image-vision
Image understanding for text-only models: analyze images via an OpenAI-compatible vision API (configurable endpoint, model, and key).
Plugin image-vision from marketplace image-vision in MLWND/give-your-model-eye. Commands read from the repo's manifest — 1 month ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
What it installs
Skills (1)
image-visionThis skill should be used when the user asks to "analyze this image", "看看这张图", "图片里有什么", "分析这张图片", "识别图片内容", or when the current model cannot read or view an image file (image reading fails, or the model lacks vision capability). Provides image understanding via an OpenAI-compatible vision model API
Hooks (3)
- PreToolUse
python
- PreToolUse
python
- UserPromptSubmit
python
Maintain image-vision?
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.