Agent Skills: multimodal-llm

Vision, audio, video generation, and multimodal LLM integration patterns. Use when processing images, transcribing audio, generating speech, generating AI video (Kling v3, Sora 2, Veo 3.1 std/lite/fast, Runway Gen-4.5 via `gen4_turbo`), or building multimodal AI pipelines.

mcp-enhancementID: yonatangross/orchestkit/multimodal-llm

Author

yonatangross

https://github.com/yonatangross View all skills

Repository

yonatangross/orchestkit

yonatangrossLicense: MIT

28134

Install this agent skill to your local

pnpm dlx add-skill https://github.com/yonatangross/orchestkit/multimodal-llm

Skill Files

Browse the full folder contents for multimodal-llm.

Download Skill

Loading file tree…

Select a file to preview its contents.