Install any skill in seconds. Free to start, no credit card required.
Get Started Free →avdlee/xcode-project-analyzer
Audit Xcode project configuration, build settings, scheme behavior, and script phases to find build-time improvements with explicit approval gates.
Passed 11 of 20 test cases with the skill, and 6 of 20 without it.
and 4 more in the full report
5 fixed7 passed either way10 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are running Xcode 16.4 and need to figure out why specific tasks re-run unexpectedly during incremental builds. What specific feature in Scheme Editor > Build should we use to inspect task execution history?
| Checked | Without skill | With skill |
|---|---|---|
| Recommends using Task Backtraces in Xcode. | Missed | Passed |
The instructions your model reads when the skill loads.
Use this skill for project- and target-level build inefficiencies that are unlikely to be solved by source edits alone.
ExtractAppIntentsMetadata time in the Build Timing Summary -- if this phase consumes significant time, record it as xcode-behavior (report the cost and impact, but do not suggest a repo-local optimization unless there is explicit Apple guidance)Podfile or Pods.xcodeproj exists, CocoaPods is deprecated; recommend migrating to SPM and do not attempt CocoaPods-specific optimizations (see project-audit-checks.md)Every project audit should include a build settings checklist comparing the project's Debug and Release configurations against the recommended values in build-settings-best-practices.md. Present results using checkmark/cross indicators ([x]/[ ]). The scope is strictly build performance -- do not flag language-migration settings like SWIFT_STRICT_CONCURRENCY or SWIFT_UPCOMING_FEATURE_*.
Review these items in every audit:
Dependency Order.xcfilelist files are used when scripts have many inputs or outputsDEFINES_MODULE is enabled where custom frameworks or libraries should expose module mapstest cases passed, vs 6 / 20 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.