Is the Xcode Build Benchmark skill free?

Yes. The skill itself is free from AvdLee/Xcode-Build-Optimization-Agent-Skill. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Xcode Build Benchmark SkillProof Score?

7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.

How do I install Xcode Build Benchmark?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Xcode Build Benchmark with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Xcode Build Benchmark

Measures Xcode clean, cached-clean and incremental build times into a JSON artifact

by AvdLee · AvdLee/Xcode-Build-Optimization-Agent-Skill

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 7.6/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 32ff2f3

This machine has only Command Line Tools (`xcodebuild -version` errors: "requires Xcode"), so no real iOS build could be benchmarked — hence outputMeasured=false. To verify the machinery anyway I put a stub `xcodebuild` on PATH that emits a fake Build Timing Summary and ran `scripts/benchmark_builds.py` end to end: exit 0, 12 raw logs plus one timestamped JSON written to the output dir, cached-clean phase auto-detected from COMPILATION_CACHE_ENABLE_CACHING=YES, medians/min/max computed per build type, and the timing parser correctly split "SwiftCompile (412 tasks) | 128.412 seconds" into name/seconds/task_count. One concrete defect: the default run (no --touch-file) tags runs `build_type: "zero-change"`, which fails the skill's own schemas/build-benchmark.schema.json (enum is clean|cached-clean|incremental) — jsonschema rejected the generated artifact. Scripts are network-free with no curl|sh, base64 or injection text; the only footgun is `shutil.rmtree` on a user-supplied --derived-data-path during the cached-clean phase.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 5/10
Docs & honesty 4/5

What Xcode Build Benchmark does

Runs repeatable xcodebuild benchmarks for a scheme — 3 clean builds, 3 zero-change builds, optional touch-file incremental builds, plus a cached-clean phase when COMPILATION_CACHE_ENABLE_CACHING is on — and writes timestamped JSON plus raw logs to .build-benchmark/. Reports medians, min/max and the dominant build-timing-summary categories instead of a single fastest run. Triggers when a developer asks to measure Xcode build times, wants a before/after baseline, or asks whether builds got faster or slower.

How to install Xcode Build Benchmark

git clone --depth 1 https://github.com/AvdLee/Xcode-Build-Optimization-Agent-Skill.git /tmp/xcode-build-benchmark-src
mkdir -p ~/.claude/skills
cp -R /tmp/xcode-build-benchmark-src/skills/xcode-build-benchmark ~/.claude/skills/xcode-build-benchmark
# Requires full Xcode (not just Command Line Tools) and an .xcodeproj/.xcworkspace.
# CLI instead: npx skills add https://github.com/AvdLee/Xcode-Build-Optimization-Agent-Skill --skill xcode-build-benchmark
# Plugin instead: /plugin marketplace add AvdLee/Xcode-Build-Optimization-Agent-Skill
# Run from the project directory:
#   python3 ~/.claude/skills/xcode-build-benchmark/scripts/benchmark_builds.py \
#     --workspace App.xcworkspace --scheme MyApp --configuration Debug \
#     --destination "platform=iOS Simulator,name=iPhone 16" --output-dir .build-benchmark

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Xcode Build Benchmark

/xcode-build-benchmark Measures Xcode clean, cached-clean and incremental build times into a JSON artifact

It also activates on plain-language prompts like these:

Benchmark our current Xcode build time
Compare build times before and after this change
Measure how long incremental builds take now

Frequently asked questions

Is the Xcode Build Benchmark skill free?: Yes. The skill itself is free from AvdLee/Xcode-Build-Optimization-Agent-Skill. SkillProof publishes the install command and an independent test verdict at no cost.
Does Xcode Build Benchmark work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Works with setup. This machine has only Command Line Tools (`xcodebuild -version` errors: "requires Xcode"), so no real iOS build could be benchmarked — hence outputMeasured=false. To verify the machinery anyway I put a stub `xcodebuild` on PATH that emits a fake Build Timing Summary and ran `scripts/benchmark_builds.py` end to end: exit 0, 12 raw logs plus one timestamped JSON written to the output dir, cached-clean phase auto-detected from COMPILATION_CACHE_ENABLE_CACHING=YES, medians/min/max computed per build type, and the timing parser correctly split "SwiftCompile (412 tasks) | 128.412 seconds" into name/seconds/task_count. One concrete defect: the default run (no --touch-file) tags runs `build_type: "zero-change"`, which fails the skill's own schemas/build-benchmark.schema.json (enum is clean|cached-clean|incremental) — jsonschema rejected the generated artifact. Scripts are network-free with no curl|sh, base64 or injection text; the only footgun is `shutil.rmtree` on a user-supplied --derived-data-path during the cached-clean phase.
What is the Xcode Build Benchmark SkillProof Score?: 7.6/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 5/10, docs & honesty 4/5.
How do I install Xcode Build Benchmark?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Xcode Build Benchmark with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.