computer-vision-expert

SKILL.md

Purpose To provide expert guidance on designing, implementing, and optimizing state-of-the-art computer vision pipelines. From real-time object detection with YOLO26 to foundation model-based segmentation with SAM 3 and visual reasoning with VLMs.

| SAM 3 VRAM Usage | Medium | Use quantized/distilled versions for local GPU inference. | | Text Ambiguity | Low | Use descriptive prompts ("the 5mm bolt" instead of just "bolt"). | | Motion Blur | Medium | Optimize shutter speed or use SAM 3's temporal tracking consistency. |

| Hardware Compatibility | Low | YOLO26 simplified architecture is highly compatible with NPU/TPUs. |

Expert en vision par ordinateur SOTA (2026). Spécialisé dans YOLO26, Segment Anything 3 (SAM 3), Vision Language Models et analyse spatiale en temps réel. Source : sickn33/antigravity-awesome-skills.

Voir l'original