Is the Xcode Build Fixer 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 Fixer 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 Fixer?

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 Fixer 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 Fixer

Applies approved Xcode build-setting, script-phase and Swift fixes, then re-benchmarks

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 · 3478161

Installed into a throwaway HOME (mktemp -d): frontmatter parsed to exactly name+description, all three referenced references/*.md plus scripts/benchmark_builds.py returned HTTP 200, the script's --help ran clean on python3 stdlib, and grep found no curl|sh, base64, hardcoded /Users paths or injection text. For output I built a slow-type-checking Swift file (chained arithmetic in score/blend/normalize, swiftc -typecheck best-of-5 = 3.97s), wrote a baseline refactor without the skill (1.70s) and a skill-following refactor per references/fix-patterns.md (1.69s) — identical, so the source-fix half gave zero measurable gain over my own instinct; the skill's extra final/private/explicit-closure-type edits changed nothing in compile time. On a second sub-task, a Debug buildSettings block, the skill artifact added four settings my baseline missed (COMPILATION_CACHE_ENABLE_CACHING, EAGER_LINKING, SWIFT_USE_INTEGRATED_DRIVER, ENABLE_TESTABILITY) plus the `[[ "$CONFIGURATION" != "Release" ]] && exit 0` script guard — a real checklist advantage, but one I could not validate as faster. Verdict is "setup" because this machine has Command Line Tools only (xcodebuild -version errors), so the skill's headline loop — xcodebuild verify plus benchmark_builds.py re-benchmark and the Execution Report deltas — was never executed; that needs full Xcode and a real .xcodeproj.

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 Fixer does

Implements previously approved Xcode build-performance changes — project.pbxproj build settings, run-script phase guards and input/output declarations, Swift source refactors that cut type-checker load, and SPM target restructuring — one reviewable fix at a time. It then re-runs the bundled xcodebuild benchmark script and reports clean, cached-clean and incremental wall-clock deltas in a fixed Execution Report table, with explicit rules for when a slower number is a real regression versus a caching trade-off. Triggers when a developer asks to apply build fixes from an optimization plan, change Debug build settings, guard a script phase, or speed up a slow-compiling Swift file.

How to install Xcode Build Fixer

git clone --depth 1 https://github.com/AvdLee/Xcode-Build-Optimization-Agent-Skill.git /tmp/xcode-build-fixer-src
mkdir -p ~/.claude/skills
cp -R /tmp/xcode-build-fixer-src/skills/xcode-build-fixer ~/.claude/skills/xcode-build-fixer
# Requires macOS with FULL Xcode (not just Command Line Tools) — the verify/re-benchmark
# step shells out to xcodebuild. Check with: xcodebuild -version
# Benchmark script needs python3 (stdlib only, no pip deps):
#   python3 ~/.claude/skills/xcode-build-fixer/scripts/benchmark_builds.py \
#     --project App.xcodeproj --scheme MyApp --configuration Debug \
#     --destination "platform=iOS Simulator,name=iPhone 16" --output-dir .build-benchmark
# SKILL.md's escalation links point at sibling skills (xcode-project-analyzer,
# xcode-compilation-analyzer, spm-build-analysis) that are NOT installed by the above.
# To get the whole set instead:
#   for s in xcode-build-fixer xcode-build-benchmark xcode-build-orchestrator \
#            xcode-compilation-analyzer xcode-project-analyzer spm-build-analysis; do
#     cp -R /tmp/xcode-build-fixer-src/skills/$s ~/.claude/skills/$s; done
# Plugin alternative: /plugin marketplace add AvdLee/Xcode-Build-Optimization-Agent-Skill
#                     /plugin install xcode-build-skills@xcode-build-skills

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

Commands — how to trigger Xcode Build Fixer

/xcode-build-fixer Applies approved Xcode build-setting, script-phase and Swift fixes, then re-benchmarks

It also activates on plain-language prompts like these:

Apply the approved build optimization plan
Fix the script phase causing slow builds
Re-benchmark after applying this build setting change

Frequently asked questions

Is the Xcode Build Fixer 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 Fixer work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Works with setup. Installed into a throwaway HOME (mktemp -d): frontmatter parsed to exactly name+description, all three referenced references/*.md plus scripts/benchmark_builds.py returned HTTP 200, the script's --help ran clean on python3 stdlib, and grep found no curl|sh, base64, hardcoded /Users paths or injection text. For output I built a slow-type-checking Swift file (chained arithmetic in score/blend/normalize, swiftc -typecheck best-of-5 = 3.97s), wrote a baseline refactor without the skill (1.70s) and a skill-following refactor per references/fix-patterns.md (1.69s) — identical, so the source-fix half gave zero measurable gain over my own instinct; the skill's extra final/private/explicit-closure-type edits changed nothing in compile time. On a second sub-task, a Debug buildSettings block, the skill artifact added four settings my baseline missed (COMPILATION_CACHE_ENABLE_CACHING, EAGER_LINKING, SWIFT_USE_INTEGRATED_DRIVER, ENABLE_TESTABILITY) plus the `[[ "$CONFIGURATION" != "Release" ]] && exit 0` script guard — a real checklist advantage, but one I could not validate as faster. Verdict is "setup" because this machine has Command Line Tools only (xcodebuild -version errors), so the skill's headline loop — xcodebuild verify plus benchmark_builds.py re-benchmark and the Execution Report deltas — was never executed; that needs full Xcode and a real .xcodeproj.
What is the Xcode Build Fixer 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 Fixer?: 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 Fixer 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.