@wentorai/research-plugins 1.2.3 → 1.3.1

package/skills/literature/discovery/arxiv-paper-monitoring/SKILL.md

@@ -1,233 +0,0 @@
----
-name: arxiv-paper-monitoring
-description: "Set up automated monitoring for new arXiv papers in your research area"
-metadata:
-  openclaw:
-    emoji: "👀"
-    category: "literature"
-    subcategory: "discovery"
-    keywords: ["arxiv monitoring", "paper alerts", "research tracking", "new papers", "literature monitoring", "RSS feeds"]
-    source: "https://clawhub.ai/arxiv-watcher"
----
-
-# arXiv Paper Monitoring
-
-## Overview
-
-Staying current with new preprints in your field is critical for active researchers. This guide covers multiple approaches to monitoring arXiv for new papers: RSS feeds, email alerts, API-based scripts, and third-party services. Choose based on your needs: passive monitoring (RSS/email) for broad awareness, or active filtering (scripts) for high-precision tracking.
-
-## Method 1: arXiv RSS Feeds
-
-The simplest approach. arXiv provides RSS feeds for every category:
-
-```
-Feed URL pattern:
-  https://rss.arxiv.org/rss/{category}
-
-Examples:
-  https://rss.arxiv.org/rss/cs.CL     — Computation and Language
-  https://rss.arxiv.org/rss/cs.AI     — Artificial Intelligence
-  https://rss.arxiv.org/rss/stat.ML   — Machine Learning (Statistics)
-  https://rss.arxiv.org/rss/q-fin.ST  — Statistical Finance
-  https://rss.arxiv.org/rss/econ.EM   — Econometrics
-```
-
-**Setup in an RSS reader** (Feedly, Inoreader, NetNewsWire):
-1. Add the feed URL for each category you follow
-2. Create a folder "arXiv" to group feeds
-3. Check daily — new papers appear Monday-Friday
-
-## Method 2: arXiv Email Alerts
-
-```
-1. Go to https://arxiv.org/help/subscribe
-2. Create/login to your arXiv account
-3. Navigate to "Email Notifications" in settings
-4. Select categories to subscribe to
-5. Choose frequency: daily digest
-```
-
-## Method 3: Python Monitoring Script
-
-For custom filtering with keyword matching:
-
-```python
-import arxiv
-import json
-from datetime import datetime, timedelta
-from pathlib import Path
-
-class ArxivMonitor:
-    """Monitor arXiv for new papers matching your research interests."""
-
-    def __init__(self, config_path: str = "monitor_config.json"):
-        with open(config_path) as f:
-            self.config = json.load(f)
-        self.seen_file = Path("seen_papers.json")
-        self.seen = json.loads(self.seen_file.read_text()) if self.seen_file.exists() else []
-
-    def check_new_papers(self) -> list:
-        """Fetch and filter new papers based on config."""
-        results = []
-        client = arxiv.Client()
-
-        for track in self.config["tracks"]:
-            query = self._build_query(track)
-            search = arxiv.Search(
-                query=query,
-                max_results=track.get("max_results", 50),
-                sort_by=arxiv.SortCriterion.SubmittedDate
-            )
-
-            for paper in client.results(search):
-                paper_id = paper.entry_id.split("/")[-1]
-                if paper_id in self.seen:
-                    continue
-
-                # Keyword matching in title + abstract
-                text = f"{paper.title} {paper.summary}".lower()
-                if self._matches_keywords(text, track.get("keywords", [])):
-                    results.append({
-                        "id": paper_id,
-                        "title": paper.title,
-                        "authors": [a.name for a in paper.authors[:5]],
-                        "abstract": paper.summary[:500],
-                        "url": paper.entry_id,
-                        "pdf": paper.pdf_url,
-                        "published": paper.published.isoformat(),
-                        "track": track["name"],
-                        "categories": paper.categories
-                    })
-                    self.seen.append(paper_id)
-
-        # Save seen list
-        self.seen_file.write_text(json.dumps(self.seen[-5000:]))  # keep last 5000
-        return results
-
-    def _build_query(self, track: dict) -> str:
-        cats = " OR ".join(f"cat:{c}" for c in track.get("categories", []))
-        return f"({cats})" if cats else track.get("query", "")
-
-    def _matches_keywords(self, text: str, keywords: list) -> bool:
-        if not keywords:
-            return True  # no filter = include all
-        return any(kw.lower() in text for kw in keywords)
-
-    def format_digest(self, papers: list) -> str:
-        """Format papers as a readable digest."""
