Research System
Automated research paper discovery, PDF monitoring, and AI-powered summarization for academic and technical literature.
Overview
The Research System automates your research workflow in a simple daily cycle:
- Automated Discovery - The system searches arXiv and Google Scholar based on your topic/keyword list and creates a daily digest
- Review & Save - You review the digest and download PDFs of interesting papers to your topic's
Sources/ folder
- Automatic Summarization - The system detects new PDFs and generates summaries in the
Notes/ folder
Sample Daily Workflow:
- Morning (Automated): System searches for new papers and creates today's digest
- When you start work: Run
/generate-research-digest to see today's papers and any new summaries
- Throughout the day: Review digest → Download interesting PDFs to
[Topic]/Sources/
- Evening (Automated): System detects new PDFs and queues them for summarization
- Next day: Run
/generate-research-digest again → Get today's papers + yesterday's summaries
Note: Timing is fully customizable during setup. Schedule the automated tasks (paper discovery and PDF monitoring) whenever works best for your workflow.
Features
- Automated Discovery: Daily arXiv searches + weekly Google Scholar searches
- PDF Monitoring: Automatically detects new PDFs you save to Sources/ folders
- AI Summarization: Generates concise bullet-point summaries with semantic tags
- Large PDF Handling: Automatically splits papers ≥5 MB into sections to avoid context overflow
- Conference Proceedings Support: Extract individual papers from multi-paper proceedings
- Intelligent Filtering: Removes irrelevant papers based on your business focus
- Flexible Integration: Works standalone or with task management systems
- Markdown-based: Works with any markdown editor (Obsidian support built-in)
Quick Start
1. Install the Plugin
Option A: Claude Code Marketplace (Recommended)
In Claude Code, run:
/plugin marketplace add ttorres33/teresa-torres-plugins
/plugin install research-system
Option B: Manual Installation
cd ~/.claude/plugins/
git clone https://github.com/ttorres33/research-system.git
2. Run Setup Wizard
In Claude Code:
/setup-research-automation
The wizard will guide you through:
- Installing Python dependencies (automated)
- Configuring research directory location
- Setting up research topics and keywords
- Configuring filter criteria
- Setting up automated cron jobs
- Getting a SerpAPI key (optional, for Google Scholar)
3. Wait for Papers or Run Manually
Papers are fetched automatically by cron job, or run manually:
/fetch-papers
4. Process New Papers
/generate-research-digest
This command:
- Archives yesterday's
research-today.md to research-today-archive/
- Generates summaries for new PDFs
- Creates new
research-today.md with today's papers and summaries
Sample Daily Workflow
Note: The timing below is just one example. During setup, you choose when each automated task runs to fit your schedule.
Automated Tasks
- Paper Discovery: Searches arXiv (daily) and Google Scholar (Sundays), creates digest in
daily-digests/YYYY-MM-DD.md
- PDF Monitoring: Scans for new PDFs you've saved, queues them for summarization
Your Workflow
- Run
/generate-research-digest to:
- Generate summaries for new PDFs
- Create research-today.md with links
- Review the digest and download interesting PDFs to topic folders
Sunday Special (Google Scholar Day)
- Large digest (~200-300 papers from Google Scholar)
- Run
/filter-research-digest to remove irrelevant papers
- If still too many, run
/update-research-filters to refine criteria
Commands
/about - Show this README for help and usage information/generate-research-digest - Generate summaries and create today's digest/research-summary - Generate summary for a single PDF (handles large PDFs automatically)/split-conference-pdf - Split conference proceedings into individual papers/filter-research-digest - Filter digest by relevance/update-research-filters - Interactively refine filter criteria/setup-research-automation - Configuration wizard/fix-scheduled-scripts - Repair cron jobs after plugin directory changes/fetch-papers - Manually run paper fetching (instead of waiting for cron)/monitor-sources - Scan for new PDFs and add to summarization queue/check-logs - View recent log entries to diagnose issues
Working with Large PDFs and Conference Proceedings
Large Paper Handling
