What problem does it solve? AI agents lose all context between sessions, forcing users to repeat facts, preferences, and project details. This Skill provides a file-based memory system that persists durable knowledge across sessions using Tiago Forte's PARA method. ## Core Features & Use Cases - Three-Layer Memory: A PARA knowledge graph (projects, areas, resources, archives) for entity facts, daily notes for raw timelines, and a tacit knowledge file capturing user patterns and preferences. - Atomic Fact Schema with Decay: Facts stored in items.yaml carry status, timestamps, and access counts; weekly synthesis rewrites summaries using recency tiers so stale facts drop out without deletion. - Semantic Recall via qmd: Search memory with vector similarity, BM25 keyword search, and reranking instead of grepping files. - Use Case: When a user mentions a coworker for the third time, create an entity folder under areas/people, record facts in items.yaml, and later recall them instantly with a qmd query. ## Quick Start Save this fact to memory and organize it under the right PARA category, then show me what you remember about my current projects.
