Back to Details

literature-review

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Literature Review

文献综述

Conduct deep literature reviews through multi-perspective dialogue and systematic search.
通过多视角对话和系统性搜索开展深度文献综述。

Input

输入

  • $0
    — Research topic or question
  • $1
    — Optional: specific focus or angle
  • $0
    — 研究主题或问题
  • $1
    — 可选：特定研究重点或视角

References

参考资料

  • Multi-perspective dialogue prompts (STORM): 
    ~/.claude/skills/literature-review/references/dialogue-prompts.md
  • Literature review workflow (AgentLaboratory): 
    ~/.claude/skills/literature-review/references/review-workflow.md
  • 多视角对话提示词（STORM）：
    ~/.claude/skills/literature-review/references/dialogue-prompts.md
  • 文献综述工作流（AgentLaboratory）：
    ~/.claude/skills/literature-review/references/review-workflow.md

Scripts (from literature-search skill)

脚本（来自literature-search技能）

bash
undefined
bash
undefined

Search Semantic Scholar

Search Semantic Scholar

python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py --query "topic" --max-results 20
python ~/.claude/skills/deep-research/scripts/search_semantic_scholar.py --query "topic" --max-results 20

Search OpenAlex

Search OpenAlex

python ~/.claude/skills/literature-search/scripts/search_openalex.py --query "topic" --max-results 20
python ~/.claude/skills/literature-search/scripts/search_openalex.py --query "topic" --max-results 20

Search arXiv

Search arXiv

python ~/.claude/skills/deep-research/scripts/search_arxiv.py --query "topic" --max-results 10
undefined
python ~/.claude/skills/deep-research/scripts/search_arxiv.py --query "topic" --max-results 10
undefined

Workflow

工作流

Step 1: Generate Expert Personas (from STORM)

步骤1：生成专家角色（来自STORM）

Given the topic, create 3-5 diverse expert personas:
  • Each represents a different perspective, role, or research angle
  • Example: "ML systems researcher focused on efficiency", "Theoretical statistician concerned with guarantees"
  • Use the persona generation prompts from references
给定研究主题，创建3-5个不同的专家角色：
  • 每个角色代表不同的视角、职位或研究方向
  • 示例：“专注于效率的ML systems研究者”、“关注性能保障的理论统计学家”
  • 使用参考资料中的角色生成提示词

Step 2: Multi-Perspective Dialogue

步骤2：多视角对话

For each persona, simulate a multi-turn Q&A conversation:
  1. Persona asks a question from their unique angle
  2. Generate search queries from the question
  3. Search literature using the search scripts
  4. Synthesize an answer grounded in retrieved papers with inline citations
  5. Record the dialogue turn with search results
  6. Repeat for 3-5 turns per persona
  7. End when persona says "Thank you so much for your help!"
针对每个专家角色，模拟多轮问答对话：
  1. 专家角色从其独特视角提出问题
  2. 根据问题生成搜索查询词
  3. 使用搜索脚本检索文献
  4. 基于检索到的论文整合答案，并添加内联引用
  5. 记录包含搜索结果的对话轮次
  6. 每个角色重复3-5轮对话
  7. 当角色说“非常感谢你的帮助！”时结束对话

Step 3: Synthesize Knowledge

步骤3：知识整合

  • Combine all persona conversations into a unified knowledge base
  • Remove redundancy across personas
  • Organize by theme/subtopic
  • Generate an outline based on the collected information
  • 将所有专家角色的对话整合为统一的知识库
  • 去除不同角色内容中的冗余信息
  • 按主题/子主题进行组织
  • 根据收集到的信息生成大纲

Step 4: Generate Literature Review

步骤4：生成文献综述

  • Write a structured review organized by the generated outline
  • Every claim must be supported by a citation
  • Include a summary table of key papers (method, contribution, limitations)
  • 根据生成的大纲撰写结构化的综述
  • 每个观点都必须有引用支持
  • 包含关键论文的汇总表格（方法、贡献、局限性）

Output

输出

A structured literature review with:
  1. Outline — Hierarchical topic structure
  2. Per-section summaries — Each grounded in retrieved papers
  3. Paper database — Structured entries for all reviewed papers
  4. Knowledge gaps — Identified areas needing further investigation
一份结构化的文献综述，包含：
  1. 大纲 — 分层主题结构
  2. 各章节摘要 — 均基于检索到的论文
  3. 论文数据库 — 所有综述论文的结构化条目
  4. 知识空白 — 已识别的需进一步研究的领域

Rules

规则

  • Every sentence in the review must be supported by gathered information
  • If information is not found, explicitly state the gap
  • Cite broadly — cover diverse approaches, not just the most popular
  • Include recent papers (last 2-3 years) alongside foundational work
  • Use inline citations: "Smith et al. [1] propose..."
  • 综述中的每一句话都必须有收集到的信息支持
  • 如果未找到相关信息，需明确说明空白
  • 广泛引用 — 涵盖多种研究方法，而非仅关注主流研究
  • 除经典文献外，还需包含近年（过去2-3年）的论文
  • 使用内联引用格式："Smith et al. [1] propose..."

Related Skills

相关技能

  • Upstream: literature-search, deep-research
  • Downstream: related-work-writing, research-planning
  • See also: survey-generation
  • 上游技能：literature-search、deep-research
  • 下游技能：related-work-writing、research-planning
  • 另见：survey-generation