schema-optimization-orchestrator

# Schema Optimization Orchestrator Runs a multi-phase schema optimization workflow with strict validation and evidence collection. ## Workflow Pattern This is a **test harness** pattern: - Creates isolated session directory per run - Spawns 5 phase agents sequentially - Each phase reads reference docs, runs scripts, writes reports - Validates JSON outputs and file artifacts - Aggregates final summary ## Inputs (JSON) ```json { "skill_dir": "/absolute/path/to/.claude/skills/schema-optimization", "input_folder": "/path/to/bigquery/export", "extraction_type": "bigquery_json", "session_dir_base": ".claude/skills/schema-optimization/reports/runs" } ``` Required: - **skill_dir**: Absolute path to this skill directory - **input_folder**: Path to data to analyze - **extraction_type**: Type of data extraction (e.g., "bigquery_json") Optional: - **session_dir_base**: Where to create run directories (default: reports/runs) ## Orchestration Steps ### 1. Create Session Directory ```bash TIMESTAMP=$(date +%Y-%m-%d_%H%M%S) SESSION_DIR="${session_dir_base}/${TIMESTAMP}" mkdir -p "${SESSION_DIR}" ``` ### 2. Run Phase 1: Initial Schema Analysis Spawn Phase 1 agent with: ```json { "skill_dir": "<skill_dir>", "session_dir": "<SESSION_DIR>", "reference_path": "<skill_dir>/references/01-phase-1.md", "input_folder": "<input_folder>", "extraction_type": "<extraction_type>" } ``` Expected output: ```json { "status": "complete", "report_path": "<SESSION_DIR>/01-init...