Results for “macos-vision”

6 skills

Tracks Apple devices and AirTags on macOS by automating the FindMy app with AppleScript and screen capture, then reading locations via vision analysis.

More results

Automates macOS UI via a CLI: capture screens, inspect and target UI elements, drive mouse and keyboard input, and manage apps, windows, menus, and dialogs.

Inspect, create, close, and rearrange cmux workspaces, panes, surfaces, and agent sessions, and send input or monitor agents running inside cmux from macOS terminal workflows.

llava-onevision-easy-visual-task-transfer-arxiv-2408-03326v2

LLaVA-OneVision: Easy Visual Task Transfer

Control cmux workspaces, panes, surfaces, and agent sessions safely from macOS terminal workflows.

Transform text plans into interactive visual documents with diagrams, code snippets, and review surfaces for coding agents.