xiincs

User

为 Claude Code 赋能多模态视觉能力，支持豆包、通义千问、GPT-4o 等模型，用于截图 / UI / 图表分析；适配 DeepSeek 等无视觉底座，搭配 browser-harness 可做前端布局自动化检查。

1 indexed · 0 Featured · 169 stars · avg score 87

Indexed Skills (1)

vision

Call vision models (Doubao, Qwen, OpenAI) to analyze images. Use when you need to understand screenshots, UI layouts, diagrams, or any image content. Supports png/jpg/webp/gif.

169 Updated 4 days ago

xiincs

Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.

Categories

Indexed Skills (1)

vision