research-lit

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Research Literature Review

研究文献综述

Research topic: $ARGUMENTS

研究主题：$ARGUMENTS

Constants

常量

PAPER_LIBRARY — Local directory containing user's paper collection (PDFs). Check these paths in order:
1. ```
papers/
```
  in the current project directory
2. ```
literature/
```
  in the current project directory
3. Custom path specified by user in
```
CLAUDE.md
```
  under
```
## Paper Library
```
MAX_LOCAL_PAPERS = 20 — Maximum number of local PDFs to scan (read first 3 pages each). If more are found, prioritize by filename relevance to the topic.
ARXIV_DOWNLOAD = false — When
```
true
```
, download top 3-5 most relevant arXiv PDFs to PAPER_LIBRARY after search. When
```
false
```
(default), only fetch metadata (title, abstract, authors) via arXiv API — no files are downloaded.
ARXIV_MAX_DOWNLOAD = 5 — Maximum number of PDFs to download when
```
ARXIV_DOWNLOAD = true
```
.

💡 Overrides:
/research-lit "topic" — paper library: ~/my_papers/
— custom local PDF path
/research-lit "topic" — sources: zotero, local
— only search Zotero + local PDFs
/research-lit "topic" — sources: zotero
— only search Zotero
/research-lit "topic" — sources: web
— only search the web (skip all local)
/research-lit "topic" — arxiv download: true
— download top relevant arXiv PDFs
/research-lit "topic" — arxiv download: true, max download: 10
— download up to 10 PDFs

PAPER_LIBRARY — 本地存储用户论文集（PDF格式）的目录。按以下顺序检查这些路径：
1. 当前项目目录下的
```
papers/
```
2. 当前项目目录下的
```
literature/
```
3. 用户在
```
CLAUDE.md
```
  的
```
## Paper Library
```
  部分指定的自定义路径
MAX_LOCAL_PAPERS = 20 — 最多扫描20份本地PDF（每份读取前3页）。如果找到更多文件，优先选择文件名与主题相关性高的论文。
ARXIV_DOWNLOAD = false — 设为
```
true
```
时，搜索后将最相关的3-5篇arXiv PDF下载到PAPER_LIBRARY；默认设为
```
false
```
时，仅通过arXiv API获取元数据（标题、摘要、作者），不下载文件。
ARXIV_MAX_DOWNLOAD = 5 — 当
```
ARXIV_DOWNLOAD = true
```
时，最多下载的PDF数量。

💡 覆盖设置：
/research-lit "topic" — paper library: ~/my_papers/
— 自定义本地PDF路径
/research-lit "topic" — sources: zotero, local
— 仅搜索Zotero + 本地PDF
/research-lit "topic" — sources: zotero
— 仅搜索Zotero
/research-lit "topic" — sources: web
— 仅搜索网络（跳过所有本地资源）
/research-lit "topic" — arxiv download: true
— 下载最相关的arXiv PDF
/research-lit "topic" — arxiv download: true, max download: 10
— 最多下载10份PDF

Data Sources

数据源

This skill checks multiple sources in priority order. All are optional — if a source is not configured or not requested, skip it silently.

本技能按优先级顺序检查多个数据源。所有数据源均为可选——若某个数据源未配置或未被请求，则自动跳过。

Source Selection

数据源选择

Parse

$ARGUMENTS

for a

— sources:

directive:

If
— sources:
is specified: Only search the listed sources (comma-separated). Valid values:
```
zotero
```
,
```
obsidian
```
,
```
local
```
,
```
web
```
,
```
all
```
.
If not specified: Default to
```
all
```
— search every available source in priority order.

Examples:

/research-lit "diffusion models"                        → all (default)
/research-lit "diffusion models" — sources: all         → all
/research-lit "diffusion models" — sources: zotero      → Zotero only
/research-lit "diffusion models" — sources: zotero, web → Zotero + web
/research-lit "diffusion models" — sources: local       → local PDFs only
/research-lit "topic" — sources: obsidian, local, web   → skip Zotero

解析

$ARGUMENTS

中的

— sources:

指令：

若指定
— sources:
：仅搜索列出的数据源（用逗号分隔）。有效值：
```
zotero
```
,
```
obsidian
```
,
```
local
```
,
```
web
```
,
```
all
```
。
若未指定：默认使用
```
all
```
——按优先级顺序搜索所有可用数据源。

