academic-talon
🎓 Full-stack academic research assistant - Search papers → Extract publication-ready BibTeX (header) → Full TEI XML document structure parsing (via GROBID) → Archive to Zotero → Serve local PDFs. Fixed arXiv AND search semantics, generates conference/journal-standard BibTeX, auto-creates Zotero collections, enables deep document understanding via GROBID structured parsing.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bigdogaaa/academic-talon🎓 Academic Talon Skill
Your AI-powered academic research assistant for paper search → BibTeX extraction → Zotero archiving → local PDF serving.
Save hours of manual work searching papers, copying citations, and organizing your library.
🎯 What it does (when to use this skill)
Trigger this skill when the user wants to:
| Task | Description |
|---|---|
| 🔍 Search papers | Find papers across multiple academic search engines (arXiv, Google Scholar, Semantic Scholar, Tavily) |
| 📝 Extract BibTeX (header analysis) | Parse PDF header and output publication-ready BibTeX matching AI conference/journal standards |
| 📄 Full text analysis | Extract full document structure in TEI XML format for further processing |
| 🗄️ Archive to Zotero | Automatically save papers to your Zotero library, default to openclaw collection, auto-create collections |
| 📂 Local PDF library | Maintain a local PDF collection and serve it via HTTP for direct access from Zotero |
🔧 Architecture & Dependencies
This is a toolbox skill that provides multiple independent academic research tools. You can use just the features you need. A common complete workflow looks like this:
User Query
↓
[academic-talon] ← this skill
↓
1. Search → Multiple search APIs (arXiv, Google Scholar via SerpAPI, etc.)
↓
2. PDF Download → saved to local `pdfs/` directory
↓
3. PDF Parsing → **GROBID service** processes PDF
↓
- Header analysis → extracts metadata → skill generates clean BibTeX
- Full text analysis → returns complete TEI XML with full document structure
↓
4. If header analysis: BibTeX Generation → skill formats clean publication-ready output
↓
5. Zotero Archiving → via **pyzotero** → your Zotero library → auto-add to collection
↓
6. PDF Serving → built-in HTTP server serves PDFs from your intranet
↓
Result: Paper in Zotero with working PDF link, clean BibTeX ready for citation
You don't have to use this full workflow - use individual tools as needed.
Required External Services
| Service | Purpose | Why do you need it? | Required? |
|---|---|---|---|
| GROBID | PDF metadata extraction | Parses PDF headers to extract title, authors, publication info for BibTeX | ✅ Required |
| Zotero API | Paper archiving | Stores papers in your Zotero library with correct metadata | ✅ Required for archiving |
| SerpAPI Key | Google Scholar search | enables searching Google Scholar | ⚙️ Optional (enables more results) |
| Semantic Scholar API Key | Semantic Scholar search | enables Semantic Scholar results | ⚙️ Optional |
| Tavily API Key | Tavily search | enables Tavily results | ⚙️ Optional |
⚙️ Setup Instructions
1. Install Python dependencies
pip install -r skills/academic-talon/requirements.txt
2. Configure environment variables (skills/academic-talon/.env)
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bigdogaaa-academic-talon": {
"enabled": true,
"auto_update": true
}
}
}