vlm-visual-refiner
CommunityVisually calibrate VLM bounding boxes.
Authorghjghjghkimo
Version1.0.0
Installs0
System Documentation
What problem does it solve?
專門用於視覺化與校準 VLM 生成的圖表邊界框 (Bounding Boxes)。當需要將相對座標轉換為標註圖片以供人工驗證或報告生成時使用。
Core Features & Use Cases
- 提供對局部標題文字的辨識與邊界框對齊，降低幻覺標註與裁切風險。
- 支援將邊界框與圖表內容關聯，以產出可追溯的校驗報告與高質量輸出。
Quick Start
Refine VLM chart bounding boxes by feeding an image and output calibrated boxes for validation.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: vlm-visual-refiner Download link: https://github.com/ghjghjghkimo/skills/archive/main.zip#vlm-visual-refiner Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.