mlx-dev

Description

Write correct, idiomatic Apple MLX code for Apple Silicon ML. Use when working with MLX arrays, neural networks, training loops, lazy evaluation, unified memory, mx.eval, mx.compile, Metal GPU, memory optimization, quantization, or Apple Silicon performance. Covers critical API differences from PyTorch/NumPy, array indexing gotchas (lists must be mx.array, slices create copies), NHWC format for Conv2d, __call__ not forward(), float64 CPU-only, mlx-lm integration, and debugging patterns.

Tool Access

Full access

Inherits all available tools

Supporting Files

10 files

Additional assets for this skill

Tool Access

This skill inherits all available tools. When active, it can use any tool Claude has access to.

Supporting Assets

references/array-indexing.md

references/compilation.md

references/dtypes.md

references/error-decoder.md

references/gradients.md

references/memory-management.md

references/neural-networks.md

references/pytorch-migration.md

references/random.md

scripts/check_memory.py

Links

GitHub Stats

0 forks

Updated 9 days ago

Related Skills

Writing Hookify Rules

46.0K

This skill should be used when the user asks to "create a hookify rule", "write a hook rule", "configure hookify", "add a hookify rule", or needs guidance on hookify rule syntax and patterns.

From hookify

frontend-design

46.0K

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, or applications. Generates creative, polished code that avoids generic AI aesthetics.

From frontend-design

claude-opus-4-5-migration

46.0K

Migrate prompts and code from Claude Sonnet 4.0, Sonnet 4.5, or Opus 4.1 to Opus 4.5. Use when the user wants to update their codebase, prompts, or API calls to use Opus 4.5. Handles model string updates and prompt adjustments for known Opus 4.5 behavioral differences. Does NOT migrate Haiku 4.5.

From claude-opus-4-5-migration