-        if not papers:
-            return "No new papers matching your criteria today."
-
-        lines = [f"# arXiv Digest — {datetime.now().strftime('%Y-%m-%d')}",
-                 f"**{len(papers)} new papers found**\n"]
-
-        for track_name in set(p["track"] for p in papers):
-            track_papers = [p for p in papers if p["track"] == track_name]
-            lines.append(f"\n## {track_name} ({len(track_papers)} papers)\n")
-            for p in track_papers:
-                authors = ", ".join(p["authors"][:3])
-                if len(p["authors"]) > 3:
-                    authors += " et al."
-                lines.append(f"### [{p['title']}]({p['url']})")
-                lines.append(f"*{authors}* — {p['published'][:10]}")
-                lines.append(f"> {p['abstract'][:200]}...\n")
-
-        return "\n".join(lines)
-```
-
-### Configuration File
-
-```json
-{
-  "tracks": [
-    {
-      "name": "RAG & Retrieval",
-      "categories": ["cs.CL", "cs.IR"],
-      "keywords": ["retrieval augmented", "RAG", "dense retrieval", "passage retrieval"],
-      "max_results": 100
-    },
-    {
-      "name": "LLM Agents",
-      "categories": ["cs.AI", "cs.CL"],
-      "keywords": ["language model agent", "tool use", "function calling", "agentic"],
-      "max_results": 100
-    },
-    {
-      "name": "Causal Inference",
-      "categories": ["econ.EM", "stat.ME"],
-      "keywords": ["difference-in-differences", "regression discontinuity", "instrumental variable"],
-      "max_results": 50
-    }
-  ]
-}
-```
-
-### Cron Job Setup
-
-```bash
-# Run daily at 8 AM
-# crontab -e
-0 8 * * 1-5 cd /path/to/monitor && python run_monitor.py >> monitor.log 2>&1
-```
-
-```python
-# run_monitor.py
-from arxiv_monitor import ArxivMonitor
-
-monitor = ArxivMonitor("monitor_config.json")
-papers = monitor.check_new_papers()
-digest = monitor.format_digest(papers)
-
-# Save digest
-with open(f"digests/{datetime.now().strftime('%Y-%m-%d')}.md", "w") as f:
-    f.write(digest)
-
-print(f"Found {len(papers)} new papers")
-```
-
-## Method 4: Third-Party Services
-
-| Service | Features | Price |
-|---------|----------|-------|
-| **Semantic Scholar Alerts** | Follow authors, topics, citation alerts | Free |
-| **Google Scholar Alerts** | Email when new papers match query | Free |
-| **ResearchRabbit** | AI-recommended papers, citation network | Free |
-| **Connected Papers** | Visual paper discovery from seed paper | Free |
-| **Arxiv Sanity** (Karpathy) | ML-filtered arXiv papers | Free |
-| **Papers With Code** | Papers + code repositories | Free |
-| **Hugging Face Daily Papers** | Community-curated ML papers | Free |
-
-### Setting Up Google Scholar Alerts
-
-```
-1. Go to https://scholar.google.com/scholar_alerts
-2. Click "Create alert"
-3. Enter search query (e.g., "retrieval augmented generation")
-4. Set email frequency: daily or weekly
-5. Google will email you when new matching papers appear
-```
-
-### Setting Up Semantic Scholar Alerts
-
-```
-1. Go to https://www.semanticscholar.org/
-2. Create an account
-3. Search for a paper or author
-4. Click "Alert" → get notified of new citations or related papers
-5. Use "Research Feeds" for topic-based monitoring
-```
-
-## Best Practices
-
-- **Limit scope**: Monitor 3-5 categories max; use keyword filtering to avoid noise
-- **Weekly review**: Even with daily alerts, do a focused weekly review session
-- **Triage quickly**: Title scan → abstract scan → full read (80/15/5 ratio)
-- **Track what you read**: Log papers in your citation manager immediately
-- **Share with your lab**: Post weekly digest to a shared Slack channel or group chat
-
-## References
-
-- [arXiv RSS Feeds](https://info.arxiv.org/help/rss.html)
