
赋予你的代理人拥抱面生态系统的力量
概览
拥抱面部技能是用于数据集创建、模型训练和评估等人工智能/机器学习任务的定义。它们与所有主要编码代理工具如OpenAI Codex、Anthropic的Claude Code、Google DeepMind的Gemini CLI和Cursor互操作。 本仓库中的技能遵循标准化的代理技能格式。 先从 hf-cli 开始。这是推荐安装的第一个技能:它会教你的代理所有 hf 命令(搜索模型、管理数据集和桶、启动 Spaces、运行作业),并且是从你本地安装的 CLI 生成的,保持最新。 实际上,技能是自成一体的文件夹,将指令、脚本和资源打包在一起,供AI代理在特定用例中使用。每个文件夹包含一个 SKILL.md 文件,内含YAML前置信息(名称和描述),后面是技能激活时编码代理遵循的指导。 如果你的代理不支持技能,你可以直接用agentsmd/AGENTS.md作为备选。
概述(AI 翻译)
“抱脸技能”是用于定义AI/ML任务的,如数据集创建、模型训练和评估。客户端插件市场将hf-cli技能作为核心枢纽操作的启动路径;额外的工作流程技能可以通过hf skills add 按需安装,或由具技能意识的客户端通过CLI/MCP集成发现。
本仓库中的技能遵循标准化的代理技能格式。
[!注] 只是想让你的代理访问拥抱面中心? 从
hf-cli开始。这是推荐安装的第一个技能:它会教代理所有hf命令(搜索模型、管理数据集和桶、启动Spaces、运行作业),并且是从你本地安装的命令行生成的,保持最新。
技能是如何运作的?
实际上,技能是自成一体的文件夹,将指令、脚本和资源打包在一起,供AI代理在特定用例中使用。每个文件夹包含一个带有YAML前置信息(名称和描述)的SKILL.md文件,后面是编码代理在技能激活时遵循的指导。
[!提示] 如果你的特工不支援技能,你可以直接用
agentsmd/AGENTS.md作为备选。
本页由 AI 翻译,技术细节请以原文为准。
README
以下为原文 README 节选,完整内容请查看原文。
Hugging Face Skills
Hugging Face Skills are definitions for AI/ML tasks like dataset creation, model training, and evaluation. The client plugin marketplaces expose the hf-cli skill as the bootstrap path for core Hub operations; additional workflow skills can be installed on demand with hf skills add or discovered by skill-aware clients over CLI/MCP integrations.
The skills in this repository follow the standardized Agent Skills format.
[!NOTE] Just want to give your agent access to the Hugging Face Hub? Start with
hf-cli. It’s the recommended first Skill to install: it teaches your agent everyhfcommand (search models, manage datasets and buckets, launch Spaces, run jobs) and is generated from your locally installed CLI so it stays current.
How do Skills work?
In practice, skills are self-contained folders that package instructions, scripts, and resources together for an AI agent to use on a specific use case. Each folder includes a SKILL.md file with YAML frontmatter (name and description) followed by the guidance your coding agent follows while the skill is active.
[!TIP] If your agent doesn’t support skills, you can use
agentsmd/AGENTS.mddirectly as a fallback.
The hf-cli skill in this repository is also available through:
- Cursor Marketplace (https://cursor.com/marketplace/huggingface)
- Codex Plugins Directory (https://developers.openai.com/codex/plugins)
Installation
Hugging Face skills are compatible with Claude Code, Codex, Gemini CLI, and Cursor.
Claude Code
- Register the repository as a plugin marketplace:
/plugin marketplace add huggingface/skills
- Install the CLI skill:
/plugin install hf-cli@huggingface/skills
- To install another Hugging Face skill, use the
hfCLI:
hf skills add
Codex
-
Copy or symlink any skills you want to use from this repository’s
skills/directory into one of Codex’s standard.agents/skillslocations (for example,$REPO_ROOT/.agents/skillsor$HOME/.agents/skills) as described in the Codex Skills guide. -
Once a skill is available in one of those locations, Codex will discover it using the Agent Skills standard and load the
SKILL.mdinstructions when it decides to use that skill or when you explicitly invoke it. -
If your Codex setup still relies on
AGENTS.md, you can use the generatedagentsmd/AGENTS.mdfile in this repo as a fallback bundle of instructions.
Gemini CLI
-
This repo includes
gemini-extension.jsonto integrate with the Gemini CLI. -
Install locally:
gemini extensions install . --consent
or use the GitHub URL:
gemini extensions install https://github.com/huggingface/skills.git --consent
推荐工具
换一个关键词,或者移除筛选条件。
安装
npx skillfish add huggingface/skills