
Raycast extension for Cachy
Read My Screen
by erbilnas
AI screenshot and browser reader: OCR, explain errors, summarize pages, and review UI with GPT-4o, Claude, or Gemini. Use region, window, or full-screen capture; clipboard images; local files; or the active browser tab. Bring your own API keys — requests go straight to OpenAI, Anthropic, or Google.
Commands
5Read My Screen
ViewMain command: capture your screen (region, window, full screen, or clipboard image) or read the current browser tab as text. Vision and text models; follow-up chat; session history.
Quick: Clipboard Image
ViewOne shortcut: analyze the image on your clipboard with your default model — shows the response immediately.
Quick: Browser Page
BackgroundOne shortcut: summarize or question the active browser tab (Chrome, Safari, Arc, Dia, Edge, and more) using page text.
Analyze Image File
ViewOpen a PNG, JPEG, WebP, or GIF from disk; analyze with AI and continue the conversation in chat.
Session History
ViewReopen saved analyses (with screen thumbnails), continue chats, and manage past sessions.