agentmods.dev

mathruffian-dot/image-vision-sidecar

讓純文字模型（DeepSeek/GLM）間接讀圖的免費 Vision Sidecar：Groq API 把 PDF/PPTX/DOCX/圖片轉成繁中 Markdown

Open on GitHub

12Stars on the repository

1Mods indexed here, across every type

1mo agoLast push, which is what freshness is scored on

Sort Relevance Recently updated Fewest tokens Security grade Repo stars Stars this week Top rated 1 mods

image-vision-sidecar

mathruffian-dot/image-vision-sidecar

Skill Claude CodeCodex

A sidecar skill that lets text-only models work from images and office documents through Groq's vision service. It converts PNG, JPG, PDF, PPTX, and DOCX files into Traditional Chinese Markdown descriptions, including extracted text.

not rated 12 1mo ago A 161 tokens