What problem does it solve?
Helps analyze a user’s surface-level behaviors (like playlists and conversation choices) and convert them into a structured long-term memory card that captures personality archetypes, core needs, boundaries, and behavior forecasts.
Core Features & Use Cases
- Layered user understanding: Collects raw signals without pre-judging, then derives behavioral patterns before mapping them to psychological archetypes and deeper needs.
- Evidence-first reasoning: Produces conclusions with explicit links from observable behavior to deeper interpretations, while clearly separating speculation and confidence gaps.
- Memory card generation for retention: Outputs a structured “user_memory_card” including identity signature, core personality traits, behavior patterns, potential interests, existential needs, and tags for retrieval.
- Iterative refinement: Updates predictions and the memory card using user feedback and newly provided data across multiple interactions.
Use Case: When you have weeks of a user’s music-listening history and chat preferences, this skill can produce a reusable profile card that guides future recommendations and interaction style while avoiding overfitting and label-bias.
Quick Start
Use the user_persona skill with the user’s playlist and conversation excerpts to generate a structured memory card.
