recall

Retrieve top-k scored memory chunks from @seed/memory for current tasks.

Updated Apr 2, 2026
One-click install
npx skills add https://github.com/phyter1/seed --skill recall-phyter1
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: recall
Source: https://github.com/phyter1/seed/tree/main/.claude/skills/recall
Command: npx skills add https://github.com/phyter1/seed --skill recall-phyter1

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables users to access and retrieve the most relevant stored memories from @seed/memory, helping to provide contextual awareness for ongoing tasks or decisions.

Core Features & Use Cases

  • Memory Retrieval: Fetch top-k scored memory chunks based on user queries.
  • Contextual Insight: Use pasted memories to inform decisions, troubleshoot issues, or recall prior actions.
  • Use Case: When preparing a report, recall relevant past decisions or incidents related to the current project to ensure consistency and accuracy.

Quick Start

Ask the AI to recall the last relevant decisions or events related to your current 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 context and historical memories for current decision-making?

To retrieve past context for decision-making, query the stored memory sources to fetch top-k scored memory chunks. This provides historical context and relevant past interactions to inform your current tasks.

What is contextual memory retrieval and when do I need it for my tasks?

Contextual memory retrieval is the process of scoring and fetching relevant historical memory chunks to provide context for ongoing tasks. You need it when preparing reports or making decisions that require recalling past incidents.

Can I use stored memories to troubleshoot issues and ensure consistency across projects?

Yes, you can use retrieved memories to troubleshoot issues and ensure consistency. By recalling relevant past decisions or incidents, you maintain accuracy and align current actions with historical project context.

How does scoring relevance work when fetching historical context from memory sources?

Scoring relevance works by evaluating and ranking stored memory chunks against your specific query. It operates within a scope of defined memory sources to ensure precise information retrieval for decision support.

What are the limitations of using memory retrieval for contextual awareness?

A limitation of memory retrieval is that it operates strictly within defined memory sources, meaning it cannot access data outside its scoped boundaries. Relevance scoring is also limited to the chunks currently stored.