hugging-face-jobs

Train language models using TRL (Transformer Reinforcement Learning) on fully managed Hugging Face infrastructure. No local GPU setup required—models train on cloud GPUs and results are automatically saved to the Hugging Face Hub.

This skill provides tools to manage datasets on the Hugging Face Hub with a focus on creation, configuration, content management, and SQL-based data manipulation. It is designed to complement the existing Hugging Face MCP server by providing dataset editing and querying capabilities.

The hf CLI provides direct terminal access to the Hugging Face Hub for downloading, uploading, and managing repositories, cache, and compute resources.

This skill provides tools to add structured evaluation results to Hugging Face model cards. It supports multiple methods for adding evaluation data:

Source details, install context, and public review data are available on the full page.

Analyzes and optimizes Flutter application size by measuring build artifacts, generating size analysis reports, utilizing Dart DevTools for component breakdown, and implementing specific size reduction strategies such as debug info splitting, resource compression, and platform-specific tree-shaking. Assumes a...

Evaluates whether APIs, configurations, and interfaces are resistant to developer misuse. Identifies designs where the "easy path" leads to insecurity.

Solves the "context problem" in multi-agent workflows where subagents don't know what context they need until they start working.