An AI agent skill to browse trending papers, search research topics, and retrieve detailed metadata from the Hugging Face Papers platform.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install hf-papers
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 hf-papers 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 HF Papers (Hugging Face Research Explorer)?
The HF Papers skill enables AI agents to interface directly with the Hugging Face Papers ecosystem, a hub for the latest advancements in machine learning. By integrating this functionality into Openclaw Skills, developers and researchers can automate the discovery of trending papers, explore community-driven upvotes, and extract deep metadata such as abstracts, authors, and linked GitHub repositories. This skill is essential for staying at the forefront of AI research without the manual overhead of daily browsing.
One of the standout benefits of using this within the suite of Openclaw Skills is the ability to link research metadata with technical implementations. It provides a structured way to navigate the often overwhelming flow of new papers, allowing for sophisticated search queries and sentiment analysis through community discussion retrieval. Because it relies on the public API, it provides immediate value for any AI-driven research workflow.
HF Papers (Hugging Face Research Explorer) Use Cases
- Identify today's trending machine learning papers based on community upvotes.
- Search for specific research topics such as LLM optimization or multimodal reasoning.
- Retrieve detailed metadata including abstracts, authors, and project links.
- Monitor community feedback and discussion comments on recent publications.
- Extract GitHub repository links to find official code implementations for new models.
How HF Papers (Hugging Face Research Explorer) Works
- The agent calls the hf_daily_papers or hf_search_papers tool to find relevant content.
- The skill queries the Hugging Face public API to retrieve a list of papers matching the criteria.
- Results are processed and returned with metadata like upvotes, paper IDs, and summaries.
- If detailed information is needed, the hf_paper_detail tool fetches comprehensive metadata for a specific paper ID.
- The skill automatically manages a local cache at ~/.cache/hf-papers/ to ensure high performance for repeat queries.
HF Papers (Hugging Face Research Explorer) Setup
To start using this skill with your agent, ensure you have the Openclaw Skills environment configured. No API keys are required for the Hugging Face public API.
# Install the skill via the Openclaw CLI
openclaw install hf-papers
HF Papers (Hugging Face Research Explorer) Data Schema & Taxonomy
The skill manages its data through structured JSON responses and local file caching. Below is a breakdown of the metadata taxonomy for papers:
| Attribute | Description | Data Type |
|---|---|---|
| id | The unique identifier (usually an arXiv ID) | String |
| upvotes | Total community upvotes on Hugging Face | Number |
| authors | List of paper contributors | Array |
| githubRepo | Linked official code repository | String (Optional) |
| ai_summary | Automatically generated summary of the research | String (Optional) |
| publishedAt | Date of publication | ISO Date String |
HF Papers (Hugging Face Research Explorer) Advanced Features
- Built-in TTL (Time-To-Live) caching logic: 15 minutes for searches and 1 hour for detailed metadata to optimize performance.
- Seamless cross-skill integration with the arxiv-reader skill using standardized arXiv IDs for full-text LaTeX extraction.
- Advanced sorting capabilities allowing agents to prioritize research by community engagement (upvotes) or recency.
- Access to deep community insights via retrieval of threaded discussion comments for any paper ID.
- Native support across multiple operating systems including macOS, Linux, and Windows.
SKILL.md
Loading
Related Openclaw Skills
Break-even Calculator for Ecommerce
A professional-grade unit economics tool designed to calculate the real no-loss line for ecommerce products by modeling complex variable costs.
Bilibili Hot Trend
A specialized automation tool for analyzing Bilibili video performance, creator metrics, and public ranking trends.
Camera API Skill
A comprehensive AI skill for managing cloud-based cameras, enabling real-time monitoring, screenshot capture, and automated event summarization.
Session Observer
A diagnostic utility for monitoring session health, token usage, and context window pressure in real-time.
Perplexity Search
A powerful search skill that integrates Perplexity Sonar models to provide citation-backed web answers and long-form research reports within your agent workflow.
Ubuntu Inspector
A comprehensive system inspection and health monitoring tool designed for Ubuntu servers.
Featured*
