reme-personal-memory

name	reme-personal-memory
description	Use when an agent needs a file-first ReMe workspace as the source of durable setup facts, stable preferences, or reusable daily decision records.

ReMe Personal Memory

This is the legacy-compatible root shim for the repository.

The canonical implementation of this skill lives at skills/reme-personal-memory/. Use that version when your host can load multiple skills from one repository.

When to Use

Use this root shim when your installer loads only the repository root and you still need the original file-first reme-personal-memory behavior.

Use it to:

• read prior setup facts, integration notes, or operating decisions
• record durable configuration changes for future agents
• preserve reusable context after completing a task
• answer questions that depend on a stable environment, tooling, or preferences

Do not use it for vector-backed memory, HTTP or MCP startup, Tool Memory, or Working Memory.

File Contract

The compatibility contract is unchanged:

• SETUP.md stores stable entrypoints, startup methods, integration topology, and boundary conditions
• MEMORY.md stores long-lived preferences, standing rules, and durable facts
• memory/YYYY-MM-DD.md stores daily actions, validations, incidents, and decisions

Read order:

1. SETUP.md
2. MEMORY.md
3. memory/YYYY-MM-DD.md

Write policy:

• write stable environment facts to SETUP.md
• write durable preferences and rules to MEMORY.md
• write day-specific execution notes to memory/YYYY-MM-DD.md

Shim Rules

• keep this root entry behaviorally aligned with skills/reme-personal-memory
• treat skills/reme-personal-memory as the canonical source for future edits
• keep the scope file-first and markdown-first