Claude Marketplaces
SkillsMCP serversMarketplacesDigestTools
Submit

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP servers by category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control
Claude Marketplaces

An independent directory of skills, plugins and MCP servers for Claude Code. Not affiliated with Anthropic.

Browse

  • Skills
  • MCP servers
  • Marketplaces
  • Weekly digest
  • Skill index
  • MCP index
  • Marketplace index

Site

  • About
  • Tools
  • Submit
  • Feedback
  • Privacy
  • llms.txt
  • Plugins reference

Maker

  • Snug
  • Agent Caffeine
  • knobs
  • Wax
  • Vectoys
  • mertduzgun.com
Crafted at
Skills/DevOps & CI/CD
avdlee avatar

Xcode Project Analyzer

avdlee/xcode-build-optimization-agent-skill

Point this at your Xcode project when incremental builds feel slower than they should or you suspect build settings are fighting you. It audits scheme configuration, target dependencies, run script phases, and build settings against Apple's recommendations, then gives you measured findings with explicit approval gates before touching anything. The checklist approach is thorough, covering everything from debug versus release config mismatches to script phases that invalidate derived data. Honest take: if you've never compared your build settings to best practices or don't know whether your scripts declare inputs and outputs, this will find low-hanging fruit fast.

installs
3.5K
GitHub stars
1.3K
last updated
Aug 21, 2026
View on GitHubSave

Install

$ npx -y skills add avdlee/xcode-build-optimization-agent-skill --skill xcode-project-analyzer --agent claude-code

Installs into .claude/skills of the current project.

Files

Xcode Project Analyzer

Use this skill for project- and target-level build inefficiencies that are unlikely to be solved by source edits alone.

Core Rules

  • Recommendation-first by default.
  • Require explicit approval before changing project files, schemes, or build settings.
  • Prefer measured findings tied to timing summaries, build logs, or project configuration evidence.
  • Distinguish debug-only pain from release-only pain.

What To Review

  • scheme build order and target dependencies
  • debug vs release build settings against the build settings best practices
  • run script phases and dependency-analysis settings
  • derived-data churn or obviously invalidating custom steps
  • opportunities for parallelization
  • explicit module dependency settings and module-map readiness
  • "Planning Swift module" time in the Build Timing Summary -- if it dominates incremental builds, suspect unexpected input modification or macro-related invalidation
  • asset catalog compilation time, especially in targets with large or numerous catalogs
  • 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)
  • zero-change build overhead -- if a no-op rebuild exceeds a few seconds, investigate fixed-cost phases (script execution, codesign, validation, CopySwiftLibs)
  • CocoaPods usage -- if a Podfile or Pods.xcodeproj exists, CocoaPods is deprecated; recommend migrating to SPM and do not attempt CocoaPods-specific optimizations (see project-audit-checks.md)
  • Task Backtraces (Xcode 16.4+: Scheme Editor > Build > Build Debugging) to diagnose why tasks re-run unexpectedly in incremental builds

Build Settings Best Practices Audit

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_*.

Apple-Derived Checks

Review these items in every audit:

  • target dependencies are accurate and not missing or inflated
  • schemes build in Dependency Order
  • run scripts declare inputs and outputs
  • .xcfilelist files are used when scripts have many inputs or outputs
  • DEFINES_MODULE is enabled where custom frameworks or libraries should expose module maps
  • headers are self-contained enough for module-map use
  • explicit module dependency settings are consistent for targets that should share modules

Typical Wins

  • skip debug-time scripts that only matter in release
  • add missing script guards or dependency-analysis metadata
  • remove accidental serial bottlenecks in schemes
  • align build settings that cause unnecessary module variants
  • fix stale project structure that forces broader rebuilds than necessary
  • identify linters or formatters that touch file timestamps without changing content, silently invalidating build inputs and forcing module replanning
  • split large asset catalogs into separate resource bundles across targets to parallelize compilation
  • use Task Backtraces to pinpoint the exact input change that triggers unnecessary incremental work

Reporting Format

For each issue, include:

  • evidence
  • likely scope
  • why it affects clean builds, incremental builds, or both
  • estimated impact
  • approval requirement

If the evidence points to package graph or build plugins, hand off to spm-build-analysis by reading its SKILL.md and applying its workflow to the same project context.

Additional Resources

  • For the detailed audit checklist, see references/project-audit-checks.md
  • For build settings best practices, see references/build-settings-best-practices.md
  • For the shared recommendation structure, see references/recommendation-format.md
  • For Apple-aligned source summaries, see references/build-optimization-sources.md
SKILL.md on GitHub

Sponsors

SnugThe clipboard manager you and your agent can use, safelyAgent CaffeineClose your lid, come back to finished workWaxBlock anything with supervision, without erasing your iPhoneOpen StepsSponsoredFree and open-source skills that make AI coding agents easier to understand, verify, and control.

Details

Repository
github.com/avdlee/xcode-build-optimization-agent-skill
Categories
DevOps & CI/CD, Git & Pull Requests, Code Review & Quality, AI & Agent Building, Automation & Workflows, Mobile Development
First seen
Apr 16, 2026

More from avdlee/xcode-build-optimization-agent-skill

All 6
  • Xcode Compilation Analyzer3.4K
  • Spm Build Analysis3.4K
  • Xcode Build Benchmark3.4K
  • Xcode Build Fixer3.6K
  • Xcode Build Orchestrator3.6K

Recommended

More DevOps & CI/CD
1avdlee avatarxcode-compilation-analyzeravdlee/xcode-build-optimization-agent-skillAnalyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-first source-level optim3.4Kinstalls
2web-infra-dev avatarios-device-automationweb-infra-dev/midscene-skillsVision-driven iOS device automation using Midscene CLI. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visi3Kinstalls
3web-infra-dev avatarcomputer-automationweb-infra-dev/midscene-skillsVision-driven desktop automation using Midscene. Control your local desktop (macOS, Windows, Linux) or a remote Windows desktop over RDP with natural language c2.8Kinstalls
4web-infra-dev avatarharmonyos-device-automationweb-infra-dev/midscene-skillsVision-driven HarmonyOS NEXT device automation using Midscene. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with a2.3Kinstalls
5web-infra-dev avatarcomputer-automationweb-infra-dev/midscene-skillsVision-driven desktop automation using Midscene. Control your local desktop (macOS, Windows, Linux) or a remote Windows desktop over RDP with natural language c2.2Kinstalls
6web-infra-dev avatarvitest-midscene-e2eweb-infra-dev/midscene-skillsEnhances Vitest with Midscene for AI-powered UI testing across Web (Playwright), Android (ADB), and iOS (WDA). Scaffolds new projects, converts existing project2.1Kinstalls