memory-curatelisted

# Memory Curate The least flashy and most consequential skill in the system. Without it, the project's memory layer slowly accumulates stale guidance that misleads every future AI Coding session. ## Core mental model Memory has **two layers**: - **Facts** — observations grounded in code / docs / decisions at a specific time - **Inferences** — derived claims about how things work / what to do Inferences depend on facts. If a fact changes and inferences don't update, the AI starts giving advice based on a world that no longer exists. ``` Fact (2026-01): "we use PostgreSQL 13, pgvector ext disabled" Infer (2026-01): "for vector search, use a separate Milvus instance" ↓ Fact (2026-04): upgraded to PG 16, pgvector enabled ← changed Infer (2026-01): "use a separate Milvus instance" ← now stale ↓ Without curation: AI keeps suggesting Milvus, even though pgvector is now available With curation: inference is invalidated → re-derived → suggests pgvector ``` Your job is to detect and repair these mismatches. ## What this skill produces 1. Refreshed `.memory/MEMORY.md` (the index) 2. Updated individual memory files (with bumped `last_verified` where applicable) 3. `.memory/curation/weekly_<YYYY-MM-DD>.md` — the curation report ## When NOT to use this skill Skip for: - Writing new factual content (that's the producing skill's job — `prd-author`, `openspec-apply-change`, etc.) - Audit/compliance freezing (use `audit-snapshot`) - Project setup (no