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

Use a ReMe workspace as the canonical file-first long-term memory source.

When to Use

Use this skill when you need to:

• recall prior environment setup or integration topology
• store durable facts that should survive the current chat
• leave operational notes for future agents
• answer questions that depend on an established workflow

Do not use this skill for temporary scratch notes, disposable reasoning, vector-backed retrieval, HTTP startup, MCP startup, Tool Memory, or Working Memory.

Workspace Contract

A ReMe workspace root contains:

• SETUP.md for stable entrypoints, install state, startup methods, integration topology, and boundary conditions
• MEMORY.md for long-lived preferences, standing rules, and durable facts
• memory/YYYY-MM-DD.md for daily changes, validation results, troubleshooting findings, and decisions

Before reading or writing, identify the workspace root from existing configuration, repository context, or explicit user instructions.

Read Order

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

If the task is about a recent installation, integration, or incident, check today's dated note after reading SETUP.md.

Write Policy

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

Writing Rules

• only write information another agent could reuse later
• include exact paths, commands, versions, and boundary conditions when relevant
• prefer concrete operational facts over narrative summaries
• update SETUP.md when entrypoints, startup methods, or topology change
• append a short dated note when today's work changes setup or debugging state

Template

Use templates/reme-workspace/ in this skill folder when you need a copyable workspace scaffold.