hugging-face-cli
Execute Hugging Face Hub operations using the hf CLI. Covers authentication, downloading models and datasets, uploading files, repository management, cache operations, cloud compute jobs, inference endpoints, and Hub browsing. Use when the user needs to interact with the Hugging Face Hub from the terminal.
npx skills add majiayu000/claude-skill-registry --skill hugging-face-cli --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Hugging Face CLI Run `hf` commands to download models, upload files, manage repos, control cache, and launch compute jobs on Hugging Face infrastructure. ## Overview The `hf` CLI provides direct terminal access to the Hugging Face Hub. It wraps `huggingface_hub` Python APIs into shell commands for authentication, file transfer, repository lifecycle, cache control, Hub browsing, cloud compute, and inference endpoint management. **What it builds:** - Download commands for models, datasets, and spaces - Upload workflows with commit messages, PRs, and sync patterns - Repository creation, tagging, branching, and settings updates - Cache inspection, cleanup, and verification pipelines - Cloud compute job definitions with GPU/TPU flavor selection - Inference endpoint deployment configurations ## Workflow ### Step 1: Authenticate ```bash # Interactive login hf auth login # Non-interactive (CI/CD) hf auth login --token $HF_TOKEN --add-to-git-credential # Verify identity hf auth whoami ``` Store tokens securely. Use `--add-to-git-credential` for git-lfs operations. The token is saved to `~/.cache/huggingface/token` by default. Override with `HF_TOKEN` environment variable. ### Step 2: Down
- Overview
- Workflow
- Step 1: Authenticate
- Step 2: Download Content
- Step 3: Upload Content
- Step 4: Manage Repositories
- Step 5: Manage Cache
- Step 6: Browse the Hub
- Step 7: Run Cloud Compute Jobs
- Step 8: Deploy Inference Endpoints
- Common Patterns
- CI/CD Model Publishing
- Download for Local Inference
- GPU Training Job with Monitoring
Interactive login hf auth login Non-interactive (CI/CD) hf auth login --token $HF_TOKEN --add-to-git-credential Verify identity hf auth whoami Full repo to cache hf download meta-llama/Llama-3.2-1B-Instruct To local directory hf download meta-llama/Llama-3.2-1B-Instruct --local-dir ./models
What does the hugging-face-cli skill do?
Execute Hugging Face Hub operations using the hf CLI. Covers authentication, downloading models and datasets, uploading files, repository management, cache operations, cloud compute jobs, inference endpoints, and Hub browsing. Use when the user needs to interact with the Hugging Face Hub from the terminal.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill hugging-face-cli --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.