LearningByDoingNow/vision-skill
针对deepseek v4 pro,glm-5.1等纯文本大模型设计的vision技能,skills遵循anthropic设计规范。Vision skills designed for text-only large language models such as DeepSeek V4 Pro and GLM-5.1, with the skills following Anthropic's design specifications.
GitHub repository with 5 stars and 0 forks.
Language: Python