Экспертный скилл по прикладной инженерии VLM, сегментационных моделей и диффузионных архитектур для GPU-деплоя. Используй ВСЕГДА когда речь идёт о: SAM2, SAM3, Florence-2, LLaVA, Grounding DINO, OWLv2, YOLO-World, EdgeTAM — выбор модели, интеграция, pipeline, код; диффузионных моделях — UNet/DiT/Flow/Flux, schedulers, LoRA, AMP, ZeRO/FSDP, text encoders (CLIP/Qwen), VAE, CFG; GPU-деплое — MIG, MPS, torch.compile, TorchAO, Triton, memory optimization, два инстанса на H100; open-vocab сегментации и phrase grounding; part-level labeling и instance masks из текстового промпта; замене/fusion текст-энкодеров; fine-tune/LoRA/DreamBooth диффузионных моделей. Триггеры: SAM, Florence, LLaVA, Grounding DINO, YOLO-World, diffusion, UNet, DiT, Flux, LoRA, scheduler, guidance_scale, VAE, CLIP embeddings, Qwen embedder, MIG, MPS, TorchAO, Triton inference, сегментация по тексту, instance masks, open-vocab detection, text-conditioned segmentation. Do NOT use for pure diffusion-only work without a VLM/segmentation component — general diffusion architecture/inference -> diffusion-engineering, FLUX.2 Klein prompting -> flux2-klein-prompting, FLUX.2 Klein / Qwen-Edit LoRA training -> flux2-lora-training.
$npx -y skills add anastasiyaw/claude-code-config --skill vlm-segmentationInstalls into the current project.
Run `npx skills use "https://github.com/anastasiyaw/claude-code-config" --skill "anastasiyaw/claude-code-config/vlm-segmentation"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/anastasiyaw/claude-code-config" that are relevant to the current task. Run `npx skills add "https://github.com/anastasiyaw/claude-code-config"` and select the relevant skills, then follow their instructions.