Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From science-skill
Analyzes images to describe content, extract data from scientific figures, plots, experimental setups, and answer general questions.
npx claudepluginhub caidish/cai-tools --plugin science-skillHow this skill is triggered — by the user, by Claude, or both
Slash command
/science-skill:visionThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Analyze an image with an image expert.
Analyzes images with MiniMax vision tool for description, OCR, text extraction, UI mockup review, chart data parsing, diagrams. Auto-triggers on image shares or analysis requests.
Extracts numerical data from scientific figure images using Claude vision and OpenCV calibration. Supports 26+ plot types and outputs CSV/JSON for meta-analyses.
Analyzes media files (PDFs, images, diagrams, screenshots) using a vision backend to extract structured data, descriptions, or summaries instead of literal file reading.
Share bugs, ideas, or general feedback.
Analyze an image with an image expert.
Run the script with an image path and a prompt:
python scripts/vision.py <image_path> "<prompt>"
# Describe a plot
python scripts/vision.py spectrum.png "Identify the emission lines in this spectrum"
# Read values from a figure
python scripts/vision.py graph.png "What is the peak wavelength shown in this plot?"