Deepseek Vision Bridge

aiskillstore/deepseek-vision-bridge

>- Deploy and maintain image understanding (OCR + local VLM + cloud VL) and image generation for Codex connected to text-only models like DeepSeek. Use when the user wants to see/read images in the conversation bar with a text-only model, set up automatic OCR or vision-model processing for pasted images, configure image generation via SiliconFlow or local Stable Diffusion/Flux, fix a broken vision proxy, or asks "看图/生图/贴图识别/图片理解/OCR代理" on a Codex+DeepSeek setup. Deploys a local proxy between Codex and the model that converts images to text before forwarding.

96k tokens

context cost

the whole folder, loaded on every use

files

ships runnable scripts

copies elsewhere

how many repositories repackaged it

404

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/aiskillstore/marketplace --skill deepseek-vision-bridge

How to use it

Copy the folder

Take aiskillstore/deepseek-vision-bridge from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.

Install what it needs

The instructions reference npm. Without those the skill loads but fails at the first command.