remember

Name: remember
Availability: InStock
Author: Yonatan

Store decisions, patterns, and outcomes in a knowledge graph via MCP memory servers.

217|20|Updated Dec 31, 2025

Search Tags:#best practices #decisions #workflow automation #knowledge graph #patterns #memory

Ready to run

npx skills add https://github.com/yonatangross/orchestkit --skill remember-yonatangross

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: remember
Source: https://github.com/yonatangross/orchestkit/tree/main/plugins/ork/skills/remember
Command: npx skills add https://github.com/yonatangross/orchestkit --skill remember-yonatangross

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) and rules (resource) components.

What problem does it solve?

This Skill prevents knowledge loss by storing important decisions, patterns, and outcomes in a persistent knowledge graph, ensuring that valuable insights are not forgotten between sessions.

Core Features & Use Cases

Persistent Memory: Saves key information as entities and relationships in a knowledge graph.
Outcome Tracking: Can mark memories as successful patterns or anti-patterns, building a best-practice library.
Use Case: After a complex debugging session, use this Skill to record the root cause and the fix, so the team can quickly reference it if a similar issue arises.

Quick Start

Use the remember skill to store the decision that we chose PostgreSQL with pgvector for RAG.

Frequently Asked Questions about remember

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

FAQPage Schema

How do I store decisions and patterns in a knowledge graph for future reference?▼

You can store decisions and patterns in a knowledge graph by using MCP memory servers to save key information as entities and relationships, preventing knowledge loss between sessions.

What is the best way to track successful patterns and anti-patterns during workflow automation?▼

Tracking successful patterns and anti-patterns involves storing outcomes in a persistent knowledge graph, allowing you to build a best-practice library by marking memories as successful or failed.

Can I automatically extract entities and relationships from natural language input?▼

Yes, automatic entity and relationship extraction from natural language input is supported, enabling you to save key information directly without manual structuring of the knowledge graph.

How do I record root causes and fixes after a complex debugging session?▼

Recording root causes and fixes is done by storing the decision and outcome in a knowledge graph via MCP memory servers, ensuring the team can quickly reference the solution if a similar issue arises.

Does this approach require a specific database to store a best practice library?▼

Building a best practice library requires MCP memory servers to persistently store decisions, patterns, and outcomes as entities and relationships within a knowledge graph structure.