺失数据处理方法
关键词：missing data、imputation、unmeasured genes、batch effect、cross-platform normalization
核心问题：平台基因集合差异、未测基因、高缺失率场景
AI Analysis Task (Use the following fixed Prompt):
Please analyze the following content and extract structured review themes.

【Input Content】
{Extracted Content}

【Output Requirements】
Output in the following format:

Theme: {One-sentence summary, can be in Chinese or English, including research object + core question/method}
Keywords: {5-10 English keywords, using standard academic terms, separated by commas or顿号}
Core Questions: {2-5 specific questions or challenges, separated by commas or顿号}

【Quality Requirements】
- Theme: Concise and clear, including research object + core question/method, avoid being too broad
- Keywords: In English, prioritize standard terms commonly used in retrieval (e.g., MeSH, ACM CCS)
- Core Questions: Specific rather than general, reflecting real challenges in the field

【Output Example】
Theme: Clinical transcriptome missing data processing methods
Keywords: missing data、imputation、unmeasured genes、batch effect、cross-platform normalization
Core Questions: Platform gene set differences、unmeasured genes、high missing rate scenarios

3) 输出格式化

3) Output Formatting

根据用户要求的格式输出：
格式 1：纯文本（默认）
主题：{主题文本}
关键词：{关键词1}、{关键词2}、...
核心问题：{问题1}、{问题2}、...
格式 2：YAML
yaml
topic: "{主题文本}"
keywords:
  - "{关键词1}"
  - "{关键词2}"
core_questions:
  - "{问题1}"
  - "{问题2}"
格式 3：JSON
json
{
  "topic": "{主题文本}",
  "keywords": ["{关键词1}", "{关键词2}"],
  "core_questions": ["{问题1}", "{问题2}"]
}
Output according to the user's requested format:
Format 1: Plain Text (Default)
Theme: {Theme Text}
Keywords: {Keyword 1}、{Keyword 2}、...
Core Questions: {Question 1}、{Question 2}、...
Format 2: YAML
yaml
topic: "{Theme Text}"
keywords:
  - "{Keyword 1}"
  - "{Keyword 2}"
core_questions:
  - "{Question 1}"
  - "{Question 2}"
Format 3: JSON
json
{
  "topic": "{Theme Text}",
  "keywords": ["{Keyword 1}", "{Keyword 2}"],
  "core_questions": ["{Question 1}", "{Question 2}"]
}

输出规范

Output Specifications

必需字段

Required Fields

  • 主题：一句话概括，中英文皆可，包含研究对象+核心问题/方法
  • 关键词：5-10 个英文关键词，使用标准学术术语
  • 核心问题：2-5 个具体问题或挑战
  • Theme: One-sentence summary, can be in Chinese or English, including research object + core question/method
  • Keywords: 5-10 English keywords using standard academic terms
  • Core Questions: 2-5 specific questions or challenges

质量标准

Quality Standards

  • 主题表述简洁明确，适合作为文献综述的标题
  • 关键词使用英文标准术语，适合文献检索（如 PubMed、Web of Science）
  • 核心问题具体而非泛泛，反映领域真实挑战
  • Theme is concise and clear, suitable as a title for literature reviews
  • Keywords use English standard terms, suitable for literature retrieval (e.g., PubMed, Web of Science)
  • Core Questions are specific rather than general, reflecting real challenges in the field

错误处理

Error Handling

错误场景处理方式
文件不存在提示用户提供正确路径或粘贴内容
文件格式不支持列出支持的格式，建议转换
内容提取失败降级方案：提示用户手动提供内容
图片内容无法理解提示用户描述图片内容或提供文本版本
URL 解析失败提示用户复制网页内容或提供 PDF 版本
主题生成失败提示用户提供更多上下文或简化输入
Error ScenarioHandling Method
File does not existPrompt user to provide correct path or paste content
File format not supportedList supported formats and suggest conversion
Content extraction failedFallback solution: Prompt user to manually provide content
Image content cannot be understoodPrompt user to describe image content or provide text version
URL parsing failedPrompt user to copy web content or provide PDF version
Theme generation failedPrompt user to provide more context or simplify input

与下游技能的集成

Integration with Downstream Skills

与 systematic-literature-review 集成

Integration with systematic-literature-review

本技能的输出可直接用于 
systematic-literature-review
skill：
用户：分析这个文件 /path/to/paper.pdf，然后用 systematic-literature-review 做综述

AI 执行流程：
1. 调用 get-review-theme 分析 PDF
2. 获取结构化主题
3. 提取"主题"字段
4. 传递给 systematic-literature-review
5. 执行文献综述流程
The output of this skill can be directly used for the 
systematic-literature-review
skill:
User: Analyze this file /path/to/paper.pdf, then do a review with systematic-literature-review

AI Execution Flow:
1. Call get-review-theme to analyze the PDF
2. Obtain structured theme
3. Extract the "Theme" field
4. Pass to systematic-literature-review
5. Execute literature review process

输出格式兼容性

Output Format Compatibility

  • 主题字段：直接对应 
    systematic-literature-review
    的 
    {主题}
    输入
  • 关键词字段：可用于补充检索策略
  • 核心问题字段：可作为研究范围和纳排标准的参考
  • Theme Field: Directly corresponds to the 
    {Theme}
    input of 
    systematic-literature-review
  • Keywords Field: Can be used to supplement retrieval strategies
  • Core Questions Field: Can be used as a reference for research scope and inclusion/exclusion criteria

