memory-review

Scan chat for durable lessons and write them as memory notes.

118|12|Updated May 5, 2026
One-click install
npx skills add https://github.com/alecs5am/ralphy --skill memory-review-alecs5am
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: memory-review
Source: https://github.com/alecs5am/ralphy/tree/main/.agents/skills/memory-review
Command: npx skills add https://github.com/alecs5am/ralphy --skill memory-review-alecs5am

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Lightweight end-of-session memory review — scan the conversation just had for durable lessons and save them into Ralphy's tiered memory, so the next session starts already knowing. The chat-native analog of hermes-agent's background self-review: signals are user corrections, frustration, durable preferences, model/provider facts discovered the hard way, and non-trivial fixes.

Core Features & Use Cases

  • Scan the conversation for signals: user corrections, frustration markers, durable preferences, discovered facts, and techniques that worked.
  • Filter out non-actionable or ephemeral data to keep memory focused and useful.
  • Write memory notes to the tiered store and surface them in chat via "saved to memory" prompts; support "forget" instantly to retire notes.

Quick Start

End a session and run memory-review to save durable lessons into memory.

Frequently Asked Questions about memory-review

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

FAQPage Schema
How do I save durable lessons from a chat session into memory for next time?

Capture durable lessons from your current chat by running an end-of-session review to scan for user corrections, durable preferences, and non-trivial fixes, then write them as memory notes into a tiered memory store.

What conversation signals should I capture for agent memory review?

Agent memory review targets user corrections, frustration markers, durable preferences, discovered model or provider facts, and techniques that worked, while filtering out ephemeral data to keep notes focused and useful.

How does writing memory notes make them available immediately in chat?

Writing memory notes uses a write-and-tell behavior that surfaces saved entries directly in chat via prompts, making the captured session lessons immediately available for the agent to use.

How many memory notes can I save from a single session review?

Session review enforces a 0-5 entry limit when writing memory notes, ensuring only the most durable and actionable lessons are captured in the tiered memory store without overloading it.

Can I retire or forget a saved memory note instantly after a session review?

Yes, you can instantly retire saved memory notes using a forget command, removing unwanted entries from the tiered memory store immediately after they are captured during the session review.

Does memory review prevent leaking sensitive data when saving session lessons?

Memory review enforces data protection by filtering non-actionable data and writing only durable lessons to tiered memory without leaking sensitive information captured during the chat session.