getting-started

## Purpose Transform the post-onboarding experience from "blank chat window" to guided value delivery. Adaptive based on what data sources are available (calendar, Granola, or neither). ## When to Run - Automatically suggested at session start if vault < 7 days old - User types `/getting-started` - After onboarding completion (Step 10) - User says they're not sure what to do next ## Entry Point ### Step 1: Check for Deferred Pre-Analysis **FIRST:** Read `.onboarding-complete` marker file to check if this is Phase 2 right after onboarding: ```python marker_file = BASE_DIR / 'System' / '.onboarding-complete' if marker_file.exists(): marker_data = json.loads(marker_file.read_text()) pre_analysis_deferred = marker_data.get('pre_analysis_deferred', False) completed_at = datetime.fromisoformat(marker_data['completed_at']) age_hours = (datetime.now() - completed_at).total_seconds() / 3600 # If onboarding just completed (< 1 hour) and pre-analysis was deferred if age_hours < 1 and pre_analysis_deferred: # This is the first /getting-started run after onboarding # MCPs are NOW loaded and we can do the full analysis with dramatic reveal run_dramatic_reveal = True else: run_dramatic_reveal = False else: run_dramatic_reveal = False ``` ### Step 2: Dramatic Reveal (if flagged) **If `run_dramatic_reveal` is True:** Say: "Hold on... analyzing your calendar and meetings. 🔍" **Execute analysis:** 1. Call calendar ...