Menu
Route Python-first MLX optimization work on Apple Silicon to focused audit, training, inference, Metal, or bridge workflows.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
| name | mlx-optimizer |
| description | Route Python-first MLX optimization work on Apple Silicon to focused audit, training, inference, Metal, or bridge workflows. |
Use this skill when the user asks Codex to optimize, audit, benchmark, profile, or explain MLX code on Apple Silicon.
.venv before any Python execution.../mlx-performance-audit/SKILL.md.../mlx-training-optimizer/SKILL.md.../mlx-inference-optimizer/SKILL.md.../mlx-metal-kernels/SKILL.md.../mlx-portability-bridges/SKILL.md.Read only the files needed for the routed task:
../../references/mlx-core-concepts.md../../references/eval-and-synchronization.md../../references/compile-and-transforms.md../../references/memory-and-dtypes.md../../references/reporting-format.mdOptimize Python MLX inference and generation loops with warmup, batching, cache handling, synchronization, quantization, and memory checks.
Guide MLX Metal profiling, mx.fast escalation, custom Metal kernels, and C++ extensions when profiling proves kernel-level bottlenecks.
Audit Python MLX repos for lazy-eval, synchronization, compile, dtype, memory, progress, and benchmark issues.
Advise on Python-first MLX integration with Swift, C, C++, and non-native language boundaries.
Optimize Python MLX training loops with value_and_grad, accumulation, checkpointing, dtype, validation cadence, memory telemetry, and progress reporting.