Agent Skills: multimodal-clip

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

ID: davila7/claude-code-templates/multimodal-clip

Install this agent skill to your local

npx skills add davila7/claude-code-templates --skill multimodal-clip

Skill Files

The files that make up multimodal-clip.

Download Skill

More agent skills