Paper Analyzer

v1.0.0

学术论文结构化阅读、拆解与分析工具。基于12个阅读要素(研究背景、研究问题、研究结论、文献综合、文献批评、研究方法、理论视角与理论框架、一致性发现、不一致性发现、研究贡献、研究不足、未来研究展望)对论文进行深度拆解,结果保存为Excel文件。当用户提到需要针对论文/文献/paper进行拆解、解析、分析、阅读、梳理...

0· 237·2 current·2 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for yipng05-max/paper-analyzer.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Paper Analyzer" (yipng05-max/paper-analyzer) from ClawHub.
Skill page: https://clawhub.ai/yipng05-max/paper-analyzer
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install paper-analyzer

ClawHub CLI

Package manager switcher

npx clawhub@latest install paper-analyzer
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description (paper analysis → produce Excel) matches the SKILL.md and the included export_excel.py. Required actions (reading PDFs/Word, extracting text, building JSON, writing Excel into the paper's folder) are consistent with the stated purpose. No unrelated environment variables or external services are requested.
Instruction Scope
Instructions explicitly tell the agent to read user-provided local files (PDF/Word), possibly call the system pdftotext, record the paper folder path and save the Excel there, and present a chat summary. Reading local files and saving output to the same folder are necessary for the task but mean the agent will access whatever files the user supplies; users should avoid feeding sensitive documents if they aren't comfortable with local processing.
Install Mechanism
There is no install spec (instruction-only), so nothing is downloaded during install — lower risk. The included Python script depends on openpyxl (and Python 3). The SKILL.md assumes python3 and optional pdftotext exist; the skill may fail if these are missing. No remote downloads or obscure URLs are present.
Credentials
The skill declares no environment variables, no credentials, and no config paths. Its access to local files is appropriate for its purpose and proportionate to the described functionality.
Persistence & Privilege
always is false and the skill does not request persistent or cross-skill privileges. It does not alter other skills or global agent settings.
Assessment
This skill appears coherent and low-risk, but check a few things before use: (1) Inspect scripts/export_excel.py yourself (it's included) to confirm behavior—it's straightforward and only writes Excel files. (2) Ensure your agent environment has Python3 and the openpyxl package (and pdftotext if you plan to rely on it); missing dependencies will cause runtime errors. (3) Be mindful that the skill will read any local files you point it to and will save Excel files into the same folder (risk of overwriting). Don’t feed documents containing secrets or sensitive data unless you are comfortable with local processing. (4) If you plan to let the agent invoke skills autonomously, remember this skill will have access to any local file paths you provide at runtime. If you want greater assurance, run the export script manually on sample JSON to confirm outputs before granting the agent broad file access.

Like a lobster shell, security has layers — review code before you run it.

latestvk978r71p5wj44sjy59a8k9aaqn834n69
237downloads
0stars
1versions
Updated 1mo ago
v1.0.0
MIT-0

论文结构化拆解分析

基于12个阅读要素对学术论文进行结构化拆解,结果保存为Excel文件存储于论文所在文件夹中。

工作流程

1. 读取论文

  • 使用 Read 工具读取用户提供的论文文件(支持 PDF、Word 等格式)
  • 对于 PDF 文件,如果 Read 工具无法直接读取,使用 pdftotext 命令提取文本
  • 对于 PDF 文件,如果页数较多,先读取前几页了解结构,再分批读取全文
  • 确保完整阅读论文的各个部分:摘要、引言、文献综述、方法、结果、讨论、结论
  • 记录论文所在的文件夹路径,用于后续保存Excel文件

2. 按12要素提取信息

阅读论文后,逐一提取12个阅读要素。要素定义详见 references/reading_elements.md

提取要点:

