memory-md

Read repository MEMORY.md files to surface gotchas and preferences.

8|Updated Jan 7, 2026

Search Tags:#context #repository #memory #notes #gotchas #memory-md

Ready to run

npx skills add https://github.com/narumiruna/skills --skill memory-md

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory-md
Source: https://github.com/narumiruna/skills/tree/main/skills/memory-md
Command: npx skills add https://github.com/narumiruna/skills --skill memory-md

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Maintains concise repository MEMORY.md notes for gotchas, stale memory corrections, and durable user preferences to surface context at the start of repository conversations.

Core Features & Use Cases

Provides a lightweight, repository-scoped memory log to avoid repeating mistakes.
Guides future interactions by surfacing user preferences and past decisions.
Used at project kickoff or during debugging to recall critical context and constraints.

Quick Start

Check for a MEMORY.md at the root of your repository and read it before planning tasks or edits.

Frequently Asked Questions about memory-md

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

FAQPage Schema

How do I maintain repository context across conversations to avoid repeating mistakes?▼

You maintain repository context by centralizing notes in a MEMORY.md file at the repository root. This stores gotchas and user preferences to surface critical context at the start of future conversations.

What is the best way to recall past decisions and constraints when debugging a repository?▼

The best way to recall past decisions is checking a MEMORY.md file at the repository root before planning tasks or edits. It surfaces durable guidance and constraints to prevent repeating past mistakes.

How does the GOTCHA and TASTE structure work for repository memory notes?▼

The GOTCHA and TASTE structure enforces a specific format for repository memory notes. It organizes durable guidance, stale memory corrections, and user preferences into a concise, standardized layout within MEMORY.md.

Do I need a specific file format to store repository memory for future work?▼

Yes, you need a MEMORY.md file created at the repository root. The system requires this markdown file to read and surface repository-specific context before planning tasks or debugging.

When should I use repository memory notes during project work?▼

Use repository memory notes at project kickoff or during debugging to recall critical context. It applies at the start of repository conversations when past context and constraints matter for planning.

Can I use a memory log to guide future interactions with my repository?▼

Yes, a repository memory log guides future interactions by surfacing user preferences and past decisions. It provides lightweight, repository-scoped context to prevent repeating mistakes during edits.