← Back to Skills Marketplace
ddongcui

Hfmirror Trending

by shunshiwei · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
115
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install hfmirror-trending
Description
通过 HF-Mirror 公开 API 获取 Hugging Face 实时热门趋势,并生成结构化中文 Markdown 报告。适用于各种对话式 AI 代理。
README (SKILL.md)

hfmirror_trending (跨平台通用版)

此 Skill 使 AI 代理能够自主获取并解析 HF-Mirror (hf-mirror.com) 的实时热点趋势。

数据来源说明:本 Skill 调用 https://hf-mirror.com/api/trending —— 这是 HF-Mirror 提供的公开、免登录 REST API,无需任何 Token 或账号授权,不涉及任何登录后数据抓取或绕过访问限制的行为。

适用场景

当用户发起关于 Hugging Face 或者是huggingface mirror最近热门模型、数据集或项目的询问时。例如:

  • “最近有哪些模型比较流行?”
  • “hugging face上最近比较火的模型有哪些?”
  • “推送今天的huggingface mirror热榜。”
  • “帮我解析一下 HF-Mirror 的趋势。”

代理工作流 (Agent Workflow)

AI 代理在处理上述指令时,应遵循以下通用的端到端逻辑:

  1. 自动拉取与解析: 代理应调用本 Skill 根目录下的处理脚本,利用其内置的网络请求功能。

    python scripts/summarize.py --fetch [out_path.md]
    

    注意:脚本兼容 Python 3,可以在 Windows (PowerShell/CMD)、Linux (Shell) 或 macOS 环境下直接运行。

  2. 精美报告生成: 脚本会自动从 https://hf-mirror.com/api/trending 抓取 JSON,并直接生成结构化的中文 Markdown。

  3. 智能推送: 代理读取生成的文件内容,并将其作为精美的消息推送给用户。

核心设计 (跨平台与环境解耦)

  • 路径无关: 代理应根据其所在的环境,通过相对路径或 Skill 环境配置来定位 scripts/summarize.py
  • 零依赖: 脚本仅使用 Python 3 标准库(json, urllib, os, sys),无需安装任何第三方包,在最精简的容器或 CLI 环境中亦可直接运行。
  • 动态抓取: 内置 --fetch 参数,消除了手动准备中间文件的需求,实现了从 API 到报告的一键转化。
  • 合规访问: 使用具名 User-Agent (hfmirror-trending-skill/1.0) 标识请求来源,遵循公开 API 最佳实践。

核心输出字段说明

  • 模型 ID: 唯一的模型标识符。
  • 下载量与点赞数: 反映社区热度。
  • 参数规模: 自动换算(如 7B, 27B),帮助用户评估部署成本。
  • 任务标签: 区分 ASR, TTS, OCR 等不同 AI 领域。
Usage Guidance
This skill appears coherent and limited: it only fetches a public HF-Mirror endpoint and generates a Markdown report. Review the script if you want to confirm behavior (it uses urllib and writes a single output file). Consider the usual operational cautions: allow network access only if you trust hf-mirror.com, run the script in a sandboxed environment if you are worried about write permissions, and verify the agent's invocation scope if you do not want autonomous periodic fetches.
Capability Analysis
Type: OpenClaw Skill Name: hfmirror-trending Version: 1.0.0 The skill is designed to fetch trending AI models and datasets from the HF-Mirror API and generate a structured Markdown report. The Python script `scripts/summarize.py` uses only standard libraries (urllib, json) to perform a GET request to a hardcoded endpoint (hf-mirror.com) and contains no evidence of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
Name/description claim to fetch HF-Mirror trending data; included script and instructions only access https://hf-mirror.com/api/trending and produce a Markdown report — this matches the stated purpose.
Instruction Scope
SKILL.md directs the agent to run scripts/summarize.py --fetch which fetches the public API, parses JSON, and writes a Markdown file. The script does not read unrelated system files or environment variables.
Install Mechanism
No install spec provided; the skill is instruction+script only and uses Python standard library; nothing is downloaded or installed at runtime.
Credentials
No environment variables, credentials, or config paths are requested. The script uses only network access to hf-mirror.com which is necessary for its function.
Persistence & Privilege
Skill is not always-enabled and does not modify other skills or system-wide settings. It writes only its own output Markdown when invoked.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install hfmirror-trending
  3. After installation, invoke the skill by name or use /hfmirror-trending
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of hfmirror-trending. - Enables agents to fetch real-time trending data from HF-Mirror's public API without login or tokens. - Generates structured, Chinese-language Markdown reports summarizing trending Hugging Face models and datasets. - Fully cross-platform and dependency-free (Python standard library only). - Includes workflow guidance for integration into AI assistants. - Utilizes a public, identified User-Agent for compliant API requests.
Metadata
Slug hfmirror-trending
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Hfmirror Trending?

通过 HF-Mirror 公开 API 获取 Hugging Face 实时热门趋势,并生成结构化中文 Markdown 报告。适用于各种对话式 AI 代理。 It is an AI Agent Skill for Claude Code / OpenClaw, with 115 downloads so far.

How do I install Hfmirror Trending?

Run "/install hfmirror-trending" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Hfmirror Trending free?

Yes, Hfmirror Trending is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Hfmirror Trending support?

Hfmirror Trending is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Hfmirror Trending?

It is built and maintained by shunshiwei (@ddongcui); the current version is v1.0.0.

💬 Comments