cv-classification
Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks.
Works with
Claude CodeCursorCodex CLIGitHub CopilotGemini CLI
Agent Skills format with YAML frontmatter. Claude Code reads it as-is.
--- name: "cv-classification" description: "Best practices for image classification tasks. Use when working on CIFAR, ImageNet, or other classification benchmarks." license: "MIT" --- ## Image Classification Best Practice Architecture selection: - Small scale (CIFAR-10/100): ResNet-18/34, WideResNet, Simple ViT - Medium scale: ResNet-50, EfficientNet-B0/B1, DeiT-Small - Large scale: ViT-B/16, ConvNeXt, Swin Transformer Training recipe: - Optimizer: AdamW (lr=1e-3 to 3e-4) or SGD (lr=0.1 with cosine decay) - Weight decay: 0.01-0.1 for AdamW, 5e-4 for SGD - Data augmentation: RandomCrop, RandomHorizontalFlip, Cutout/CutMix - Warmup: 5-10 epochs linear warmup for transformers - Batch size: 128-256 for CNNs, 512-1024 for ViTs (if memory allows) Standard benchmarks: - CIFAR-10: ~96% (ResNet-18), ~97% (WideResNet) - CIFAR-100: ~80% (ResNet-18), ~84% (WideResNet) - ImageNet: ~76% (ResNet-50), ~81% (ViT-B/16)
More General & Other skills
find-skills
vercel-labs/skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
1.5M
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
972.7k
grill-with-docs
mattpocock/skills
A relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.
828.8k
