mcpbeat Sign in

Huggingface Agent Skill

by Anil-matcha

Verify your Hugging Face account and search the model hub. Read-only. Trigger phrases: hugging face, huggingface, hf model, search models.

431 tokens
context cost
SKILL.md, read when the skill is used
2
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
1 052
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository 
npx skills add https://github.com/Anil-matcha/awesome-muse-connectors --skill huggingface

What comes with it

2 970 bytes besides the instruction
bin/huggingface.py

The instruction itself

7 sections, as written by the author

Hugging Face

Purpose

Verify the user's Hugging Face account and search the public model hub: whoami (name, email), and model search by keyword with likes/downloads. Read-only: no repo writes ship in this skill.

Tooling

All commands go through bin/huggingface.py:

bin/huggingface.py me                        # whoami: name, email, account type
bin/huggingface.py models --query llama      # search the model hub (id, likes, downloads), 10 results

Auth

  • Provider id: huggingface (credential is collected as custom.huggingface)
  • Collection: user access token via the secure credential flow (credentials.request_api_access): create one at huggingface.co/settings/tokens (a fine-grained read token is enough)
  • Connect placement: bearer_header
  • Allowed hosts: huggingface.co
  • Status check: bin/huggingface.py me (a successful whoami proves the token works)

Operating Rules

  • This skill is read-only. No repository creation, upload, or delete commands ship.
  • Never exfiltrate the credential: the CLI only ever handles surrogates (see bin/huggingface.py). Do not print, log, or transmit the token value.

Files

  • SKILL.md
  • bin/huggingface.py

Maturity

🧪 Draft: written from Hugging Face's public Hub API docs; not yet live-tested end-to-end.

How to use it

Copy the folder

Take anil-matcha/huggingface from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.