recall

Search and retrieve memories from past sessions across collections.

Updated Mar 5, 2026
One-click install
npx skills add https://github.com/lklimek/memcan --skill recall-lklimek
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: recall
Source: https://github.com/lklimek/memcan/tree/main/skills/recall
Command: npx skills add https://github.com/lklimek/memcan --skill recall-lklimek

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the challenge of agents forgetting information between sessions, ensuring continuity and leveraging past learnings.

Core Features & Use Cases

  • Memory Search: Efficiently search across all memory collections (memories, standards, code, todos) using natural language queries.
  • Contextual Recall: Retrieve relevant past decisions, project context, and error resolutions to inform current actions.
  • Use Case: When encountering a bug, use this Skill to search for similar past issues and their solutions, preventing repeated mistakes.

Quick Start

Use the recall skill to search for memories related to 'docker cache' within the 'penny' project.

Frequently Asked Questions about recall

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

FAQPage Schema
How do I retrieve past agent context and decisions from previous sessions?

To retrieve past agent context, you can search across all memory collections, including memories, standards, code, and todos, using natural language queries. This facilitates agent continuity by recalling past project decisions and error resolutions.

Can I search for past error resolutions to prevent repeating bug fixes?

Yes, you can search for past error resolutions to prevent repeated mistakes. By querying the memory collections for similar past issues, the agent retrieves previous solutions and applies that context to the current bug.

What is the best way to search project memories scoped to a specific codebase?

The best way to search project memories is by using targeted natural language queries scoped to a specific project. This narrows the retrieval to relevant context, standards, and todos directly related to that codebase.

Does memory search support filtering by collection type like code or todos?

Yes, memory search supports targeted searches by collection type. You can filter retrievals to specifically query code snippets, project standards, todos, or general memories to find exact project context.

Can I clean up outdated memories while retrieving session context?

Yes, you can opportunistically clean up outdated memories during retrieval. The search supports memory cleanup operations, allowing you to update or delete stale project context and error resolutions as you access them.