remember-that

Persist user corrections and preferences to GLOBAL.md or project-specific AGENTS.md files.

Updated Nov 26, 2025
One-click install
npx skills add https://github.com/Aias/dotfiles --skill remember-that
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: remember-that
Source: https://github.com/Aias/dotfiles/tree/main/agents/skills/remember-that
Command: npx skills add https://github.com/Aias/dotfiles --skill remember-that

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Extract and persist durable learnings from conversation context, so user preferences and corrections influence future interactions across sessions and projects.

Core Features & Use Cases

  • Analyze recent context to identify corrections, preferences, and recurring patterns.
  • Determine appropriate storage locations: GLOBAL.md for universal rules, or project-specific storage like AGENTS.md or hooks for enforcement.
  • Provide a workflow for applying remembered rules via skill triggers or direct edits to the appropriate files.

Quick Start

Tell the AI to persist this correction or preference to the appropriate storage (GLOBAL.md, AGENTS.md, or hooks) for future conversations.

Frequently Asked Questions about remember-that

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

FAQPage Schema
How do I persist user preferences and corrections across AI sessions?

To persist user preferences across sessions, extract corrections from conversation context and route them to appropriate long-term stores like GLOBAL.md or project-specific AGENTS.md files for future retrieval.

What is the difference between GLOBAL.md and AGENTS.md for memory persistence?

GLOBAL.md stores universal rules that apply across all sessions and projects, while AGENTS.md stores project-specific preferences and corrections to enforce context-aware behavior within a defined project scope.

How do I apply remembered rules using hooks in my project?

Apply remembered rules by routing identified preferences to project-specific storage like hooks or AGENTS.md files, triggering enforcement through skill triggers or direct edits to the appropriate configuration files.

Can I use context hooks to remember user corrections automatically?

Yes, context hooks analyze recent conversation history to identify recurring patterns and corrections, persisting durable learnings to appropriate storage locations for consistent application across sessions.

What are the limitations of persisting conversation context to long-term memory?

Limitations include potential sensitive data leakage, requiring safeguards to avoid leaking sensitive data, and the need for a defined workflow for storage selection, annotation, and update triggers to maintain accuracy.

Does remember-that work without external dependencies for memory storage?

Yes, the Skill operates without external dependencies, routing identified corrections and preferences directly to internal markdown files like GLOBAL.md and AGENTS.md for durable, cross-session memory persistence.