LoserFox/marisa-distro--plugins-modlens ↗★ 7
@liustack/modlens
Plug-in vision for text-only LLMs, powered by the free Antigravity CLI
AI Analysis
核心用途是为不支持多模态的文本模型补充视觉理解能力。适合需要向模型发送图片、截图并基于图像内容进行问答的场景。
Install
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:LoserFox/marisa-distro#4aa96256d0af09fa65e64679a1c7826342e9ded2&path:plugins/modlensREADME
Read the full README ↗Usage
Once installed, just chat. Paste an image or drop a path, ask anything, and the skill triggers on its own: the image goes to a vision engine and the answer comes back grounded in what it read. Paste once, and later questions about the same image do not need another paste.