示例：

/research-lit "diffusion models"                        → 全部（默认）
/research-lit "diffusion models" — sources: all         → 全部
/research-lit "diffusion models" — sources: zotero      → 仅Zotero
/research-lit "diffusion models" — sources: zotero, web → Zotero + 网络
/research-lit "diffusion models" — sources: local       → 仅本地PDF
/research-lit "topic" — sources: obsidian, local, web   → 跳过Zotero

Source Table

数据源表格

Priority	Source	ID	How to detect	What it provides
1	Zotero (via MCP)	`zotero`	Try calling any `mcp__zotero__*` tool — if unavailable, skip	Collections, tags, annotations, PDF highlights, BibTeX, semantic search
2	Obsidian (via MCP)	`obsidian`	Try calling any `mcp__obsidian-vault__*` tool — if unavailable, skip	Research notes, paper summaries, tagged references, wikilinks
3	Local PDFs	`local`	`Glob: papers/*/.pdf, literature/*/.pdf`	Raw PDF content (first 3 pages)
4	Web search	`web`	Always available (WebSearch)	arXiv, Semantic Scholar, Google Scholar

Graceful degradation: If no MCP servers are configured, the skill works exactly as before (local PDFs + web search). Zotero and Obsidian are pure additions.

优先级	数据源	标识	检测方式	提供内容
1	Zotero（通过MCP）	`zotero`	尝试调用任意 `mcp__zotero__*` 工具——若不可用则跳过	文集、标签、注释、PDF高亮内容、BibTeX、语义搜索
2	Obsidian（通过MCP）	`obsidian`	尝试调用任意 `mcp__obsidian-vault__*` 工具——若不可用则跳过	研究笔记、论文摘要、带标签的参考文献、维基链接
3	本地PDF	`local`	`Glob: papers/*/.pdf, literature/*/.pdf`	原始PDF内容（前3页）
4	网络搜索	`web`	始终可用（WebSearch）	arXiv、Semantic Scholar、Google Scholar

优雅降级：若未配置MCP服务器，本技能仍可正常工作（本地PDF + 网络搜索）。Zotero和Obsidian是额外扩展的数据源。

Workflow

工作流程

Step 0a: Search Zotero Library (if available)

步骤0a：搜索Zotero图书馆（若可用）

Skip this step entirely if Zotero MCP is not configured.

Try calling a Zotero MCP tool (e.g., search). If it succeeds:

Search by topic: Use the Zotero search tool to find papers matching the research topic
Read collections: Check if the user has a relevant collection/folder for this topic
Extract annotations: For highly relevant papers, pull PDF highlights and notes — these represent what the user found important
Export BibTeX: Get citation data for relevant papers (useful for
```
/paper-write
```
later)
Compile results: For each relevant Zotero entry, extract:
- Title, authors, year, venue
- User's annotations/highlights (if any)
- Tags the user assigned
- Which collection it belongs to

📚 Zotero annotations are gold — they show what the user personally highlighted as important, which is far more valuable than generic summaries.

若未配置Zotero MCP，则完全跳过此步骤。

尝试调用Zotero MCP工具（如搜索工具）。若调用成功：

按主题搜索：使用Zotero搜索工具查找与研究主题匹配的论文
查看文集：检查用户是否有与该主题相关的文集/文件夹
提取注释：对于高度相关的论文，提取PDF高亮内容和笔记——这些内容代表用户认为重要的信息
导出BibTeX：获取相关论文的引用数据（后续可用于
```
/paper-write
```
功能）
整理结果：为每个相关的Zotero条目提取以下信息：
- 标题、作者、年份、发表会议/期刊
- 用户的注释/高亮内容（若有）
- 用户添加的标签
- 所属的文集

📚 Zotero注释是黄金资源——它们展示了用户个人认为重要的内容，比通用摘要更有价值。

Step 0b: Search Obsidian Vault (if available)

步骤0b：搜索Obsidian库（若可用）

Skip this step entirely if Obsidian MCP is not configured.

Try calling an Obsidian MCP tool (e.g., search). If it succeeds:

Search vault: Search for notes related to the research topic
Check tags: Look for notes tagged with relevant topics (e.g.,
```
#diffusion-models
```
,
```
#paper-review
```
)
Read research notes: For relevant notes, extract the user's own summaries and insights
Follow links: If notes link to other relevant notes (wikilinks), follow them for additional context
Compile results: For each relevant note:
- Note title and path
- User's summary/insights
- Links to other notes (research graph)
- Any frontmatter metadata (paper URL, status, rating)

📝 Obsidian notes represent the user's processed understanding — more valuable than raw paper content for understanding their perspective.

