research-summarizer

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Research Summarizer

研究总结工具

Read less. Understand more. Cite correctly.

Structured research summarization workflow that turns dense source material into actionable briefs. Built for product managers, analysts, founders, and anyone who reads more than they should have to.

Not a generic "summarize this" — a repeatable framework that extracts what matters, compares across sources, and formats citations properly.

少阅读，多理解，规范引用。

将密集的源材料转化为可执行简报的结构化研究总结工作流。专为产品经理、分析师、创始人及所有需要大量阅读的人群打造。

这不是通用的“总结一下”工具，而是一个可重复的框架，能提取关键信息、跨来源对比并规范格式引用。

Slash Commands

斜杠命令

Command	What it does
`/research:summarize`	Summarize a single source into a structured brief
`/research:compare`	Compare 2-5 sources side-by-side with synthesis
`/research:cite`	Extract and format all citations from a document

命令	功能
`/research:summarize`	将单一来源总结为结构化简报
`/research:compare`	并排对比2-5个来源并进行综合分析
`/research:cite`	从文档中提取并格式化所有引用

When This Skill Activates

技能触发场景

Recognize these patterns from the user:

"Summarize this paper / article / report"
"What are the key findings in this document?"
"Compare these sources"
"Extract citations from this PDF"
"Give me a research brief on [topic]"
"Break down this whitepaper"
Any request involving: summarize, research brief, literature review, citation, source comparison

If the user has a document and wants structured understanding → this skill applies.

识别用户的以下请求模式：

"总结这篇论文/文章/报告"
"这份文档的关键发现是什么？"
"对比这些来源"
"从这份PDF中提取引用"
"给我一份关于[主题]的研究简报"
"拆解这份白皮书"
任何涉及以下关键词的请求：总结、研究简报、文献综述、引用、来源对比

如果用户持有文档并需要结构化的理解 → 适用本技能。

Workflow

工作流程

/research:summarize

— Single Source Summary

/research:summarize

— 单一来源总结

Identify source type
- Academic paper → use IMRAD structure (Introduction, Methods, Results, Analysis, Discussion)
- Web article → use claim-evidence-implication structure
- Technical report → use executive summary structure
- Documentation → use reference summary structure

Extract structured brief

Title: [exact title]
Author(s): [names]
Date: [publication date]
Source Type: [paper | article | report | documentation]

## Key Thesis
[1-2 sentences: the central argument or finding]

## Key Findings
1. [Finding with supporting evidence]
2. [Finding with supporting evidence]
3. [Finding with supporting evidence]

## Methodology
[How they arrived at these findings — data sources, sample size, approach]

## Limitations
- [What the source doesn't cover or gets wrong]

## Actionable Takeaways
- [What to do with this information]

## Notable Quotes
> "[Direct quote]" (p. X)

Assess quality
- Source credibility (peer-reviewed, reputable outlet, primary vs secondary)
- Evidence strength (data-backed, anecdotal, theoretical)
- Recency (when published, still relevant?)
- Bias indicators (funding source, author affiliation, methodology gaps)

识别来源类型
- 学术论文 → 使用IMRAD结构（引言、方法、结果、分析、讨论）
- 网页文章 → 使用主张-证据-启示结构
- 技术报告 → 使用执行摘要结构
- 文档 → 使用参考摘要结构

提取结构化简报

标题: [准确标题]
作者: [姓名]
日期: [发布日期]
来源类型: [论文 | 文章 | 报告 | 文档]

## 核心论点
[1-2句话：核心论证或发现]

## 关键发现
1. [带支撑证据的发现]
2. [带支撑证据的发现]
3. [带支撑证据的发现]

## 研究方法
[他们得出这些发现的方式——数据源、样本量、方法]

## 局限性
- [该来源未涵盖或存在错误的内容]

## 可执行要点
- [如何利用这些信息]

## 重要引用
> "[直接引用]" (第X页)

质量评估
- 来源可信度（同行评审、知名渠道、一手 vs 二手）
- 证据强度（数据支持、轶事、理论）
- 时效性（发布时间，是否仍具相关性？）
- 偏见指标（资金来源、作者所属机构、方法漏洞）

/research:compare

— Multi-Source Comparison

/research:compare

— 多来源对比

Collect sources (2-5 documents)
Summarize each using the single-source workflow above

Build comparison matrix

| Dimension        | Source A        | Source B        | Source C        |
|------------------|-----------------|-----------------|-----------------|
| Central Thesis   | ...             | ...             | ...             |
| Methodology      | ...             | ...             | ...             |
| Key Finding      | ...             | ...             | ...             |
| Sample/Scope     | ...             | ...             | ...             |
| Credibility      | High/Med/Low    | High/Med/Low    | High/Med/Low    |

Synthesize
- Where do sources agree? (convergent findings = stronger signal)
- Where do they disagree? (divergent findings = needs investigation)
- What gaps exist across all sources?
- What's the weight of evidence for each position?