-- [arXiv API Documentation](https://info.arxiv.org/help/api/)
-- [Semantic Scholar Research Feeds](https://www.semanticscholar.org/product/research-feeds)
-- [Google Scholar Alerts](https://scholar.google.com/scholar_alerts)

package/skills/literature/discovery/paper-tracking-guide/SKILL.md

@@ -1,211 +0,0 @@
----
-name: paper-tracking-guide
-description: "Track new publications via RSS, alerts, and citation notifications"
-metadata:
-  openclaw:
-    emoji: "🔔"
-    category: "literature"
-    subcategory: "discovery"
-    keywords: ["literature alert", "citation notification", "RSS feed", "new publication tracking", "related papers"]
-    source: "N/A"
----
-
-# Paper Tracking Guide
-
-## Overview
-
-Staying current with the literature is one of the most persistent challenges in academic research. With over 5 million new papers published annually across all disciplines, manual browsing of journals and preprint servers is neither scalable nor reliable. Researchers who set up automated tracking systems gain a significant advantage: they discover relevant work earlier, avoid duplicating existing results, and identify collaboration opportunities.
-
-This guide covers five complementary strategies for tracking new publications: RSS feeds from preprint servers and journals, keyword-based alerts from search engines, citation tracking for monitoring who cites your work or key papers, social and community feeds, and AI-powered discovery tools. The goal is to build a personalized monitoring pipeline that delivers relevant papers to you daily with minimal noise.
-
-Each strategy is described with setup instructions, tool recommendations, and configuration tips so you can have a working tracking system within an afternoon.
-
-## RSS Feeds from Preprint Servers
-
-RSS remains the most reliable method for monitoring preprint servers like arXiv, bioRxiv, and SSRN.
-
-### arXiv RSS Setup
-
-arXiv provides RSS feeds for every category and subcategory:
-
-```
-# Feed URL format
-https://rss.arxiv.org/rss/{category}
-
-# Examples
-https://rss.arxiv.org/rss/cs.CL    # Computation and Language
-https://rss.arxiv.org/rss/cs.LG    # Machine Learning
-https://rss.arxiv.org/rss/stat.ML  # Statistics: Machine Learning
-https://rss.arxiv.org/rss/q-bio.GN # Genomics
-```
-
-### bioRxiv and medRxiv
-
-```
-# bioRxiv new papers by subject
-https://connect.biorxiv.org/biorxiv_xml.php?subject=neuroscience
-
-# medRxiv new papers
-https://connect.medrxiv.org/medrxiv_xml.php?subject=epidemiology
-```
-
-### Recommended RSS Readers
-
-| Reader | Platform | Free Tier | Best Feature |
-|--------|----------|-----------|-------------|
-| Feedly | Web/Mobile | 100 feeds | AI prioritization |
-| Inoreader | Web/Mobile | 150 feeds | Rules & filters |
-| Miniflux | Self-hosted | Unlimited | Full control |
-| NetNewsWire | macOS/iOS | Unlimited | Native, fast, open-source |
-| Feedbin | Web | Paid only | Clean interface |
-
-### Filtering High-Volume Feeds
-
-For categories with 50+ daily papers, set up keyword filters in your RSS reader:
-
-```
-# Inoreader rule example
-IF title contains "transformer" OR "attention mechanism"
-AND title does NOT contain "survey" OR "review"
-THEN star AND move to "Priority" folder
-```
-
-## Keyword-Based Alerts
-
-### Google Scholar Alerts
-
-1. Go to [scholar.google.com/scholar_alerts](https://scholar.google.com/scholar_alerts)
-2. Click "Create alert"
-3. Enter a search query using operators:
-
-```
-# Specific phrase
-"graph neural network" "drug discovery"
-
-# Author tracking
-author:"Yoshua Bengio"
-
-# Venue-specific
-source:"Nature Machine Intelligence"
-```
-
-Tips:
-- Create 5-10 focused alerts rather than 1-2 broad ones.
