mcpbeat

Vision Support

walkerkiller/vision-support

为非多模态模型(如 deepseek-v4-pro、GLM-5.1、mimo-v2.5-pro 等纯文本模型)提供图片识别能力。当主模型无法识别图片、用户发送了截图/设计稿/UI 截图需要分析、或者用户说'看看这张图'、'分析这个截图'、'这张图片有什么问题'时,自动触发此技能。也适用于用户粘贴了图片但当前模型不支持图片输入的任何场景。支持同时识别多张图片,通过配置多个识图模型实现主备回退。使用指令 /skill:vision-support 或 /vision 也可手动触发。铁律:本技能配置的模型仅用于图片内容识别,绝不参与主逻辑推理。注意:如果当前模型本身是多模态模型(如 Claude Sonnet 4、GPT-4o、Gemini 等可以直接识图的模型),不要使用此技能,直接让主模型识别即可。

100k tokens
context cost
the whole folder, loaded on every use
18
files
ships runnable scripts
0
copies elsewhere
how many repositories repackaged it
38
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/WALKERKILLER/Look-Tongji-Notes --skill vision-support

How to use it

Copy the folder

Take walkerkiller/vision-support 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.