Hugging Face API 工具构建器 - 创建可重用命令行脚本与实用工具

hugging-face-tool-builder by huggingface/skills

225 周安装量

10,000 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/huggingface/skills --skill hugging-face-tool-builder

AI/机器学习自动化命令行工具

🇨🇳中文介绍

Hugging Face API 工具构建器

你现在的目标是创建可重用的命令行脚本和实用工具，用于使用 Hugging Face API，允许在有用的情况下进行链式调用、管道传输和中间处理。你可以直接访问 API，也可以使用 hf 命令行工具。模型和数据集卡片可以直接从仓库访问。

脚本规则

请确保遵循以下规则：

脚本必须接受 --help 命令行参数来描述其输入和输出
非破坏性脚本在移交给用户之前应进行测试
优先使用 Shell 脚本，但如果复杂度或用户需求需要，可以使用 Python 或 TSX。
重要：使用 HF_TOKEN 环境变量作为 Authorization 请求头。例如：curl -H "Authorization: Bearer ${HF_TOKEN}" https://huggingface.co/api/。这为数据访问提供了更高的速率限制和适当的授权。
在确定最终设计之前，先研究 API 返回数据的结构；在组合性有优势的地方利用管道和链式调用——尽可能选择简单的解决方案。
完成后分享使用示例。

在有疑问或需要澄清的地方，请务必确认用户的偏好。

示例脚本

以下路径相对于此技能目录。

参考示例：

references/hf_model_papers_auth.sh — 自动使用 HF_TOKEN 并链式执行 trending → 模型元数据 → 模型卡片解析（带后备方案）；它演示了多步骤 API 使用以及对受保护/私有内容的授权管理。

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

相关 Skills

FlyClaw：零登录航班聚合查询工具，Python实现多源航班信息与价格搜索

4,000,000 周安装

find-skills 技能搜索工具 - Vercel Labs 开源智能体技能包管理器

812,900 周安装

Azure RBAC 权限管理工具：查找最小角色、创建自定义角色与自动化分配

117,000 周安装

React 组合模式指南：Vercel 组件架构最佳实践，提升代码可维护性

109,600 周安装

references/find_models_by_paper.sh — 通过 --token 可选地使用 HF_TOKEN，进行一致的认证搜索，并在 arXiv 前缀搜索范围过窄时提供重试路径；它展示了稳健的查询策略和清晰的面向用户的帮助信息。

references/hf_model_card_frontmatter.sh — 使用 hf CLI 下载模型卡片，提取 YAML 前言，并输出 NDJSON 摘要（许可证、管道标签、标签、受保护提示标志）以便于过滤。

基础示例（极其简单，逻辑最少，使用 HF_TOKEN 请求头输出原始 JSON）：

references/baseline_hf_api.sh — bash
references/baseline_hf_api.py — python
references/baseline_hf_api.tsx — typescript 可执行文件

可组合实用工具（stdin → NDJSON）：

references/hf_enrich_models.sh — 从 stdin 读取模型 ID，获取每个 ID 的元数据，为流式管道输出每行一个 JSON 对象。

通过管道实现组合性（兼容 shell 的 JSON 输出）：

references/baseline_hf_api.sh 25 | jq -r '.[].id' | references/hf_enrich_models.sh | jq -s 'sort_by(.downloads) | reverse | .[:10]'
references/baseline_hf_api.sh 50 | jq '[.[] | {id, downloads}] | sort_by(.downloads) | reverse | .[:10]'
printf '%s\n' openai/gpt-oss-120b meta-llama/Meta-Llama-3.1-8B | references/hf_model_card_frontmatter.sh | jq -s 'map({id, license, has_extra_gated_prompt})'

以下是 https://huggingface.co 上可用的主要 API 端点

/api/datasets
/api/models
/api/spaces
/api/collections
/api/daily_papers
/api/notifications
/api/settings
/api/whoami-v2
/api/trending
/oauth/userinfo

API 使用 OpenAPI 标准在 https://huggingface.co/.well-known/openapi.json 进行了文档化。

重要： 不要尝试 直接读取 https://huggingface.co/.well-known/openapi.json，因为它太大而无法处理。

重要： 使用 jq 查询和提取相关部分。例如，

获取所有 160 个端点的命令

curl -s "https://huggingface.co/.well-known/openapi.json" | jq '.paths | keys | sort'

模型搜索端点详情

curl -s "https://huggingface.co/.well-known/openapi.json" | jq '.paths["/api/models"]'

你也可以查询端点以查看数据的结构。这样做时，请将结果限制在较小的数量，以便于处理，但仍具有代表性。

使用 HF 命令行工具

hf 命令行工具让你可以进一步访问 Hugging Face 仓库内容和基础设施。

❯ hf --help
Usage: hf [OPTIONS] COMMAND [ARGS]...

  Hugging Face Hub CLI

Options:
  --help                Show this message and exit.

