memory-systemlisted

## Purpose A coding agent's context resets between sessions. Without a durable place to record decisions, conventions, and the reasoning behind them, every new session either re-derives context from scratch (slow, and prone to contradicting earlier decisions) or plows ahead without it (fast, and prone to redoing work or reversing a decision nobody remembers making). This skill defines a small, low-overhead file layout that fixes that, and the routine for keeping it current. ## When to use it At the start of every nontrivial task, before touching code. At the end of every nontrivial task, before considering it done. "Nontrivial" means: it involved a design or approach decision, it changed behavior a future session would need to know about, or it took more than a few minutes of back-and-forth to get right. A one-line typo fix doesn't need a memory update; a new feature, an architecture change, or a fix for a subtle bug does. ## File layout Create these under `docs/memory/` in the project root the first time this skill is used on a project that doesn't have them yet: - **`docs/memory/core-principles.md`** — the stable layer. Architectural decisions and constraints that rarely change: the chosen stack, non-negotiable invariants, things that would require a real conversation to reverse. Keep this short — if it's growing every week, content belongs in one of the other files instead. - **`docs/memory/workflow.md`** — the process layer. How this specific team/project actually w