Multi-phase schema optimization workflow orchestrator. Creates session directories, spawns phase agents sequentially, validates outputs, aggregates results. Trigger: "run schema optimization", "optimize schema workflow", "execute schema phases"
npxskills add jeremylongshore/claude-code-plugins-plus-skills--skill schema-optimization-orchestratorLoading…
Runs a multi-phase schema optimization workflow with strict validation and evidence collection.
This is a test harness pattern:
{
"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:
Optional:
TIMESTAMP=$(date +%Y-%m-%d_%H%M%S)
SESSION_DIR="${session_dir_base}/${TIMESTAMP}"
mkdir -p "${SESSION_DIR}"
Spawn Phase 1 agent with:
{
"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:
{
"status": "complete",
"report_path": "<SESSION_DIR>/01-initial-schema-analysis.md",
"schema_summary": {
"total_tables": 0,
"total_fields": 0,
"key_findings": []
}
}
Validation:
status is "complete"report_path file existsschema_summary has required keysSpawn Phase 2 agent with:
{
"skill_dir": "<skill_dir>",
"session_dir": "<SESSION_DIR>",
"reference_path": "<skill_dir>/references/02-phase-2.md",
"phase1_report_path": "<phase1_report_path>",
"input_folder": "<input_folder>"
}
Expected output:
{
"status": "complete",
"report_path": "<SESSION_DIR>/02-field-utilization-analysis.md",
"utilization_summary": {
"unused_fields": [],
"low_utilization_fields": [],
"recommendations": []
}
}
Spawn Phase 3 agent with:
{
"skill_dir": "<skill_dir>",
"session_dir": "<SESSION_DIR>",
"reference_path": "<skill_dir>/references/03-phase-3.md",
"phase1_report_path": "<phase1_report_path>",
"phase2_report_path": "<phase2_report_path>",
"input_folder": "<input_folder>"
}
Expected output:
{
"status": "complete",
"report_path": "<SESSION_DIR>/03-impact-assessment.md",
"impact_summary": {
"high_risk_changes": [],
"medium_risk_changes": [],
"low_risk_changes": [],
"estimated_savings": {}
}
}
Spawn Phase 4 agent with:
{
"skill_dir": "<skill_dir>",
"session_dir": "<SESSION_DIR>",
"reference_path": "<skill_dir>/references/04-phase-4-verify-with-script.md",
"phase2_report_path": "<phase2_report_path>",
"phase3_report_path": "<phase3_report_path>",
"input_folder": "<input_folder>",
"script_path": "<skill_dir>/scripts/analyze_field_utilization.sh",
"output_folder_path": "<input_folder>"
}
Expected output:
{
"status": "complete",
"report_path": "<SESSION_DIR>/04-field-utilization-verification.md",
"verification_summary": {
"files_analyzed": 0,
"conclusions_confirmed": [],
"conclusions_revised": [],
"unexpected_findings": [],
"revised_action_items": []
}
}
Spawn Phase 5 agent with:
{
"skill_dir": "<skill_dir>",
"session_dir": "<SESSION_DIR>",
"reference_path": "<skill_dir>/references/05-phase-5.md",
"phase1_report_path": "<phase1_report_path>",
"phase2_report_path": "<phase2_report_path>",
"phase3_report_path": "<phase3_report_path>",
"phase4_report_path": "<phase4_report_path>"
}
Expected output:
{
"status": "complete",
"report_path": "<SESSION_DIR>/05-final-recommendations.md",
"recommendations_summary": {
"priority_actions": [],
"implementation_plan": [],
"success_metrics": []
}
}
{
"status": "complete",
"session_dir": "<SESSION_DIR>",
"timestamp": "YYYY-MM-DD_HHMMSS",
"phase_reports": {
"phase1": "<SESSION_DIR>/01-initial-schema-analysis.md",
"phase2": "<SESSION_DIR>/02-field-utilization-analysis.md",
"phase3": "<SESSION_DIR>/03-impact-assessment.md",
"phase4": "<SESSION_DIR>/04-field-utilization-verification.md",
"phase5": "<SESSION_DIR>/05-final-recommendations.md"
},
"final_summary": {
"total_tables": 0,
"total_fields": 0,
"unused_fields": 0,
"optimization_opportunities": 0,
"estimated_savings_pct": 0,
"verification_status": "confirmed"
}
}
If any phase fails:
{
"status": "error",
"failed_phase": 3,
"error_message": "Phase 3 agent failed validation",
"session_dir": "<SESSION_DIR>",
"completed_phases": ["phase1", "phase2"]
}
After each phase:
status is "complete" (fail if not)report_path exists on disk (fail if not)User: "Run schema optimization on my BigQuery export"
Claude: [Creates session directory]
Claude: [Spawns Phase 1 agent]
Claude: [Validates Phase 1 output]
Claude: [Spawns Phase 2 agent with Phase 1 report]
Claude: [... continues through Phase 5]
Claude: [Returns final JSON summary]
reports/runs/2025-01-15_143022/
├── 01-initial-schema-analysis.md
├── 02-field-utilization-analysis.md
├── 03-impact-assessment.md
├── 04-field-utilization-verification.md
└── 05-final-recommendations.md
Each file is evidence of work completed.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or multi-account), or reading/injecting/running secrets via op.
CLI to manage emails via IMAP/SMTP. Use `himalaya` to list, read, write, reply, forward, search, and organize emails from the terminal. Supports multiple accounts and message composition with MML (MIME Meta Language).