若未配置Obsidian MCP，则完全跳过此步骤。

尝试调用Obsidian MCP工具（如搜索工具）。若调用成功：

搜索库内容：搜索与研究主题相关的笔记
检查标签：查找带有相关主题标签的笔记（如
```
#diffusion-models
```
,
```
#paper-review
```
）
读取研究笔记：对于相关笔记，提取用户自己的摘要和见解
跟踪链接：若笔记链接到其他相关笔记（维基链接），则跟踪这些链接以获取更多上下文信息
整理结果：为每个相关笔记提取以下信息：
- 笔记标题和路径
- 用户的摘要/见解
- 指向其他笔记的链接（研究图谱）
- 任何前置元数据（论文URL、状态、评分）

📝 Obsidian笔记代表了用户的已处理的理解——对于了解用户的视角，比原始论文内容更有价值。

Step 0c: Scan Local Paper Library

步骤0c：扫描本地论文库

Before searching online, check if the user already has relevant papers locally:

Locate library: Check PAPER_LIBRARY paths for PDF files
```
Glob: papers/**/*.pdf, literature/**/*.pdf
```
De-duplicate against Zotero: If Step 0a found papers, skip any local PDFs already covered by Zotero results (match by filename or title).
Filter by relevance: Match filenames and first-page content against the research topic. Skip clearly unrelated papers.
Summarize relevant papers: For each relevant local PDF (up to MAX_LOCAL_PAPERS):
- Read first 3 pages (title, abstract, intro)
- Extract: title, authors, year, core contribution, relevance to topic
- Flag papers that are directly related vs tangentially related
Build local knowledge base: Compile summaries into a "papers you already have" section. This becomes the starting point — external search fills the gaps.

📚 If no local papers are found, skip to Step 1. If the user has a comprehensive local collection, the external search can be more targeted (focus on what's missing).

在进行在线搜索前，先检查用户本地是否已有相关论文：

定位库路径：检查PAPER_LIBRARY路径中的PDF文件
```
Glob: papers/**/*.pdf, literature/**/*.pdf
```
与Zotero去重：若步骤0a已找到论文，则跳过Zotero结果中已包含的本地PDF（通过文件名或标题匹配）。
按相关性筛选：将文件名和第一页内容与研究主题匹配，跳过明显不相关的论文。
总结相关论文：对于每篇相关的本地PDF（最多MAX_LOCAL_PAPERS篇）：
- 读取前3页（标题、摘要、引言）
- 提取：标题、作者、年份、核心贡献、与主题的相关性
- 标记直接相关和间接相关的论文
构建本地知识库：将摘要整理成“您已有的论文”部分。这将作为后续工作的起点——外部搜索将填补缺失的内容。

📚 若未找到本地论文，则直接跳至步骤1。若用户已有全面的本地论文集，外部搜索可更具针对性（专注于缺失的内容）。

Step 1: Search (external)

步骤1：（外部）搜索

Use WebSearch to find recent papers on the topic
Check arXiv, Semantic Scholar, Google Scholar
Focus on papers from last 2 years unless studying foundational work
De-duplicate: Skip papers already found in Zotero, Obsidian, or local library

arXiv API search (always runs, no download by default):

Locate the fetch script and search arXiv directly:

bash

undefined

使用WebSearch查找与主题相关的近期论文
检查arXiv、Semantic Scholar、Google Scholar
除非研究基础理论，否则重点关注近2年的论文
去重：跳过已在Zotero、Obsidian或本地库中找到的论文

arXiv API搜索（始终运行，默认不下载）：

定位获取脚本并直接搜索arXiv：

bash

undefined

Try to find arxiv_fetch.py

尝试查找arxiv_fetch.py

SCRIPT=$(find tools/ -name "arxiv_fetch.py" 2>/dev/null | head -1)

If not found, check ARIS install

若未找到，检查ARIS安装目录

[ -z "$SCRIPT" ] && SCRIPT=$(find ~/.claude/skills/arxiv/ -name "arxiv_fetch.py" 2>/dev/null | head -1)

Search arXiv API for structured results (title, abstract, authors, categories)

搜索arXiv API获取结构化结果（标题、摘要、完整作者列表、分类、日期）

python3 "$SCRIPT" search "QUERY" --max 10


If `arxiv_fetch.py` is not found, fall back to WebSearch for arXiv (same as before).

The arXiv API returns structured metadata (title, abstract, full author list, categories, dates) — richer than WebSearch snippets. Merge these results with WebSearch findings and de-duplicate.

