Skip to main content

Huggingface Best

Plugin Active

Find the best AI model for any task by querying Hugging Face leaderboards and benchmarks. Recommends top models based on task type, hardware constraints, and benchmark scores.

Purpose

To help users find the most suitable AI model for their specific tasks and hardware limitations by leveraging Hugging Face's benchmark data.

Features

  • Query Hugging Face leaderboards and benchmarks
  • Recommend top models based on task type
  • Filter models by hardware constraints (e.g., device memory)
  • Enrich model data with parameter count and license information
  • Present model comparisons in a tabular format

Use Cases

  • When seeking the best AI model for a specific task like coding or text generation.
  • When comparing different AI models based on benchmark scores and size.
  • When unsure which AI model can run on available hardware.
  • When needing to quickly identify state-of-the-art models for a given use case.

Non-Goals

  • Training or fine-tuning AI models.
  • Running AI models directly.
  • Providing an exhaustive list of all available models.
  • Evaluating models not present on official Hugging Face leaderboards.

Security

  • warning:Secret ManagementThe skill script references `~/.cache/huggingface/token` and `$(cat ~/.cache/huggingface/token)` for API access, suggesting it might expose or handle user tokens without clear indication of secure handling.
  • info:Data ExfiltrationThe skill reads a Hugging Face token from a local file for API authentication, which is a common practice but should ideally be handled more securely.
  • warning:Keychain-stored secretsThe skill references a Hugging Face token from `~/.cache/huggingface/token`, which is likely stored in plain text and not routed through secure keychain storage.

Code Execution

  • warning:ValidationThe skill parses user input for task and device, but it does not appear to use a schema validation library for input sanitization or parameter validation.
  • warning:Error HandlingThe skill includes basic error handling for API calls (e.g., 'leaderboard not found'), but it lacks structured error reporting with retryable flags or hints for the agent.

Errors

  • warning:Actionable error messagesError messages for API call failures are present but lack specific remediation steps or links to documentation, making them less actionable for the agent.

Installation

First, add the marketplace

/plugin marketplace add huggingface/skills
/plugin install huggingface-best@huggingface-skills

Quality Score

79 /100
Analyzed about 14 hours ago

Trust Signals

Last commit1 day ago
Stars10.5k
LicenseApache-2.0
Status
View Source

© 2025 SkillRepo · Find the right skill, skip the noise.