Stats
Actions
Tags
From mlx-optimizer
Audit Python MLX repos for lazy-eval, synchronization, compile, dtype, memory, progress, and benchmark issues.
How this skill is triggered — by the user, by Claude, or both
Slash command
/mlx-optimizer:mlx-performance-auditThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Use this skill for repo-wide MLX performance reviews and unknown bottlenecks.
Use this skill for repo-wide MLX performance reviews and unknown bottlenecks.
Before any Python execution, use the target repo's .venv. Never install
Python packages globally.
../../references/mlx-core-concepts.md../../references/eval-and-synchronization.md../../references/compile-and-transforms.md../../references/memory-and-dtypes.md../../references/reporting-format.mdgit --no-pager status --short.../../scripts/mlx_audit.py from this plugin repo when
the target repo is local and scanning is useful.Use ../../templates/optimization-report.md as the report structure. Every
finding needs file, line, evidence, candidate impact, confidence, verification,
and residual risk.
npx 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.