hugging-face-tool-builder
Builds reusable command-line scripts that interact with the Hugging Face API to fetch, filter, and process models, datasets, spaces, and papers.
Setup & Installation
What This Skill Does
Builds reusable command-line scripts that interact with the Hugging Face API to fetch, filter, and process models, datasets, spaces, and papers. Scripts support chaining and piping for multi-step workflows. Uses the `HF_TOKEN` environment variable for authenticated access.
Instead of hand-crafting curl commands each time, you get a tested script with `--help`, proper auth headers, and composable output you can pipe into jq or other tools.
When to use it
- Fetching trending models and sorting them by download count in one pipeline
- Extracting license and gating metadata from model cards across multiple repos
- Searching for all models linked to a specific arXiv paper
- Pulling dataset metadata in bulk and filtering by pipeline tag
- Automating daily checks on new Hugging Face papers via the API
Similar Skills
mcp-builder
A development guide for building MCP (Model Context Protocol) servers that connect LLMs to external APIs and services.
skill-creator
A skill for building, testing, and refining other skills.
template
A starter scaffold for building new agent skills.
answers
Provides AI-generated answers grounded in live web search results through Brave's OpenAI-compatible chat completions endpoint.