From mlx-optimizer
Optimize Python MLX inference and generation loops with warmup, batching, cache handling, synchronization, quantization, and memory checks.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mlx-optimizer:mlx-inference-optimizerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill for MLX inference, generation, serving loops, batch scoring,
Use this skill for MLX inference, generation, serving loops, batch scoring, streaming output, or latency/throughput questions.
Before any Python execution, use the target repo's .venv. Never install
Python packages globally.
../../references/inference-patterns.md../../references/eval-and-synchronization.md../../references/memory-and-dtypes.mdnpx claudepluginhub sealad886/mlx-optimizer-plugin --plugin mlx-optimizerCreates, edits, and optimizes skills for Claude Code, including drafting, evaluating with test prompts, iterating on performance, and improving skill descriptions for better triggering accuracy.