skill-memory-as-carton-projection

name

skill-memory-as-carton-projection

description

WHAT: the architecture where persistent agent memory files (MEMORY.md and other memory artifacts) are auto-generated VIEWS projected from the CartON knowledge graph, with CartON as the single source of truth — you never hand-edit the memory file, you change the graph and recompile. WHEN: when designing or improving how the agent's persistent memory works across sessions, deciding where memory should be stored, or wondering why MEMORY.md should not be edited directly.

'''Understanding that MEMORY.md '''Replayable skill pattern - understand=context only''' '''How persistent agent memory is structured '''Skill category classification''' '''Personal domain category enum for observation tagging''' '''How persistent agent memory is structured '''Pattern where memory files are generated outputs of a knowledge graph '''The concept that all memory artifacts (MEMORY.md '''When designing or improving how the agent's persistent memory works across sessions''' '''Architecture where CartON is source of truth and files are auto-generated views''' '''Self-referential — this IS the foundational understanding''' '''GIINT component this skill documents'''

---

Skill Contents

• reference.md — detailed reference (read for full docs)