An automated academic assistant that searches Baidu Scholar and arXiv, downloads PDFs, and generates AI-powered summaries of research papers.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install baidu-scholar-helper
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install baidu-scholar-helper using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Baidu Scholar Helper?
Baidu Scholar Helper is a specialized integration for Openclaw Skills designed to significantly accelerate the literature review process for researchers and developers. By bridging the gap between search engines and local document management, this tool provides a unified workflow for discovering, acquiring, and analyzing scientific literature.
This skill eliminates the manual effort of navigating multiple academic portals by providing a single interface to query both Baidu Scholar and arXiv. It prioritizes high-impact research by sorting results by citation count and automatically organizes downloaded papers into a structured local library, making it a vital asset for anyone involved in deep technical research or academic study.
Baidu Scholar Helper Use Cases
- Conducting rapid literature reviews by searching for highly cited papers in specific domains.
- Automating the bulk download of research PDFs for offline reading and archival.
- Extracting technical model architecture diagrams from papers to understand system designs at a glance.
- Generating concise summaries of core innovations and methodologies to quickly filter relevant research materials.
How Baidu Scholar Helper Works
- The user initiates a search using a specific keyword and optional filters such as publication year.
- The skill queries Baidu Scholar or the arXiv API to retrieve metadata including titles, authors, and citation counts.
- Search results are automatically ranked by citation volume to highlight the most influential papers first.
- For each relevant result, the skill identifies the full-text PDF link and initiates a background download.
- Downloaded PDFs are saved to a dedicated directory on the user's desktop, organized by search topic.
- The skill uses AI to parse the abstract and body text, extracting core work and innovation points for a final report.
- System-level tools are used to identify and extract model architecture diagrams directly from the PDF files.
Baidu Scholar Helper Setup
To begin using this skill within your environment, first install the required Python libraries:
pip install requests beautifulsoup4 Pillow
You must also install the poppler-utils system dependency to enable PDF image and text extraction features:
- macOS:
brew install poppler
- Ubuntu/Debian:
sudo apt-get install -y poppler-utils
Verify your installation by ensuring the following commands are available in your path:
which pdftotext pdfimages
Baidu Scholar Helper Data Schema & Taxonomy
Baidu Scholar Helper manages research data using a structured directory approach for Openclaw Skills. All downloaded materials are stored relative to the user's desktop to ensure easy access.
| Data Type | Organization Logic |
|---|---|
| Root Directory | ~/Desktop/papers/ |
| Topic Folders | ~/Desktop/papers/<search-keyword>/ |
| PDF Naming | Title_Year_Type.pdf (where Type is J for Journal or C for Conference) |
| Metadata | Captured fields include Citations, Authors, Source, and Abstract |
| Extracted Assets | Model diagrams and figures are extracted to temporary directories during processing |
Baidu Scholar Helper Advanced Features
- Intelligent citation-based ranking that prioritizes classic and high-impact papers in search results.
- Automated model figure extraction, isolating neural network and system architecture diagrams from PDF content.
- Cross-platform academic support combining traditional Chinese academic databases with global pre-print servers.
- Multi-threaded download and organization, creating structured research repositories based on query keywords.
- High-speed AI summarization that identifies 'Core Work' and 'Innovation Points' without requiring full manual reading.
SKILL.md
Loading
Related Openclaw Skills
Lululemon Brand Intelligence
A specialized brand intelligence skill providing deep technical and market insights into the Lululemon ecosystem.
Lucasfilm Knowledge Integration
A comprehensive knowledge module providing deep technical and historical data on the Lucasfilm cinematic empire.
Bean-to-Soldier Operations Distillation
A professional methodology for distilling complex project operations into standardized, reusable core skills for rapid organizational scaling.
Macy's Brand Guide
A comprehensive digital dossier on Macy's, covering its transition from a 19th-century dry goods store to a modern omnichannel retail powerhouse.
Consulting Methods Toolkit
A professional-grade framework library for structured management consulting, strategic diagnostics, and actionable problem-solving.
Self-Distill Skill (Personality Metadata Framework)
A structured personality profiling framework that combines Jungian psychology, MBTI, and behavioral data to generate quantifiable metadata profiles.
Featured*
