autoglm-image-recognition

What problem does it solve?

It helps you recognize and describe image contents without manually interpreting what’s in a picture, turning an input image into a readable description.

Core Features & Use Cases

• Image understanding: Generates descriptive text for what’s in an image (objects, scenes, and possibly text).
• Flexible input: Supports using either a public image URL directly or a local image file that is first uploaded to obtain a public URL.
• Custom prompting: Allows an optional prompt to guide recognition (e.g., “识别图中文字” vs default “描述图片”).

Quick Start

Provide a public image URL (http/https) and ask the agent to generate an image description using the autoglm-image-recognition skill with the default prompt.