- Home
- Skills
- Research & Analysis
- Scholar Paper Finder
Works with the AI Agents you already use
Scholar Paper Finder
Use to search arXiv by keyword, author, category, or ID; fetch and read abstracts, download PDFs, extract metadata, watch a topic for new papers, and export cle
Free
Scholar Paper Finder
Example session with this skill installed
Find the latest 5 papers in cs.LG about diffusion models, download the PDFs, and give me the BibTeX citations.
- Read your context and instructions
- Compiled the scholar paper finder
Found 5 papers.
IDs: 2506.12345, 2506.12346...
Abstracts retrieved.
PDFs downloaded and converted to text.
BibTeX generated
@misc{author2025,
title = {Diffusion Models...},
eprint = {2506.12345},
...
}
Connects securely to your tools. The creator never sees your data.
About this skill
The problem
Finding specific academic research on arXiv is tedious when relying on manual web searches and browser-based PDF viewing. Developers and researchers often struggle to automate literature reviews, monitor new topic trends, or generate accurate BibTeX citations for their local repositories.
What it does
- Searches arXiv using Boolean logic for keywords, authors, categories, or specific paper IDs.
- Parses Atom XML responses to extract metadata, including abstracts and submission dates.
- Downloads full-text PDFs and converts them to searchable text for deeper analysis.
- Implements a daily "watch" function to identify and diff new papers in specific research areas.
- Generates correctly formatted BibTeX entries for reference management software.
Frameworks & tools
This skill utilizes the official arXiv API, Python for XML parsing, and pdftotext for full-text extraction.
Why this beats prompting it yourself
Standard LLM prompts rely on training data that quickly becomes outdated or lack the ability to fetch the actual PDF content for verification. This skill interfaces directly with the live arXiv API and handles the specific XML parsing and BibTeX formatting rules that typically cause LLM hallucinations.
Use cases
- Automate a daily digest of new papers in specific machine learning categories.
- Retrieve and index the full text of all papers published by a specific author.
- Build a local citation library by converting arXiv IDs into clean BibTeX files.
- Perform deep keyword searches across thousands of abstracts to find niche research.
Known limitations
Cannot access paywalled literature outside of arXiv. It does not provide citation counts or impact metrics. Subject to arXiv API rate limits.
Only works with arXiv content. No support for citation metrics or impact factors. Requires pdftotext for full-body extraction.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
This skill has been used 8 times.
Trust & safety
Security scan
Security scan passed 3 months ago
- Free with an Agensi account
Requires
Permissions
Allowed Hosts