hf-papers
Browse, search, and analyze papers from the Hugging Face Papers platform. Get trending papers, search by topic, and retrieve detailed metadata including community engagement and linked resources.
Description
This skill wraps the Hugging Face Papers public API. It provides access to daily trending papers, keyword search, paper details (abstract, authors, upvotes, GitHub repos, project pages), and discussion comments. No authentication required.
For full paper text, use the returned arXiv ID with the arxiv-reader skill.
Results are cached locally (~/.cache/hf-papers/) for fast repeat access.
Usage Examples
- - "What are today's trending papers on Hugging Face?"
- "Search Hugging Face Papers for diffusion models"
- "Get details for paper 2401.12345 on HF"
- "Show me comments on HF paper 2405.67890"
Process
- 1. Discover — Use
hf_daily_papers to see what's trending today - Search — Use
hf_search_papers to find papers on a topic - Inspect — Use
hf_paper_detail to get full metadata for a specific paper - Discuss — Use
hf_paper_comments to read community discussion - Deep read — Use
arxiv_fetch (from arxiv-reader) with the paper's arXiv ID for full text
Tools
hfdailypapers
Get today's trending papers from Hugging Face.
Parameters:
- -
limit (number, optional): Max papers to return (default: 20, max: 100) - INLINECODE8 (string, optional): Sort by
upvotes or date (default: upvotes)
Returns: INLINECODE12
Example:
CODEBLOCK0
hfsearchpapers
Search Hugging Face Papers by keyword.
Parameters:
- -
query (string, required): Search query
Returns: INLINECODE14
Example:
CODEBLOCK1
hfpaperdetail
Get detailed metadata for a specific paper.
Parameters:
- -
paper_id (string, required): Paper ID (arXiv ID, e.g. 2401.12345)
Returns: INLINECODE17
Example:
CODEBLOCK2
hfpapercomments
Get discussion comments for a paper.
Parameters:
- -
paper_id (string, required): Paper ID (arXiv ID)
Returns: INLINECODE19
Example:
CODEBLOCK3
Notes
- - All results are cached locally — repeat requests are instant (15-minute TTL for daily/search, 1-hour for details)
- Paper IDs are arXiv IDs — use with
arxiv-reader skill for full LaTeX text - No authentication required; uses HF public API
- Daily papers update throughout the day as the community submits and upvotes
hf-papers
浏览、搜索和分析来自Hugging Face Papers平台的论文。获取热门论文、按主题搜索，并检索包括社区互动和关联资源在内的详细元数据。
描述
该技能封装了Hugging Face Papers的公共API。它提供每日热门论文、关键词搜索、论文详情（摘要、作者、点赞数、GitHub仓库、项目页面）以及讨论评论的访问。无需认证。
如需获取论文全文，请使用返回的arXiv ID配合arxiv-reader技能。
结果会本地缓存（~/.cache/hf-papers/），以便快速重复访问。
使用示例
- - 今天Hugging Face上有什么热门论文？
- 在Hugging Face Papers上搜索扩散模型
- 获取HF上论文2401.12345的详细信息
- 显示HF论文2405.67890的评论
流程
- 1. 发现 — 使用hfdailypapers查看今日热门论文
- 搜索 — 使用hfsearchpapers按主题查找论文
- 查看 — 使用hfpaperdetail获取特定论文的完整元数据
- 讨论 — 使用hfpapercomments阅读社区讨论
- 深度阅读 — 使用arxiv_fetch（来自arxiv-reader）配合论文的arXiv ID获取全文
工具
hfdailypapers
获取Hugging Face今日热门论文。
参数：
- - limit（数字，可选）：返回的最大论文数（默认：20，最大：100）
- sort（字符串，可选）：按upvotes或date排序（默认：upvotes）
返回： { papers: [{ id, title, summary, upvotes, authors, publishedAt, githubRepo?, projectPage?, aisummary?, aikeywords? }], count: number }
示例：
json
{ limit: 10, sort: upvotes }
hfsearchpapers
按关键词搜索Hugging Face Papers。
参数：
返回： { papers: [{ id, title, summary, upvotes, authors, publishedAt, githubRepo?, projectPage?, ai_summary? }], query: string, count: number }
示例：
json
{ query: 多模态推理 }
hfpaperdetail
获取特定论文的详细元数据。
参数：
- - paper_id（字符串，必需）：论文ID（arXiv ID，例如2401.12345）
返回： { id, title, summary, authors, publishedAt, upvotes, numComments, githubRepo?, githubStars?, projectPage?, aisummary?, aikeywords?, organization? }
示例：
json
{ paper_id: 2401.12345 }
hfpapercomments
获取论文的讨论评论。
参数：
- - paper_id（字符串，必需）：论文ID（arXiv ID）
返回： { paper_id, comments: [{ author, content, createdAt }], count: number }
示例：
json
{ paper_id: 2401.12345 }
注意事项
- - 所有结果都会本地缓存——重复请求即时响应（每日/搜索缓存15分钟，详情缓存1小时）
- 论文ID为arXiv ID——配合arxiv-reader技能获取完整LaTeX文本
- 无需认证；使用HF公共API
- 每日论文随社区提交和点赞情况全天更新
