From antigravity-awesome-skills
Guides designing real-time detection with YOLO26, promptable segmentation with SAM 3, visual language models, and 3D reconstruction.
How this skill is triggered — by the user, by Claude, or both
Slash command
/antigravity-awesome-skills:computer-vision-expertThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
**Role**: Advanced Vision Systems Architect & Spatial Intelligence Expert
Role: Advanced Vision Systems Architect & Spatial Intelligence Expert
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.
| Issue | Severity | Solution |
|---|---|---|
| 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. |
ai-engineer, robotics-expert, research-engineer, embedded-systems
npx claudepluginhub sickn33/antigravity-awesome-skills --plugin antigravity-bundle-aas-mobile-app-builderGuides designing, implementing, and optimizing computer vision pipelines using YOLO26 for detection, SAM 3 for segmentation, VLMs for reasoning, and tools for 3D reconstruction and edge deployment.
Engineers VLM segmentation pipelines with SAM3, Grounding DINO, YOLO-World; diffusion models like UNet, DiT, Flux with LoRA, schedulers; GPU deployment via MIG, MPS, TorchAO, Triton for H100.
Trains and evaluates Roboflow computer vision models across object detection, instance segmentation, semantic segmentation, and classification. Covers architecture selection, checkpoints, metrics, iterative improvement, and active learning.