LogoClawIndex
CasesSkillsAbout
LogoClawIndex

hugging-face-evaluation - Manage Hugging Face model evaluations

Add and manage evaluation results in Hugging Face model cards by extracting README tables, importing Artificial Analysis scores, or running custom evaluations.

Tags

Updated: 2026-10-16
hugging-facemodel-evaluationmodel-cardsmodel-indexvllmlightevalinspect-aiartificial-analysis

Capabilities

Check existing pull requestsInspect evaluation tablesExtract README evaluation dataImport Artificial Analysis scores

Typical Inputs

Hugging Face repository IDREADME contentTable selection

Typical Outputs

Generated evaluation YAMLUpdated model card metadataEvaluation scores

What this skill does

  • Check existing pull requests
  • Inspect evaluation tables
  • Extract README evaluation data
  • Import Artificial Analysis scores
  • Generate model-index YAML
  • Merge evaluation metadata
  • Validate model-index metadata
  • Run Hugging Face Jobs evaluations
  • Run GPU model evaluations
  • Create evaluation pull requests

Inputs

  • Hugging Face repository ID
  • README content
  • Table selection
  • Model column hints
  • Model and task identifiers
  • Hugging Face write token
  • Artificial Analysis API key
  • Evaluation hardware
  • GPU model resources

Outputs

  • Generated evaluation YAML
  • Updated model card metadata
  • Evaluation scores
  • Evaluation job
  • Evaluation pull request

Requirements

  • Python environment
  • uv or installed dependencies
  • Hugging Face write access
  • Artificial Analysis API key for imports
  • GPU and sufficient memory for vLLM
  • uv installed for vLLM evaluation
  • Hugging Face Jobs access for remote jobs

Source

  • Spec: SKILL.md

ClawIndex

OpenClaw Skills & Use Case Index

ClawIndex is an ecosystem-driven index of OpenClaw skills and real-world use cases.

Index

Skills·
Cases

Meta

About·
Disclaimer·
Email·
GitHub
© 2026 ClawIndex All Rights Reserved.