Searching protocol for "visual-context"
See web pages clearly with screenshots and a11y.
Capture Slidev screenshots for visual context.
Share and read screenshots with Claude Code.
Transcribe audio & video to Markdown.
Enhance transcripts with visual context, automatically.
Capture context-driven screenshots automatically.
Analyze videos with Gemini API.
Extract and analyze PDFs with AI-powered markdown output.
Analyze images with AI chat.
VLA patterns for cognitive robotics.
Analyze videos with Gemini AI — summarize, transcribe, and answer questions.
Capture and save test screenshots automatically.