  • 研究背景: 从引言开头提取宏观背景,区分实践背景、理论背景、政策背景
  • 研究问题: 识别核心研究问题,判断其类型(what/why/how/should)
  • 研究结论: 从结论和讨论部分提取对研究问题的直接回答
  • 文献综合: 从文献综述部分梳理作者如何分类整理已有研究
  • 文献批评: 提取作者对已有研究的评价,重点关注研究gap的表述
  • 研究方法: 从方法论部分提取具体研究方法和研究设计
  • 理论视角与理论框架: 识别论文采用的理论基础和分析框架
  • 一致性发现: 从讨论部分提取与已有研究一致的发现
  • 不一致性发现: 从讨论部分提取与已有研究不一致的发现
  • 研究贡献: 提取作者自述的研究贡献(新方法/新材料/新理论/新观点/新概念)
  • 研究不足: 从结论或讨论的局限性部分提取
  • 未来研究展望: 提取作者对后续研究的建议

如论文中某要素未明确提及,标注"论文未明确提及"并尝试基于论文内容进行合理推断,推断内容用括号标注。

3. 保存为Excel文件

分析完成后,将结果保存为Excel文件,存放于被分析论文所在的文件夹中。

使用 scripts/export_excel.py 脚本生成Excel。先用 Python 将分析数据写入临时JSON文件,再调用脚本。

单篇论文

生成文件名:论文拆解_<论文简称>.xlsx,包含一个工作表。

构造JSON数据并调用脚本:

python3 <skill_path>/scripts/export_excel.py --mode single --output "<论文所在文件夹>/论文拆解_<论文简称>.xlsx" --json '<json_string>'

JSON结构:

{
  "title": "论文标题",
  "author": "作者",
  "source": "期刊/来源",
  "year": "年份",
  "elements": {
    "研究背景": "内容...",
    "研究问题": "内容...",
    "研究结论": "内容...",
    "文献综合": "内容...",
    "文献批评": "内容...",
    "研究方法": "内容...",
    "理论视角与理论框架": "内容...",
    "一致性发现": "内容...",
    "不一致性发现": "内容...",
    "研究贡献": "内容...",
    "研究不足": "内容...",
    "未来研究展望": "内容..."
  }
}

多篇论文

生成文件名:论文拆解汇总_<N>篇.xlsx,包含每篇论文的独立工作表 + 最后一个"横向对比汇总"工作表。

python3 <skill_path>/scripts/export_excel.py --mode multi --output "<论文所在文件夹>/论文拆解汇总_<N>篇.xlsx" --json '<json_string>'

JSON结构:

{
  "papers": [
    { "title": "...", "author": "...", "source": "...", "year": "...", "elements": { ... } },
    ...
  ],
  "summary": {
    "paper_labels": ["论文A简称", "论文B简称", ...],
    "elements": {
      "研究背景": ["论文A精简版", "论文B精简版", ...],
      ...12个要素各一个数组...
    }
  }
}

重要:由于JSON字符串可能很长,使用Python将JSON写入临时文件,再用 --json "$(cat /tmp/paper_data.json)" 传入,或直接在Python中调用脚本。推荐方式:

import json, subprocess
data = { ... }  # 构造好的数据
with open("/tmp/_paper_analysis.json", "w") as f:
    json.dump(data, f, ensure_ascii=False)
subprocess.run(["python3", "<skill_path>/scripts/export_excel.py",
    "--mode", "multi",
    "--output", "<输出路径>",
    "--json", json.dumps(data, ensure_ascii=False)])

4. 输出到对话

在保存Excel后,同时在对话中以markdown表格简要呈现分析结果,并告知用户Excel文件的保存路径。

5. 内容要求

  • 使用中文输出(除非论文为英文且用户要求英文输出)
  • 每个要素的内容应简明扼要但信息充分,单篇表格中每个要素2-5句话
  • 汇总对比表中每个单元格压缩为1-2句核心要点
  • 忠于论文原文,避免过度解读;推断内容明确标注
  • 在研究问题要素中标注问题类型(what/why/how/should)

Comments

Loading comments...