using-forgetful-memory

Query Forgetful MCP memories to surface prior decisions and architectural insights.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/Compass-Brand/compass-forge --skill using-forgetful-memory-compass-brand
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: using-forgetful-memory
Source: https://github.com/Compass-Brand/compass-forge/tree/main/.claude/skills/using-forgetful-memory
Command: npx skills add https://github.com/Compass-Brand/compass-forge --skill using-forgetful-memory-compass-brand

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Forgetful memory integration helps you surface past decisions, patterns, and architectural insights at the start of a project by proactively querying the Forgetful MCP, reducing rework and context loss.

Core Features & Use Cases

  • Proactive memory queries: surface relevant memories and decisions when starting new work or revisiting past discussions.
  • Context preservation: capture important decisions, patterns, and preferences to keep teams aligned across projects.
  • Quick initiation: retrieve recent memories, summarize context, and link related notes to new work.

Quick Start

Use Forgetful memory to check for prior context before writing new features or making architectural choices; run a memory query like: "What precedents exist for this design?" to get immediate context.

Frequently Asked Questions about using-forgetful-memory

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I retrieve past project decisions and architectural context before starting new work?

Memory atomicity requires creating discrete, concise memory units with strict constraints on content length, attribution, and linked relationships. This ensures retrieved context remains structured and directly relevant to the query.

How do I document key architectural notes and capture project context?

Document architectural notes by using the create_memory command from the Forgetful MCP. This proactively captures important decisions, patterns, and preferences to keep teams aligned across projects.

What is the best way to reference previous patterns and preferences during development?

Forgetful memory integration requires explicit interaction with MCP tools, specifically query_memory, get_recent_memories, and create_memory. No additional dependencies are needed to manage memory retrieval and creation.

Why does memory atomicity matter when managing project context?

Memory atomicity requires creating discrete, concise memory units with strict constraints on content length, attribution, and linked relationships. This ensures retrieved context remains structured and directly relevant to the query.