remember

Consolidate session learnings into persistent documentation across CLAUDE.md and references.

Updated Jan 19, 2026
One-click install
npx skills add https://github.com/ddaanet/agent-core --skill remember-ddaanet
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: remember
Source: https://github.com/ddaanet/agent-core/tree/main/skills/remember
Command: npx skills add https://github.com/ddaanet/agent-core --skill remember-ddaanet

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Consolidate session learnings into persistent, actionable documentation to ensure learnings survive across sessions and are available for CLAUDE.md, skill references, and runbooks.

Core Features & Use Cases

  • Capture Learnings: Aggregate recent session learnings into structured, searchable documentation.
  • Update Core Docs: Refresh CLAUDE.md, context files, and targeted references with new rules and patterns.
  • Pattern Consolidation: Route insights to the correct skill references and decision files to support progressive disclosure.

Quick Start

Execute remember to consolidate the latest session learnings into CLAUDE.md and the appropriate skill references.

Frequently Asked Questions about remember

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

FAQPage Schema
How do I persist session learnings into CLAUDE.md documentation?

To persist session learnings into CLAUDE.md documentation, execute the consolidation process to capture new rules and patterns, drafting atomic updates that refresh core context files and targeted references.

How does knowledge management routing work for agent-core fragments?

Knowledge management routing works by directing aggregated insights to the correct skill references and decision files, ensuring progressive disclosure by updating the memory index and routing configuration.

Can I update domain references and runbooks automatically when capturing learnings?

Yes, you can update domain references and runbooks automatically. The consolidation process reads sources like agents/learnings.md and drafts precise, atomic updates across relevant context files.

What is the best way to consolidate session learnings into actionable documentation?

The best way to consolidate session learnings is to aggregate recent discoveries into structured documentation, routing insights to the correct decision files to ensure they survive across sessions.

Do I need existing memory index files to route insights to skill references?

You need existing memory index files to effectively route insights. The process updates the memory index and routing configuration to support progressive disclosure and ensure learnings are available.

Why does documentation update routing fail to preserve patterns across sessions?

Documentation update routing fails to preserve patterns when insights are not routed to the correct skill references and decision files, preventing the memory index from maintaining progressive disclosure.