skill-memory

Organize domain knowledge into grepable markdown entries with timestamps.

6|Updated Apr 7, 2026
One-click install
npx skills add https://github.com/Kgan01/ghengis-skills --skill skill-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: skill-memory
Source: https://github.com/Kgan01/ghengis-skills/tree/main/plugins/ghengis-skills/skills/skill-memory
Command: npx skills add https://github.com/Kgan01/ghengis-skills --skill skill-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Organizes and persists transferable domain knowledge from past tasks into a grepable plain-text knowledge base that grows with experience, eliminating reliance on vector databases.

Core Features & Use Cases

  • Lessons learned — Document non-obvious pitfalls and fixes from past tasks
  • Patterns discovered — Capture reusable approaches and techniques
  • Pitfalls encountered — Record traps to avoid in future work
  • Successful approaches — Explain what worked and why
  • Environment specifics — Note setup details that mattered

Quick Start

Document a recent non-trivial task by adding a new knowledge entry with timestamp, lessons, patterns, and pitfalls.

Frequently Asked Questions about skill-memory

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

FAQPage Schema
How do I create a grepable knowledge base from lessons learned in past tasks?

Create a grepable knowledge base by organizing transferable domain knowledge from past non-trivial tasks into structured markdown plain-text files. This captures lessons, patterns, pitfalls, and successful approaches, eliminating reliance on vector databases.

What is a grepable knowledge base and how does it store project retrospectives?

A grepable knowledge base is a collection of structured markdown plain-text files that stores project retrospective entries. It persists transferable domain knowledge by recording timestamps, lessons, patterns, pitfalls, and recommendations without requiring a vector database.

Do I need a vector database to maintain a searchable knowledge base of lessons learned?

No, you do not need a vector database to maintain a searchable knowledge base of lessons learned. You can organize and persist transferable domain knowledge directly into grepable plain-text files using structured markdown formats.

What's the best way to document pitfalls and successful approaches after completing a task?

The best way to document pitfalls and successful approaches is by adding a new structured markdown entry to a plain-text knowledge base. Enforce a consistent format with timestamps to capture lessons, patterns, pitfalls, and recommendations after non-trivial tasks.

Can I use markdown to capture engineering patterns and environment specifics in a knowledge base?

Yes, you can use markdown to capture engineering patterns and environment specifics in a knowledge base. The system stores knowledge as structured markdown entries in plain files, ensuring consistent formatting for all lessons, patterns, and setup details.