xcode-build-orchestrator — Робота агентів, навичка для агента від avdlee/xcode-build-optimization-agent-skill

# Benchmark Artifacts

All skills in this repository should treat `.build-benchmark/` as the canonical location for measured build evidence.

## Goals

- Keep build measurements reproducible.
- Make clean and incremental build data easy to compare.
- Preserve enough context for later specialist analysis without rerunning the benchmark.

## Wall-Clock vs Cumulative Task Time

The `duration_seconds` field on each run and the `median_seconds` in the summary represent **wall-clock time** -- how long the developer actually waits. This is the primary success metric.

The `timing_summary_categories` are **aggregated task times** parsed from Xcode's Build Timing Summary. Because Xcode runs many tasks in parallel across CPU cores, these totals typically exceed the wall-clock duration. A large cumulative `SwiftCompile` value is diagnostic evidence of compiler workload, not proof that compilation is blocking the build. Always compare category totals against the wall-clock median before concluding that a category is a bottleneck.

## File Layout

Recommended outputs:

- `.build-benchmark/<timestamp>-<scheme>.json`
- `.build-benchmark/<timestamp>-<scheme>-clean-1.log`
- `.build-benchmark/<times

# Build Settings Best Practices

This reference lists Xcode build settings that affect build performance. Use it to audit a project and produce a pass/fail checklist.

The scope is strictly **build performance**. Do not flag language-migration settings like `SWIFT_STRICT_CONCURRENCY` or `SWIFT_UPCOMING_FEATURE_*` -- those are developer adoption choices unrelated to build speed.

## How To Read This Reference

Each setting includes:

- **Setting name** and the Xcode build-settings key
- **Recommended value** for Debug and Release
- **Why it matters** for build time
- **Risk** of changing it

Use checkmark and cross indicators when reporting:

- `[x]` -- setting matches the recommended value
- `[ ]` -- setting does not match; include the actual value and the expected value

## Debug Configuration

These settings optimize for fast iteration during development.

### Compilation Mode

- **Key:** `SWIFT_COMPILATION_MODE`
- **Recommended:** `singlefile` (Xcode UI: "Incremental"; or unset -- Xcode defaults to singlefile for Debug)
- **Why:** Single-file mode recompiles only changed files. `wholemodule` recompiles the entire target on every change.
- **Risk:** Low

### Swift Optimization Le

# Orchestration Report Template

Use this structure when the orchestrator consolidates benchmark evidence and specialist findings. The `generate_optimization_report.py` script produces this format automatically when given the benchmark and diagnostics artifacts.

```markdown
# Xcode Build Optimization Plan

## Project Context
- **Project:** `App.xcodeproj`
- **Scheme:** `MyApp`
- **Configuration:** `Debug`
- **Destination:** `platform=iOS Simulator,name=iPhone 16`
- **Xcode:** Xcode 26.x
- **Date:** 2026-01-01T00:00:00Z
- **Benchmark artifact:** `.build-benchmark/<timestamp>-<scheme>.json`

## Baseline Benchmarks

| Metric | Clean | Cached Clean | Zero-Change |
|--------|-------|-------------|-------------|
| Median | 0.000s | 0.000s | 0.000s |
| Min | 0.000s | 0.000s | 0.000s |
| Max | 0.000s | 0.000s | 0.000s |
| Runs | 3 | 3 | 3 |

> **Cached Clean** = clean build with a warm compilation cache. This is the realistic scenario for branch switching, pulling changes, or Clean Build Folder. Only present when `COMPILATION_CACHE_ENABLE_CACHING = YES` is detected. "Zero-Change" = rebuild with no edits (measures fixed overhead). Use `--touch-file` in the benchmark script to measure true 

# Recommendation Format

All optimization skills should report recommendations in a shared structure so the orchestrator can merge and prioritize them cleanly.

## Required Fields

Each recommendation should include:

- `title`
- `wait_time_impact` -- plain-language statement of expected wall-clock impact, e.g. "Expected to reduce your clean build by ~3s", "Reduces parallel compile work but unlikely to reduce build wait time", or "Impact on wait time is uncertain -- re-benchmark to confirm"
- `actionability` -- classifies how fixable the issue is from the project (see values below)
- `category`
- `observed_evidence`
- `estimated_impact`
- `confidence`
- `approval_required`
- `benchmark_verification_status`

### Actionability Values

Every recommendation must include an `actionability` classification:

- `repo-local` -- Fix lives entirely in project files, source code, or local configuration. The developer can apply it without side effects outside the repo.
- `package-manager` -- Requires CocoaPods or SPM configuration changes that may have broad side effects (e.g., linkage mode, dependency restructuring). These should be benchmarked before and after.
- `xcode-behavior` -- Observed 

---
name: xcode-build-orchestrator
description: Orchestrate Xcode build optimization by benchmarking first, running the specialist analysis skills, prioritizing findings, requesting explicit approval, delegating approved fixes to xcode-build-fixer, and re-benchmarking after changes. Use when a developer wants an end-to-end build optimization workflow, asks to speed up Xcode builds, wants a full build audit, or needs a recommend-first optimization pass covering compilation, project settings, and packages.
---

# Xcode Build Orchestrator

Use this skill as the recommend-first entrypoint for end-to-end Xcode build optimization work.

## Non-Negotiable Rules

- Wall-clock build time (how long the developer waits) is the primary success metric. Every recommendation must state its expected impact on the developer's actual wait time.
- Start in recommendation mode.
- Benchmark before making changes.
- Do not modify project files, source files, packages, or scripts without explicit developer approval.
- Preserve the evidence trail for every recommendation.
- Re-benchmark after approved changes and report the wall-clock delta.

## Two-Phase Workflow

The orchestration is designed as two dis