-- Use quotation marks for exact phrases.
-- Review and refine alerts monthly.
-
-### Semantic Scholar Alerts
-
-Semantic Scholar offers research feed customization:
-
-1. Create an account at [semanticscholar.org](https://www.semanticscholar.org/)
-2. Add papers to your library
-3. The recommendation engine learns your interests
-4. Enable weekly email digest
-
-### PubMed Alerts (Biomedical)
-
-```
-# Create a saved search at pubmed.ncbi.nlm.nih.gov
-# Example query with MeSH terms
-("machine learning"[MeSH] OR "deep learning"[MeSH])
-AND "drug discovery"[MeSH]
-AND "2024/01/01"[Date - Publication] : "3000"[Date - Publication]
-
-# Set up email alerts: Save search > Create alert > Weekly
-```
-
-## Citation Tracking
-
-Citation tracking answers: "Who is building on this foundational paper?"
-
-### Methods
-
-| Method | Coverage | Real-time | Cost |
-|--------|----------|-----------|------|
-| Google Scholar "Cited by" alerts | Broad | Near real-time | Free |
-| Semantic Scholar citation alerts | CS, biomedical | Weekly | Free |
-| Web of Science citation reports | Comprehensive | Weekly | Institutional |
-| Scopus citation alerts | Comprehensive | Configurable | Institutional |
-| ResearchGate notifications | Author-based | Real-time | Free |
-
-### Setting Up Google Scholar Citation Alerts
-
-1. Search for the paper on Google Scholar.
-2. Click "Cited by N" below the paper.
-3. Click the envelope icon ("Create alert") at the top of the results page.
-4. Receive an email whenever a new paper cites the tracked paper.
-
-### Tracking Your Own Citations
-
-1. Create a [Google Scholar Profile](https://scholar.google.com/intl/en/scholar/citations.html).
-2. Verify your papers.
-3. Enable "New citations to my articles" alerts.
-4. Monitor your h-index and i10-index trends.
-
-## AI-Powered Discovery Tools
-
-### Connected Papers
-
-[connectedpapers.com](https://connectedpapers.com/) builds a visual graph of related papers:
-
-1. Enter a seed paper (title, DOI, or URL).
-2. The tool generates a similarity graph (not citation graph).
-3. Papers that are close together share more conceptual similarity.
-4. Use "Prior works" and "Derivative works" views for temporal exploration.
-
-### Elicit
-
-[elicit.com](https://elicit.com/) uses language models to search and summarize papers:
-
-1. Ask a natural-language research question.
-2. Elicit finds relevant papers and extracts key findings.
-3. Use the "Columns" feature to compare methods, datasets, and results across papers.
