data-analysislisted

# Data Analysis Skill This skill provides patterns and best practices for AI-powered data analysis across the Empathy Ledger platform, ensuring quotes, themes, summaries, and suggestions appear consistently everywhere. ## Core Data Model ### Analysis Pipeline ``` Transcript (raw audio/text) ↓ AI Analysis Theme Extraction → themes[] array Quote Extraction → key_quotes[] array Summary Generation → ai_summary text Sentiment Analysis → sentiment_scores{} ↓ Story Creation Story (authored content) ↓ Connections Related Stories ← theme matching Suggested Content ← AI recommendations ``` ### Key Tables for Analysis | Table | Analysis Fields | Purpose | |-------|-----------------|---------| | `transcripts` | `themes`, `key_quotes`, `ai_summary`, `ai_processing_status` | Raw interview analysis | | `stories` | `themes`, `cultural_tags`, `featured_quote` | Published story metadata | | `storytellers` | `expertise_themes`, `connection_strength` | Storyteller insights | | `story_suggestions` | `reason`, `confidence_score`, `theme_overlap` | AI recommendations | ## Theme System ### Standard Theme Categories ```typescript const THEME_CATEGORIES = { cultural: ['identity', 'heritage', 'tradition', 'language', 'ceremony'], family: ['kinship', 'elders', 'children', 'ancestors', 'community'], land: ['country', 'connection', 'seasons', 'wildlife', 'sacred-sites'], resilience: ['survival', 'adaptation', 'strength', 'healing', 'hope'], knowledge: ['wisdom', 'teaching', 'l