deepseek-eyes
by 20kiki
Use when the user shares an image (screenshot, photo, diagram) that Claude can't natively see, or when the user asks to analyze/describe/understand an image. Route every image the user wants analyzed through this skill — send the image path to the bundled eyes.py script, which calls a vision model (default: qwen3.6-plus) via 百炼 (DashScope) and returns a Chinese text description. Then answer the user's question based on that description.