Agent Skills › Prismer-AI/Prismer › hf-papers

hf-papers

GitHub

用于浏览、搜索和分析 Hugging Face 上的机器学习论文。支持查看热门论文、关键词搜索、获取论文元数据及社区讨论，并可结合 arXiv 工具进行深度阅读，适用于 ML 研究探索场景。

docker/plugin/prismer-workspace/skills/hf-papers/SKILL.md Prismer-AI/Prismer

Trigger Scenarios

查找最新 AI/ML 论文搜索特定技术主题的研究了解 Hugging Face 平台趋势

Install

npx skills add Prismer-AI/Prismer --skill hf-papers -g -y

More Options

Non-standard path

npx skills add https://github.com/Prismer-AI/Prismer/tree/main/docker/plugin/prismer-workspace/skills/hf-papers -g -y

Use without installing

npx skills use Prismer-AI/Prismer@hf-papers

指定 Agent (Claude Code)

npx skills add Prismer-AI/Prismer --skill hf-papers -a claude-code -g -y

安装 repo 全部 skill

npx skills add Prismer-AI/Prismer --all -g -y

预览 repo 内 skill

npx skills add Prismer-AI/Prismer --list

SKILL.md

Frontmatter

{
    "name": "hf-papers",
    "metadata": {
        "openclaw": {
            "tags": [
                "huggingface",
                "research",
                "academic",
                "papers",
                "trending"
            ],
            "emoji": "🤗",
            "requires": {
                "os": [
                    "darwin",
                    "linux",
                    "win32"
                ],
                "bins": []
            }
        }
    },
    "description": "Browse trending papers, search by keyword, and get paper details from Hugging Face Papers. Use when the user wants to find ML research, asks about recent AI papers, trending models, or mentions Hugging Face Papers."
}

hf-papers

Browse, search, and analyze papers from the Hugging Face Papers platform.

Process

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

hf_daily_papers — Get trending papers. Params: limit (default: 20), sort (upvotes or date)
hf_search_papers — Search by keyword. Params: query (required)
hf_paper_detail — Get paper metadata. Params: paper_id (required, arXiv ID)
hf_paper_comments — Get discussion comments. Params: paper_id (required)