Search Memory

Search memory stores to retrieve past insights and decisions for current responses.

154|33|Updated Aug 7, 2025
One-click install
npx skills add https://github.com/nowledge-co/community --skill search-memory
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Search Memory
Source: https://github.com/nowledge-co/community/tree/main/nowledge-mem-claude-code-plugin/skills/search-memory
Command: npx skills add https://github.com/nowledge-co/community --skill search-memory

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Users often face recurring problems or need to recall past decisions, but manually searching through old conversations or documents is time-consuming and inefficient. This Skill proactively retrieves relevant past insights, preventing rework and accelerating problem-solving.

Core Features & Use Cases

  • Proactive Contextual Search: The AI autonomously searches your memory store when past insights would improve the current response, based on strong contextual signals, saving you from explicit search queries.
  • Leverage Stored Knowledge: Accesses previously distilled breakthroughs, decisions, and solutions to inform current tasks, ensuring you always build upon existing knowledge.
  • Use Case: You're debugging a complex issue, and Claude recognizes a pattern similar to a problem you solved months ago. It proactively searches your memories, finds the documented solution, and provides it, saving you hours of re-investigation and frustration.

Quick Start

The AI will autonomously search based on context:

"I'm encountering an error with database migrations."

AI might respond: "I found a memory from last month about a similar migration issue..."

You can also explicitly request:

"Search my memories for solutions to database connection problems." "What did we decide about the API design last week?"

Frequently Asked Questions about Search Memory

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

FAQPage Schema
How do I search through past conversations to find relevant insights?

Search memory retrieves past insights and decisions from your conversation history automatically. When you face a problem, Claude proactively searches for similar patterns you've solved before, surfacing documented solutions without requiring explicit queries, so you avoid rework and accelerate problem-solving.

Can Claude automatically find solutions to recurring problems I've encountered before?

Yes. Search memory autonomously detects contextual signals—like debugging patterns or architecture decisions—and retrieves relevant past insights. If you solved a similar database migration or connection issue months ago, Claude surfaces that documented solution immediately.

What kind of past decisions and solutions does search memory retrieve?

Search memory accesses distilled breakthroughs, design decisions, debugging solutions, and domain-specific reasoning stored across your conversations. It applies context-aware retrieval across continuity, pattern matching, decision rationale, and recurring themes in debugging, architecture, and technical questions.

How do I explicitly search my memory for specific topics or decisions?

You can request explicit searches using natural language: 'Search my memories for database connection problems' or 'What did we decide about the API design?' Search memory supports structured queries with configurable modes, limits, and query parameters to deliver concise, synthesized insights.

Does search memory work across different types of technical problems?

Search memory handles debugging, architecture discussions, and domain-specific questions. It enforces proactive context-aware retrieval and memory indexing, so it surfaces relevant insights whether you're troubleshooting errors, reviewing past design decisions, or solving recurring technical challenges.