Produce synthesis brief

## Consensus Findings
[What most sources agree on]

## Contested Points
[Where sources disagree, with strongest evidence for each side]

## Gaps
[What none of the sources address]

## Recommendation
[Based on weight of evidence, what should the reader believe/do?]

收集来源（2-5份文档）
逐一总结 使用上述单一来源工作流

构建对比矩阵

| 维度        | 来源A        | 来源B        | 来源C        |
|------------------|-----------------|-----------------|-----------------|
| 核心论点   | ...             | ...             | ...             |
| 研究方法      | ...             | ...             | ...             |
| 关键发现      | ...             | ...             | ...             |
| 样本/范围     | ...             | ...             | ...             |
| 可信度      | 高/中/低    | 高/中/低    | 高/中/低    |

综合分析
- 各来源的共识点？（趋同发现 = 更强信号）
- 各来源的分歧点？（差异发现 = 需要进一步调查）
- 所有来源都存在哪些信息空白？
- 每个立场的证据权重如何？

生成综合简报

## 共识发现
[多数来源达成一致的内容]

## 争议点
[来源存在分歧的内容，以及各方最有力的证据]

## 信息空白
[所有来源均未涉及的内容]

## 建议
[基于证据权重，读者应相信/采取的行动]

/research:cite

— Citation Extraction

/research:cite

— 引用提取

Scan document for all references, footnotes, in-text citations
Extract and format using the requested style (APA 7 default)
Classify citations by type:
- Primary sources (original research, data)
- Secondary sources (reviews, meta-analyses, commentary)
- Tertiary sources (textbooks, encyclopedias)
Output sorted bibliography with classification tags

Supported citation formats:

APA 7 (default) — social sciences, business
IEEE — engineering, computer science
Chicago — humanities, history
Harvard — general academic
MLA 9 — arts, humanities

扫描文档 查找所有参考文献、脚注、文内引用
提取并格式化 使用指定格式（默认APA 7）
按类型分类引用:
- 一手来源（原创研究、数据）
- 二手来源（综述、元分析、评论）
- 三手来源（教科书、百科全书）
输出带分类标签的排序参考文献列表

支持的引用格式:

APA 7（默认）——社会科学、商业
IEEE——工程、计算机科学
Chicago——人文、历史
Harvard——通用学术
MLA 9——艺术、人文

Tooling

工具集

scripts/extract_citations.py

scripts/extract_citations.py

CLI utility for extracting and formatting citations from text.

Features:

Regex-based citation detection (DOI, URL, author-year, numbered references)
Multiple output formats (APA, IEEE, Chicago, Harvard, MLA)
JSON export for integration with reference managers
Deduplication of repeated citations

Usage:

bash

undefined

用于从文本中提取并格式化引用的CLI工具。

功能:

基于正则表达式的引用检测（DOI、URL、作者-年份、编号参考文献）
多种输出格式（APA、IEEE、Chicago、Harvard、MLA）
JSON导出，可与参考文献管理器集成
重复引用去重

用法:

bash

undefined

Extract citations from a file (APA format, default)

从文件提取引用（默认APA格式）

python3 scripts/extract_citations.py document.txt

Specify format

指定格式

python3 scripts/extract_citations.py document.txt --format ieee

JSON output

JSON输出

python3 scripts/extract_citations.py document.txt --format apa --output json

From stdin

从标准输入读取

cat paper.txt | python3 scripts/extract_citations.py --stdin

undefined

cat paper.txt | python3 scripts/extract_citations.py --stdin

undefined

scripts/format_summary.py

scripts/format_summary.py

CLI utility for generating structured research summaries.

Features:

Multiple summary templates (academic, article, report, executive)
Configurable output length (brief, standard, detailed)
Markdown and plain text output
Key findings extraction with evidence tagging

Usage:

bash

undefined

用于生成结构化研究总结的CLI工具。

功能:

多种总结模板（学术、文章、报告、执行摘要）
可配置输出长度（简短、标准、详细）
Markdown和纯文本输出
带证据标记的关键发现提取

用法:

bash

undefined

Generate structured summary template

生成结构化总结模板

python3 scripts/format_summary.py --template academic

Brief executive summary format

简短的执行摘要格式

python3 scripts/format_summary.py --template executive --length brief

All templates listed

列出所有模板

python3 scripts/format_summary.py --list-templates

JSON output

JSON输出

python3 scripts/format_summary.py --template article --output json

---

python3 scripts/format_summary.py --template article --output json

---

Quality Assessment Framework

质量评估框架

Rate every source on four dimensions:

Dimension	High	Medium	Low
Credibility	Peer-reviewed, established author	Reputable outlet, known author	Blog, unknown author, no review
Evidence	Large sample, rigorous method	Moderate data, sound approach	Anecdotal, no data, opinion
Recency	Published within 2 years	2-5 years old	5+ years, may be outdated
Objectivity	No conflicts, balanced view	Minor affiliations disclosed	Funded by interested party, one-sided