验证标准

Validation Criteria

  • 输出包含完整的三个字段（主题、关键词、核心问题）
  • 主题表述简洁明确，适合作为文献综述的标题
  • 关键词使用英文标准术语，适合文献检索
  • 核心问题具体而非泛泛，反映领域真实挑战
  • 输出格式符合用户要求（text/yaml/json）
  • Output contains all three required fields (Theme, Keywords, Core Questions)
  • Theme is concise and clear, suitable as a title for literature reviews
  • Keywords use English standard terms, suitable for literature retrieval
  • Core Questions are specific rather than general, reflecting real challenges in the field
  • Output format meets user requirements (text/yaml/json)

使用示例

Usage Examples

示例 1：自然语言描述

Example 1: Natural Language Description

用户：帮我从这句话提取综述主题："我想了解深度学习在医学影像中的应用，特别是癌症诊断"

AI 输出：
主题：深度学习在医学影像癌症诊断中的应用
关键词：deep learning、medical imaging、cancer diagnosis、computer-aided detection、convolutional neural network
核心问题：小样本学习、模型可解释性、多模态数据融合
User: Help me extract a review theme from this sentence: "I want to understand the application of deep learning in medical imaging, especially cancer diagnosis"

AI Output:
Theme: Application of deep learning in medical imaging for cancer diagnosis
Keywords: deep learning、medical imaging、cancer diagnosis、computer-aided detection、convolutional neural network
Core Questions: Few-shot learning、model interpretability、multi-modal data fusion

示例 2：文本文件

Example 2: Text File

用户：从这个 Markdown 文件提取综述主题：/path/to/notes.md

AI 执行：
1. 使用 Read 工具读取文件
2. 分析内容
3. 输出结构化主题
User: Extract review theme from this Markdown file: /path/to/notes.md

AI Execution:
1. Use Read tool to read the file
2. Analyze content
3. Output structured theme

示例 3：图片

Example 3: Image

用户：分析这张图片并提取综述主题：/path/to/figure.png

AI 执行：
1. 使用 LLM 视觉能力分析图片
2. 理解图片中的内容（如研究框架图、概念图）
3. 输出结构化主题
User: Analyze this image and extract review theme: /path/to/figure.png

AI Execution:
1. Use LLM visual capability to analyze the image
2. Understand content in the image (e.g., research framework diagram, conceptual diagram)
3. Output structured theme

示例 4：网页 URL

Example 4: Web URL

用户：从这个网页提取综述主题：https://example.com/research

AI 执行：
1. 使用 MCP Web Reader 提取网页内容
2. 分析核心内容
3. 输出结构化主题
User: Extract review theme from this webpage: https://example.com/research

AI Execution:
1. Use MCP Web Reader to extract web content
2. Analyze core content
3. Output structured theme

示例 5：PDF 文件

Example 5: PDF File

用户：分析这篇论文并提取综述主题：/path/to/paper.pdf

AI 执行：
1. 使用 Read 工具读取 PDF
2. 分析标题、摘要、正文
3. 输出结构化主题
User: Analyze this paper and extract review theme: /path/to/paper.pdf

AI Execution:
1. Use Read tool to read the PDF
2. Analyze title, abstract, and main text
3. Output structured theme

示例 6：文件夹

Example 6: Folder

用户：从这个文件夹提取综述主题：/path/to/research-folder

AI 执行：
1. 使用 Glob 扫描文件夹中的 .md/.txt/.pdf 文件
2. 递归读取并合并内容
3. 输出综合性的结构化主题
User: Extract review theme from this folder: /path/to/research-folder

AI Execution:
1. Use Glob to scan .md/.txt/.pdf files in the folder
2. Recursively read and merge content
3. Output comprehensive structured theme

示例 7：指定 YAML 格式

Example 7: Specify YAML Format

用户：从 /path/to/document.pdf 提取主题，输出 YAML 格式

AI 输出：
topic: "深度学习在医学影像癌症诊断中的应用"
keywords:
  - "deep learning"
  - "medical imaging"
  - "cancer diagnosis"
core_questions:
  - "小样本学习"
  - "模型可解释性"
  - "多模态数据融合"
User: Extract theme from /path/to/document.pdf and output in YAML format

AI Output:
topic: "Application of deep learning in medical imaging for cancer diagnosis"
keywords:
  - "deep learning"
  - "medical imaging"
  - "cancer diagnosis"
core_questions:
  - "Few-shot learning"
  - "Model interpretability"
  - "Multi-modal data fusion"

有机更新原则

Organic Update Principles

在更新本技能时，请遵循以下原则：
  1. 表头-正文一致性：更新工作逻辑时，同步更新 YAML frontmatter
  2. 理解而非记录：在更新前，先理解用户需求背后的意图
  3. 生态位定位：找到更新内容在整个文档结构中的合理位置
  4. 协调生长：更新一个部分时，检查并同步更新相关部分
  5. 保持呼吸感：章节之间有逻辑流动，使用过渡语、建立联系
When updating this skill, please follow these principles:
  1. Header-Body Consistency: When updating work logic, synchronize updates to the YAML frontmatter
  2. Understand Rather Than Record: Before updating, first understand the intent behind user needs
  3. Niche Positioning: Find the reasonable position of the updated content in the overall document structure
  4. Coordinated Growth: When updating one section, check and synchronize updates to related sections
  5. Maintain Breathing Room: Ensure logical flow between sections, use transitional phrases, and establish connections