mm-cli-skill
>
vlmrun-cli-skill
Use the VLM Run CLI (`vlmrun`) to interact with Orion visual AI agent. Process images, videos, and documents with natural language. Triggers: image understanding/generation, object detection, OCR, video summarization, document extraction, image generation, visual AI chat, 'generate an image/video', 'analyze this image/video', 'extract text from', 'summarize this video', 'process this PDF'.
vlmrun-gw
Use the `vlmrun` Python SDK and CLI. The `vlmrun gw` CLI parses documents and runs chat completions over text, images and video on the VLM Run gateway (gateway.vlm.run), plus multimodal embeddings and audio transcription. The same gateway calls work from Python through the OpenAI SDK or `VLMRun().gateway`. The `VLMRun` client and `vlmrun generate` / `vlmrun execute` cover the platform API — schema-typed predictions, agent executions, files and hub domains. Covers every command and flag, model selection, methods, request knobs, response shapes, cost and errors. Use when asked to read/parse/OCR a PDF, scan, receipt or form, convert a document to markdown, extract text with bounding boxes, get a document's layout or tables, describe or answer questions about an image or video, embed images or text for search, transcribe speech, extract structured JSON from a document, or run and poll an agent execution.