Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIDeepSeekDeepSeekMuseMuse+22 more

    Hf Model Registry

    1

    Search, download, upload, and manage models, datasets, and Spaces on the Hugging Face Hub with the hf CLI. Use when a model or dataset must be fetched for a job

    Free

    3 usesSecurity scanned
    Hf Model Registry

    Hf Model Registry

    Example session with this skill installed

    Search for a Qwen 2.5 0.5B model, download it to my cache using the v1.0 tag, and show me the repository info to verify the file list.

    • Read your context and instructions
    • Compiled the hf model registry

    I've searched and located 'Qwen/Qwen2.5-0.5B'.

    1. Downloaded revision 'v1.0' successfully.
    2. Verified repository info:
    • Files: model.safetensors, config.json, tokenizer.json
    • Size: ~950MB
    • Commit: a1b2c3d
      Weights are ready in the hub cache.
    model.safetensors, config.json, tokenizer.json

    Connects securely to your tools. The creator never sees your data.

    About this skill

    The problem

    Manually managing large machine learning artifacts via browser or git is slow and prone to corruption. Developers struggle with interrupted downloads, disk space management, and inconsistent metadata when publishing models.

    What it does

    • Authenticates and manages identity across Hugging Face organizations.
    • Searches the Hub for specific model weights, datasets, and Spaces.
    • Downloads large checkpoints with built-in resumability and revision pinning.
    • Queries dataset schemas and previews data using SQL over Parquet files.
    • Uploads trained artifacts with automated repository creation and tagging.

    Frameworks & tools

    Hugging Face CLI (hf), PyTorch, TensorFlow, Transformers, Datasets, and Parquet.

    Why this beats prompting it yourself

    This skill handles the nuances of the new 'hf' CLI syntax, replacing legacy commands. It ensures you use optimized transfer methods like resumable large-folder uploads rather than basic git clones which fail on large binary files.

    Use cases

    • Fetch specific model revisions for reproducible training pipelines.
    • Preview dataset rows via SQL to verify data quality before downloading gigabytes.
    • Automate the publication of fine-tuned LoRA adapters with proper README cards.
    • Clean up local Hub caches to recover disk space on compute instances.

    Known limitations

    Requires the new Hugging Face CLI (hf) to be installed; not intended for in-training data streaming.

    Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse All Claude Skills.

    Requires the hf CLI tool installed via curl. Not for real-time data streaming during training loops. Not recommended for tiny files where git clone is faster.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before buying a skill.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    3 uses

    Times used to date

    Free to use

    No account required to browse

    Trust & safety

    Security scan

    Security scan passed 3 months ago

    • Free with an Agensi account

    Accounts
    Hf

    Permissions

    Terminal / Shell
    Network Access

    Allowed Hosts

    hf.co
    Listed3 months ago

    What's inside

    Frequently Asked Questions

    This skill automates the discovery, retrieval, and management of assets on the Hugging Face Hub, solving common issues like interrupted downloads of large weights and the complexity of managing local disk caches via the CLI.

    The skill is designed for use with any AI agent or automation pipeline that has access to a terminal environment where the Hugging Face Hub library and CLI are installed.

    Yes, this skill provides specialized commands for querying dataset schemas and previewing specific rows using SQL over Parquet files, allowing you to verify data quality before committing to a full download.

    Unlike basic Git-based methods, this skill utilizes optimized transfer protocols via the 'hf' CLI, supporting resumable uploads for large checkpoints and automated repository tagging for better MLOps organization.

    The skill focuses on the new 'hf' CLI syntax, ensuring your workflows remain current with Hugging Face's latest standards and avoiding deprecated legacy commands.

    Free