Commands:
  auth                 Manage authentication (login, logout, etc.).
  cache                Manage local cache directory.
  download             Download files from the Hub.
  endpoints            Manage Hugging Face Inference Endpoints.
  env                  Print information about the environment.
  jobs                 Run and manage Jobs on the Hub.
  repo                 Manage repos on the Hub.
  repo-files           Manage files in a repo on the Hub.
  upload               Upload a file or a folder to the Hub.
  upload-large-folder  Upload a large folder to the Hub.
  version              Print information about the hf version.

hf CLI 命令已取代现已弃用的 huggingface_hub CLI 命令。

🇺🇸English

Hugging Face API Tool Builder

Your purpose is now is to create reusable command line scripts and utilities for using the Hugging Face API, allowing chaining, piping and intermediate processing where helpful. You can access the API directly, as well as use the hf command line tool. Model and Dataset cards can be accessed from repositories directly.

Script Rules

Make sure to follow these rules:

Scripts must take a --help command line argument to describe their inputs and outputs
Non-destructive scripts should be tested before handing over to the User
Shell scripts are preferred, but use Python or TSX if complexity or user need requires it.
IMPORTANT: Use the HF_TOKEN environment variable as an Authorization header. For example: curl -H "Authorization: Bearer ${HF_TOKEN}" https://huggingface.co/api/. This provides higher rate limits and appropriate authorization for data access.
Investigate the shape of the API results before commiting to a final design; make use of piping and chaining where composability would be an advantage - prefer simple solutions where possible.
Share usage examples once complete.

Be sure to confirm User preferences where there are questions or clarifications needed.

Sample Scripts

Paths below are relative to this skill directory.

Reference examples:

references/hf_model_papers_auth.sh — uses HF_TOKEN automatically and chains trending → model metadata → model card parsing with fallbacks; it demonstrates multi-step API usage plus auth hygiene for gated/private content.
references/find_models_by_paper.sh — optional HF_TOKEN usage via --token, consistent authenticated search, and a retry path when arXiv-prefixed searches are too narrow; it shows resilient query strategy and clear user-facing help.
references/hf_model_card_frontmatter.sh — uses the hf CLI to download model cards, extracts YAML frontmatter, and emits NDJSON summaries (license, pipeline tag, tags, gated prompt flag) for easy filtering.

Baseline examples (ultra-simple, minimal logic, raw JSON output with HF_TOKEN header):

references/baseline_hf_api.sh — bash
references/baseline_hf_api.py — python
references/baseline_hf_api.tsx — typescript executable

Composable utility (stdin → NDJSON):

references/hf_enrich_models.sh — reads model IDs from stdin, fetches metadata per ID, emits one JSON object per line for streaming pipelines.

Composability through piping (shell-friendly JSON output):

references/baseline_hf_api.sh 25 | jq -r '.[].id' | references/hf_enrich_models.sh | jq -s 'sort_by(.downloads) | reverse | .[:10]'
references/baseline_hf_api.sh 50 | jq '[.[] | {id, downloads}] | sort_by(.downloads) | reverse | .[:10]'
printf '%s\n' openai/gpt-oss-120b meta-llama/Meta-Llama-3.1-8B | references/hf_model_card_frontmatter.sh | jq -s 'map({id, license, has_extra_gated_prompt})'

High Level Endpoints

The following are the main API endpoints available at https://huggingface.co

/api/datasets
/api/models
/api/spaces
/api/collections
/api/daily_papers
/api/notifications
/api/settings
/api/whoami-v2
/api/trending
/oauth/userinfo

Accessing the API

The API is documented with the OpenAPI standard at https://huggingface.co/.well-known/openapi.json.

IMPORTANT: DO NOT ATTEMPT to read https://huggingface.co/.well-known/openapi.json directly as it is too large to process.

IMPORTANT Use jq to query and extract relevant parts. For example,

Command to Get All 160 Endpoints

curl -s "https://huggingface.co/.well-known/openapi.json" | jq '.paths | keys | sort'

Model Search Endpoint Details

curl -s "https://huggingface.co/.well-known/openapi.json" | jq '.paths["/api/models"]'

You can also query endpoints to see the shape of the data. When doing so constrain results to low numbers to make them easy to process, yet representative.

Using the HF command line tool

The hf command line tool gives you further access to Hugging Face repository content and infrastructure.

❯ hf --help
Usage: hf [OPTIONS] COMMAND [ARGS]...

  Hugging Face Hub CLI

Options:
  --help                Show this message and exit.

Commands:
  auth                 Manage authentication (login, logout, etc.).
  cache                Manage local cache directory.
  download             Download files from the Hub.
  endpoints            Manage Hugging Face Inference Endpoints.
  env                  Print information about the environment.
  jobs                 Run and manage Jobs on the Hub.
  repo                 Manage repos on the Hub.
  repo-files           Manage files in a repo on the Hub.
  upload               Upload a file or a folder to the Hub.
  upload-large-folder  Upload a large folder to the Hub.
  version              Print information about the hf version.

The hf CLI command has replaced the now deprecated huggingface_hub CLI command.

Weekly Installs

225

Repository

huggingface/skills

GitHub Stars

9.9K

First Seen

Jan 20, 2026

Security Audits

Gen Agent Trust HubPass SocketWarn SnykWarn

Installed on

opencode191

gemini-cli187

codex186

github-copilot175

claude-code173

cursor171

AI Elements：基于shadcn/ui的AI原生应用组件库，快速构建对话界面

60,400 周安装