Overall Rating:

4 Highs = Strong source — cite with confidence
2+ Mediums = Adequate source — cite with caveats
2+ Lows = Weak source — verify independently before citing

从四个维度对每个来源进行评级:

维度	高	中	低
可信度	同行评审、知名作者	知名渠道、已知作者	博客、未知作者、无评审
证据强度	大样本、严谨方法	中等数据、合理方法	轶事、无数据、观点
时效性	2年内发布	2-5年前发布	5年以上，可能过时
客观性	无利益冲突、观点平衡	披露次要关联	由利益相关方资助、片面观点

整体评级:

4项均为高 = 强来源 — 可放心引用
2项及以上为中 = 合格来源 — 引用时需注明 Caveats
2项及以上为低 = 弱来源 — 引用前需独立验证

Summary Templates

总结模板

See

references/summary-templates.md

for:

Academic paper summary template (IMRAD)
Web article summary template (claim-evidence-implication)
Technical report template (executive summary)
Comparative analysis template (matrix + synthesis)
Literature review template (thematic organization)

See

references/citation-formats.md

for:

APA 7 formatting rules and examples
IEEE formatting rules and examples
Chicago, Harvard, MLA quick reference

查看

references/summary-templates.md

获取:

学术论文总结模板（IMRAD）
网页文章总结模板（主张-证据-启示）
技术报告模板（执行摘要）
对比分析模板（矩阵 + 综合分析）
文献综述模板（主题式组织）

查看

references/citation-formats.md

获取:

APA 7格式规则及示例
IEEE格式规则及示例
Chicago、Harvard、MLA快速参考

Proactive Triggers

主动触发规则

Flag these without being asked:

Source has no date → Note it. Undated sources lose credibility points.
Source contradicts other sources → Highlight the contradiction explicitly. Don't paper over disagreements.
Source is behind a paywall → Note limited access. Suggest alternatives if known.
User provides only one source for a compare → Ask for at least one more. Comparison needs 2+.
Citations are incomplete → Flag missing fields (year, author, title). Don't invent metadata.
Source is 5+ years old in a fast-moving field → Warn about potential obsolescence.

无需用户询问，自动标记以下情况:

来源无日期 → 注明该情况。无日期来源会降低可信度评分。
来源与其他来源矛盾 → 明确突出矛盾点。不要掩盖分歧。
来源需付费访问 → 注明访问受限。如有已知替代方案可建议。
用户仅提供一个来源用于对比 → 请求至少再提供一个。对比需要2个及以上来源。
引用信息不完整 → 标记缺失字段（年份、作者、标题）。不要编造元数据。
来源在快速发展领域已发布5年以上 → 警告可能已过时。

Installation

安装

One-liner (any tool)

一键安装（适用于所有工具）

bash

git clone https://github.com/alirezarezvani/claude-skills.git
cp -r claude-skills/product-team/research-summarizer ~/.claude/skills/

bash

git clone https://github.com/alirezarezvani/claude-skills.git
cp -r claude-skills/product-team/research-summarizer ~/.claude/skills/

Multi-tool install

多工具安装

bash

./scripts/convert.sh --skill research-summarizer --tool codex|gemini|cursor|windsurf|openclaw

bash

./scripts/convert.sh --skill research-summarizer --tool codex|gemini|cursor|windsurf|openclaw

OpenClaw

bash

clawhub install cs-research-summarizer

bash

clawhub install cs-research-summarizer

research-summarizer

Original

Translation

Research Summarizer

研究总结工具

Slash Commands

斜杠命令

When This Skill Activates

技能触发场景

Workflow

工作流程

/research:summarize — Single Source Summary

/research:summarize — 单一来源总结

/research:compare — Multi-Source Comparison

/research:compare — 多来源对比

/research:cite — Citation Extraction

/research:cite — 引用提取

Tooling

工具集

scripts/extract_citations.py

scripts/extract_citations.py

Extract citations from a file (APA format, default)

从文件提取引用（默认APA格式）

Specify format

指定格式

JSON output

JSON输出

From stdin

从标准输入读取

scripts/format_summary.py

scripts/format_summary.py

Generate structured summary template

生成结构化总结模板

Brief executive summary format

简短的执行摘要格式

All templates listed

列出所有模板

JSON output

JSON输出

Quality Assessment Framework

质量评估框架

Summary Templates

总结模板

Proactive Triggers

主动触发规则

Installation

安装

One-liner (any tool)

一键安装（适用于所有工具）

Multi-tool install

多工具安装

OpenClaw

OpenClaw

Related Skills

相关技能

`/research:summarize`
— Single Source Summary

`/research:summarize`
— 单一来源总结

`/research:compare`
— Multi-Source Comparison

`/research:compare`
— 多来源对比

`/research:cite`
— Citation Extraction

`/research:cite`
— 引用提取

`scripts/extract_citations.py`

`scripts/extract_citations.py`

`scripts/format_summary.py`

`scripts/format_summary.py`