vl-vision-skill
当用户询问看到什么、能看到什么、需要观察周围环境/图像分析时触发,通过摄像头实时拍摄并使用Ollama qwen3.5:9b模型进行视觉分析
Source facts
- Repository
- vanstrong12138/OpenClawPi
- Last source activity
- March 12, 2026 at 03:08
- Detected SKILL.md language
- Chinese
- Stars
- 60
- Forks
- 8
Install options
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Review the source files
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Showing SKILL.md
- name
- vl_vision_skill
- description
- 当用户询问看到什么、能看到什么、需要观察周围环境/图像分析时触发,通过摄像头实时拍摄并使用Ollama qwen3.5:9b模型进行视觉分析