apple-silicon

Solid

Use when tuning or profiling native code on Apple M-series Macs: unified memory, 16 KiB pages, Accelerate and Metal for matrix work, xctrace and leaks, Rosetta 2, or sysctl hardware queries.

AI & Automation 52 stars 9 forks Updated 5 days ago Apache-2.0

Install

View on GitHub

Quality Score: 83/100

Stars 20%
57
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Apple Silicon ## Contract | Field | Bound contract | |---|---| | Trigger | Code runs on an M-series Mac and needs to be checked for page-size assumptions, moved onto Accelerate or Metal for matrix work, profiled with Instruments or the command-line memory tools, or diagnosed for Rosetta 2 translation. | | Authority | Read-only: reads the host through `sysctl`, `arch`, `lipo`, `file`, `xctrace`, `vmmap`, `heap`, `leaks`, and `sample`, and writes traces only under the output path the user names; rollback is deleting those trace files. No remote mutation. | | Side effect | Trace and sample files in the named output directory. Profiling attaches to the target process. | | Done | The report names the chip and its features from `sysctl`, states whether the binary runs native or translated, lists every page-size assumption found in the code with its fix, and points each hotspot at the Accelerate, Metal, or threading change that addresses it. | ## Inputs - The binary or source under review, and how it is launched. - Whether the workload is matrix or convolution heavy (Accelerate and Metal candidates) or general CPU work. - Output directory for traces. - Xcode command-line tools installed (`xcode-select -p` prints the path). ## Procedure 1. Read the hardware. All CPU cores, the GPU, and the Neural Engine share one DRAM pool, so a Metal buffer in shared storage mode needs no copy to reach the GPU, and one process's memory total includes its GPU allocations. Done when: chip name...

Details

Author
OutlineDriven
Repository
OutlineDriven/outline-driven-development
Created
9 months ago
Last Updated
5 days ago
Language
Python
License
Apache-2.0

Similar Skills

Semantically similar based on skill content — not just same category

Testing & QA Listed

macos-trace

Autonomous closed-loop performance optimization engine for macOS applications using xctrace and Xcode Instruments. Handles the full lifecycle: aligning optimization targets with the user, headless diagnostic trace capture, isolating hotspots, implementing code fixes, re-testing with differential A/B verification, and iterating until performance goals are met without manual GUI intervention. Use when the user reports high CPU usage, memory growth or leaks, UI stutter or dropped frames, slow cold launch, audio dropouts, or thermal issues in a macOS application, and asks to profile, benchmark, or optimize it.

1 Updated 3 days ago
kmgcc
AI & Automation Listed

ios-performance-engineering

Measure and fix iOS/macOS performance with Instruments (Time Profiler, Allocations, Hangs, App Launch), `xctrace` in CI, `OSSignposter`, MetricKit field telemetry (`MXMetricManager`, `MXHangDiagnostic`), `XCTMetric` baselines, launch time, memory footprint, and binary size. Use when diagnosing hangs, hitches, high memory, slow launch, or a large binary, wiring MetricKit, or setting CI perf baselines. SwiftUI body re-render analysis from code review → apple-skills:guide-swiftui-performance-audit or swiftui-expert's `.trace` toolchain; this skill owns measurement and the system-level surface.

19 Updated today
wei18
AI & Automation Listed

native-app-profiling

Profile native macOS/iOS apps for CPU hotspots, hangs, and hitches using Instruments traces. Use when asked to identify performance hotspots, profile CPU usage, or diagnose slow code paths without opening Instruments.

3 Updated today
patrickserrano