-
-### Research Rabbit
-
-[researchrabbit.ai](https://www.researchrabbit.ai/) provides:
-
-- Citation network visualization
-- "Similar work" recommendations
-- Author network exploration
-- Collection-based monitoring with email alerts
-
-## Building Your Daily Pipeline
-
-A recommended daily reading workflow:
-
-```
-Morning (15 min):
-1. Check RSS reader for new preprints (filtered by keywords)
-2. Star 3-5 papers for reading later
-3. Quick-scan abstracts of starred papers
-
-Weekly (1 hour):
-1. Read 2-3 starred papers in full
-2. Add to Zotero with tags and notes
-3. Check citation alerts for tracked papers
-4. Review AI recommendations (Semantic Scholar, Research Rabbit)
-
-Monthly (30 min):
-1. Audit alert quality -- prune noisy alerts, add new ones
-2. Update RSS feed subscriptions for evolving interests
-3. Share interesting papers with lab group
-```
-
-## Best Practices
-
-- **Limit your feeds.** It is better to thoroughly read 5 papers per week than to skim 50.
-- **Use a reference manager from day one.** Zotero, Paperpile, or Mendeley -- pick one and use it consistently.
-- **Tag papers by project.** When you start writing, you will need to find that paper you read six months ago.
-- **Share with your team.** Set up a shared Zotero group or Slack channel for paper recommendations.
-- **Track trends, not just individual papers.** Notice when multiple groups independently converge on the same idea.
-- **Combine automated and social discovery.** Algorithms miss papers that colleagues recommend.
-
-## References
-
-- [arXiv RSS Feeds](https://info.arxiv.org/help/rss.html) -- Official arXiv RSS documentation
-- [Google Scholar Alerts](https://scholar.google.com/scholar_alerts) -- Citation and keyword alerts
-- [Semantic Scholar](https://www.semanticscholar.org/) -- AI-powered paper search
-- [Connected Papers](https://www.connectedpapers.com/) -- Visual paper exploration
-- [Research Rabbit](https://www.researchrabbit.ai/) -- Collection-based paper discovery

package/skills/literature/fulltext/zotero-scihub-guide/SKILL.md

@@ -1,168 +0,0 @@
----
-name: zotero-scihub-guide
-description: "Zotero plugin for automatic PDF retrieval from Sci-Hub"
-metadata:
-  openclaw:
-    emoji: "🔓"
-    category: "literature"
-    subcategory: "fulltext"
-    keywords: ["Zotero", "Sci-Hub", "PDF download", "open access", "full text", "paper retrieval"]
-    source: "https://github.com/ethanwillis/zotero-scihub"
----
-
-# Zotero Sci-Hub Guide
-
-## Overview
-
-Zotero Sci-Hub is a Zotero plugin that automatically fetches PDFs from Sci-Hub when papers cannot be found through standard open-access channels. It integrates seamlessly into Zotero's existing PDF retrieval workflow — when Zotero's built-in retriever fails, the plugin automatically attempts Sci-Hub as a fallback. Useful for researchers at institutions with limited journal subscriptions.
-
-## Installation
-
-```bash
-# Download the .xpi file from GitHub releases
-# In Zotero 7: Tools → Add-ons → Install Add-on From File
-
-# Manual installation
-# 1. Go to https://github.com/ethanwillis/zotero-scihub/releases
-# 2. Download zotero-scihub-*.xpi
-# 3. In Zotero: Tools → Add-ons → gear icon → Install from file
-```
-
-## Configuration
-
-```
-# In Zotero: Edit → Preferences → Zotero Sci-Hub
-
-# Settings:
-# 1. Sci-Hub URL: Set current working mirror
-#    - The plugin ships with default URLs
-#    - Update if mirrors change
-
-# 2. Automatic mode:
-#    - ON: Try Sci-Hub automatically after Zotero fails
-#    - OFF: Only fetch via right-click menu
-
-# 3. DOI sources: Where to look for DOIs
-#    - Item DOI field
-#    - Item URL field
-#    - Item Extra field
-```
-
-## Usage Workflow
-
-```markdown
