Catalog
All AI skills
12 skills. Every one is readable here; downloads and live use need a subscription.
azure-ai-vision-imageanalysis-java
Build image analysis applications with Azure AI Vision SDK for Java. Use when implementing image captioning, OCR text extraction, object detection, tagging, or smart cropping.
azure-ai-vision-imageanalysis-py
Azure AI Vision Image Analysis SDK for captions, tags, objects, OCR, people detection, and smart cropping. Use for computer vision and image understanding tasks.
computer-vision-expert
SOTA Computer Vision Expert (2026). Specialized in YOLO26, Segment Anything 3 (SAM 3), Vision Language Models, and real-time spatial analysis.
hugging-face-vision-trainer
Train object detection, image classification, and SAM or SAM2 segmentation models locally or on Hugging Face Jobs, with dataset validation and results saved to the Hub.
auri-core
Auri: assistente de voz inteligente (Alexa + Claude claude-opus-4-20250805). Visao do produto, persona Vitoria Neural, stack AWS, modelo Free/Pro/Business/Enterprise, roadmap 4 fases, GTM, north star WAC e analise competitiva.
brain-to-docs
Interview the user to turn project vision and decisions into README and ADR documentation.
deterministic-design
Render the UI and prove it's balanced + usable: a deterministic layout audit (centroid / optical-center / pixel-oracle balance via explicit math + annotated screenshot) plus a vision-judged Nielsen usability audit by a separate fresh-eyes judge. The measurement layer taste-only design skills lack.
hugging-face-model-trainer
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment.
liuguang-banlan-ui
Builds two parameterized UI modes—流光溢彩白 (iridescent white) and 五彩斑斓黑 (colorful black)—with OKLCH, WebGL/CSS fallback, vision gating, screenshot QA, and total/per-color intensity reports. Use when a UI request names either mode or needs measured color parameters.
lookdev-auto
Automated visual tuning: a vision or video model rates rendered variants in a loop. Render several labeled variants into one artifact, ask the model to rate them and suggest better values, render the suggestions, ask it to pick the best, repeat until good — the model is the eye, you run the loop.
spatial-computing-ui
Web and App implementation guide for Spatial Computing UI. Trigger when user wants floating elements, environmental awareness, and Apple Vision Pro style.
spatial-design
Web and App implementation guide for Spatial Design. Trigger when user wants environment-aware layouts, Apple Vision Pro inspiration, and mixed reality aesthetics.