**Optional PDF download** (only when `ARXIV_DOWNLOAD = true`):

After all sources are searched and papers are ranked by relevance:
```bash

python3 "$SCRIPT" search "QUERY" --max 10


若未找到`arxiv_fetch.py`，则回退到使用WebSearch搜索arXiv（与之前的方式相同）。

arXiv API返回结构化元数据（标题、摘要、完整作者列表、分类、日期）——比WebSearch的片段内容更丰富。将这些结果与WebSearch的结果合并并去重。

**可选PDF下载**（仅当`ARXIV_DOWNLOAD = true`时启用）：

在搜索所有数据源并按相关性对论文排序后：
```bash

Download top N most relevant arXiv papers

下载相关性最高的N篇arXiv论文

python3 "$SCRIPT" download ARXIV_ID --dir papers/

- Only download papers ranked in the top ARXIV_MAX_DOWNLOAD by relevance
- Skip papers already in the local library
- 1-second delay between downloads (rate limiting)
- Verify each PDF > 10 KB

python3 "$SCRIPT" download ARXIV_ID --dir papers/

- 仅下载相关性排名前ARXIV_MAX_DOWNLOAD的论文
- 跳过已在本地库中的论文
- 下载间隔1秒（速率限制）
- 验证每个PDF文件大小大于10 KB

Step 2: Analyze Each Paper

步骤2：分析每篇论文

For each relevant paper (from all sources), extract:

Problem: What gap does it address?
Method: Core technical contribution (1-2 sentences)
Results: Key numbers/claims
Relevance: How does it relate to our work?
Source: Where we found it (Zotero/Obsidian/local/web) — helps user know what they already have vs what's new

对于所有数据源中的相关论文，提取以下信息：

问题：该论文解决了什么研究空白？
方法：核心技术贡献（1-2句话）
结果：关键数据/结论
相关性：该论文与我们的研究工作有何关联？
来源：论文的获取渠道（Zotero/Obsidian/本地/网络）——帮助用户区分已有资源和新资源

Step 3: Synthesize

步骤3：综合分析

Group papers by approach/theme
Identify consensus vs disagreements in the field
Find gaps that our work could fill
If Obsidian notes exist, incorporate the user's own insights into the synthesis

按方法/主题对论文分组
识别领域内的共识与分歧
找出我们的研究工作可以填补的空白
若存在Obsidian笔记，将用户的个人见解融入综合分析中

Step 4: Output

步骤4：输出结果

Present as a structured literature table:

| Paper | Venue | Method | Key Result | Relevance to Us | Source |
|-------|-------|--------|------------|-----------------|--------|

Plus a narrative summary of the landscape (3-5 paragraphs).

If Zotero BibTeX was exported, include a

references.bib

snippet for direct use in paper writing.

以结构化的文献表格形式呈现：

| 论文 | 发表会议/期刊 | 方法 | 关键结果 | 与我们研究的相关性 | 来源 |
|-------|-------|--------|------------|-----------------|--------|

外加一段关于研究领域现状的叙述性摘要（3-5段）。

若已导出Zotero BibTeX，则包含

references.bib

片段，可直接用于论文写作。

Step 5: Save (if requested)

步骤5：保存（若请求）

Save paper PDFs to
```
literature/
```
or
```
papers/
```
Update related work notes in project memory
If Obsidian is available, optionally create a literature review note in the vault

将论文PDF保存至
```
literature/
```
或
```
papers/
```
目录
更新项目记忆中的相关研究工作笔记
若Obsidian可用，可选择在库中创建一篇文献综述笔记

Key Rules

核心规则

Always include paper citations (authors, year, venue)
Distinguish between peer-reviewed and preprints
Be honest about limitations of each paper
Note if a paper directly competes with or supports our approach
Never fail because a MCP server is not configured — always fall back gracefully to the next data source
Zotero/Obsidian tools may have different names depending on how the user configured the MCP server (e.g.,
```
mcp__zotero__search
```
or
```
mcp__zotero-mcp__search_items
```
). Try the most common patterns and adapt.

始终包含论文引用信息（作者、年份、发表会议/期刊）
区分同行评审论文和预印本
如实说明每篇论文的局限性
标注论文是否直接竞争或支持我们的研究方法
绝不因MCP服务器未配置而失效——始终优雅地回退到下一个数据源
Zotero/Obsidian工具的名称可能因用户配置MCP服务器的方式而异（如
```
mcp__zotero__search
```
或
```
mcp__zotero-mcp__search_items
```
）。尝试最常见的命名模式并灵活调整。