-### Automatic PDF Retrieval
-1. Add item to Zotero (via browser connector, DOI, or manual)
-2. Zotero tries built-in PDF retrieval (Open Access, institutional)
-3. If no PDF found → plugin automatically queries Sci-Hub
-4. PDF attached to Zotero item
-
-### Manual Retrieval
-1. Right-click item(s) in Zotero
-2. Select "Fetch PDF from Sci-Hub"
-3. Works for single items or batch selection
-
-### Bulk Retrieval
-1. Select multiple items (Ctrl+A for all)
-2. Right-click → "Fetch PDF from Sci-Hub"
-3. Plugin processes items sequentially with rate limiting
-```
-
-## Integration with Other Plugins
-
-```markdown
-### Recommended Plugin Stack
-1. **Zotero Connector** — Browser extension for importing items
-2. **Zotero Sci-Hub** — PDF fallback retrieval
-3. **ZotFile/ZotMoov** — Organize downloaded PDFs
-4. **Zotero Better BibTeX** — Citation key management
-5. **Zotero PDF Translate** — Translate retrieved papers
-
-### Workflow
-Import item → Auto-fetch PDF → Organize files → Read & annotate
-```
-
-## Troubleshooting
-
-```markdown
-### Common Issues
-
-**PDF not found:**
-- Check if DOI is present in item metadata
-- Try updating the Sci-Hub mirror URL
-- Some very recent papers may not be available yet
-
-**Connection errors:**
-- Current mirror may be down; try alternate URL
-- Check network/proxy settings
-- Some institutions block Sci-Hub domains
-
-**Duplicate PDFs:**
-- Disable automatic mode if using other PDF fetchers
-- Check Zotero's duplicate detection settings
-```
-
-## Programmatic Alternative
-
-```python
-# For building custom PDF retrieval pipelines
-import requests
-
-def fetch_paper_by_doi(doi, output_path):
-    """Attempt to fetch paper PDF via DOI resolution."""
-    # Try Unpaywall first (legal open access)
-    unpaywall_url = (
-        f"https://api.unpaywall.org/v2/{doi}"
-        f"?email=your@email.com"
-    )
-    resp = requests.get(unpaywall_url)
-    if resp.ok:
-        data = resp.json()
-        if data.get("is_oa") and data.get("best_oa_location"):
-            pdf_url = data["best_oa_location"].get("url_for_pdf")
-            if pdf_url:
-                pdf = requests.get(pdf_url)
-                with open(output_path, "wb") as f:
-                    f.write(pdf.content)
-                return True
-
-    # Try CORE API
-    core_url = f"https://api.core.ac.uk/v3/search/works?q=doi:{doi}"
-    resp = requests.get(core_url)
-    if resp.ok:
-        results = resp.json().get("results", [])
-        if results and results[0].get("downloadUrl"):
-            pdf = requests.get(results[0]["downloadUrl"])
-            with open(output_path, "wb") as f:
-                f.write(pdf.content)
-            return True
-
-    return False
-```
-
-## Legal Considerations
-
-```markdown
-### Open Access Alternatives
-Before using Sci-Hub, check these legal sources:
-1. **Unpaywall** — Browser extension for legal OA versions
-2. **CORE** — Aggregator of OA research papers
-3. **PubMed Central** — Free biomedical literature archive
-4. **arXiv/bioRxiv** — Preprint servers
-5. **Author websites** — Many post preprints freely
-6. **Interlibrary Loan** — Request through your library
-7. **Email the author** — Most researchers share on request
-```
-
-## Use Cases
-
-1. **PDF retrieval**: Automatic paper downloading for Zotero
-2. **Literature collection**: Build reading libraries efficiently
-3. **Systematic reviews**: Bulk-fetch papers for review pipelines
-4. **Research onboarding**: Quickly gather papers for new topics
-
-## References
-
-- [Zotero Sci-Hub GitHub](https://github.com/ethanwillis/zotero-scihub)
-- [Unpaywall](https://unpaywall.org/) — Legal OA alternative
-- [CORE](https://core.ac.uk/) — OA aggregator