What problem does it solve? AI agents lose all context between sessions, forcing users to repeatedly re-explain their preferences, coding conventions, and past decisions. This Skill provides persistent, searchable memory so agents recall what was already learned instead of re-discovering it. ## Core Features & Use Cases - Structured Memory Index: Maintains a lightweight MEMORY.md index (max 200 lines) that points to detailed topic files for user preferences, project conventions, tech decisions, and feedback history. - Four Memory Operations: Supports Save, Recall, Search, and Prune workflows triggered by phrases like "remember this" or "what do you remember about X". - Session Start Protocol: Automatically loads the memory index at session start and silently applies relevant context without reciting it. - Use Case: A developer tells the agent "remember we use bun instead of npm". In the next session, the agent reads the memory index and uses bun in all commands without being told again. ## Quick Start Remember that I prefer concise responses and use bun instead of npm for all package management in this project.
